Ultra-high-resolution (UHR) text-to-image synthesis faces significant hurdles, including immense computational costs and a scarcity of training data. To address these, we introduce RealUHR, an efficient and scalable framework for generating photorealistic 4K images. At its core, RealUHR employs a Patch-Cascade Flow Matching pipeline that ensures global coherence without costly patch fusion by initiating generation from a semantically meaningful structure. This enables highly efficient, few-step inference for independent patches. Our key contribution is Guidance-Consistent Adaptation (GCA), a novel two-stage strategy to resolve the fundamental objective mismatch in guidance-distilled models. GCA allows powerful backbones like FLUX to be effectively adapted for patch-aware UHR synthesis. The framework's detail-rendering capabilities are further enhanced by a non-uniform time schedule. Experiments show that RealUHR establishes superior performance in both quality and efficiency, and excels in zero-shot applications such as creative up-sampling and generative artifact suppression.

Electronic Design Automation (EDA) requires early stage timing guidance to maximize optimization potential. Accurate timing estimation is essential in the High-Level Synthesis (HLS) stage. However, current HLS tools often produce inaccurate timing predictions, resulting in unmet performance targets. While post-synthesis EDA tool chains can provide precise timing analysis, their exhaustive methodologies are prohibitively time-consuming and computationally expensive. Recent machine learning approaches have demonstrated promising results in predicting design-level timing metrics in HLS designs, such as Worst Negative Slack (WNS) and Critical Path (CP) delay. Nevertheless, fine-grained, path-level timing estimation remains an unresolved challenge. In this work, we present HLS-Timer, the first path-level timing estimator for HLS. The proposed framework employs a graph-based representation of the HLS design, integrating local structural features with global contextual information to model timing paths and provide accurate, finegrained delay predictions. Experimental results demonstrate that on previously unseen designs HLS-Timer achieves exceptional accuracy in path-level delay estimation (Pearson $\mathbf{R}=\mathbf{0. 9 4}, \mathbf{R}^{\mathbf{2}} =0.93$, MAPE $=18.96 \%$), highlighting its strong generalization capability. Furthermore, it surpasses state-of-the-art baselines in design-level timing prediction, reducing MAPE to $9.97 \%$ for WNS and $6.79 \%$ for CP delays.

High-level synthesis (HLS) streamlines accelerator customization by delivering a high-level hardware programming paradigm enriched with a variety of optimization directives. However, the quality of HLS designs is largely determined by the selection of directives in navigating trade-offs among multiple design metrics, a non-trivial process that can significantly prolong design turnaround time. Design space exploration (DSE) serves as a promising solution to this problem, but existing studies on DSE suffer from a lack of efficiency or generalization capability in large-scale application scenarios. To address this problem, this paper proposes AutoShrink, a DSE engine that automatically and adaptively shrinks the large search space of an HLS design to gradually retain only high-quality solutions. AutoShrink incorporates: (1) a comprehensive design space pruning strategy that integrates domain knowledge and consolidates the joint effect of directives; and (2) an importance-guided Pareto optimization algorithm that dynamically tracks the importance ranking of the applied directives and leverages this ranking to effectively steer the search toward Pareto-optimal solutions. Experimental results demonstrate that AutoShrink efficiently achieves a close approximation of the Pareto frontier across diverse benchmarks with design spaces scaling up to 1016, which attains an average deviation of only 8.1%, outperforming three generic optimization methods and three state-of-the-art customized approaches by 5.73× and 4.47×, respectively.

We introduce UniReal, a unified framework designed to address various image generation and editing tasks. Existing solutions often vary by tasks, yet share fundamental principles: preserving consistency between inputs and outputs while capturing visual variations. Inspired by recent video generation models that effectively balance consistency and variation across frames, we propose a unifying approach that treats image-level tasks as discontinuous video generation. Specifically, we treat varying numbers of input and output images as frames, enabling seamless support for tasks such as image generation, editing, customization, composition, etc. Although designed for image-level tasks, we leverage videos as a scalable source for universal supervision. UniReal learns world dynamics from large-scale videos, demonstrating advanced capability in handling shadows, reflections, pose variation, and object interaction, while also exhibiting emergent capability for novel applications.

The advent of large Vision-Language Models (VLMs) has significantly advanced multimodal tasks, enabling more sophisticated and accurate reasoning across various applications, including image and video captioning, visual question answering, and cross-modal retrieval. Despite their superior capabilities, VLMs struggle with fine-grained image regional composition information perception. Specifically, they have difficulty accurately aligning the segmentation masks with the corresponding semantics and precisely describing the compositional aspects of the referred regions. However, compositionality – the ability to understand and generate novel combinations of known visual and textual components – is critical for facilitating coherent reasoning and understanding across modalities by VLMs. To address this issue, we propose FineCaption, a novel VLM that can recognize arbitrary masks as referential inputs and process high-resolution images for compositional image captioning at different granularity levels. To support this endeavor, we introduce CompositionCap, a new dataset for multi-grained region compositional image captioning, which introduces the task of compositional attribute-aware regional image captioning. Empirical results demonstrate the effectiveness of our proposed model compared to other state-of-the-art VLMs. Additionally, we analyze the capabilities of current VLMs in recognizing various visual prompts for compositional region image captioning, highlighting areas for improvement in VLM design and training. https://hanghuacs.github.io/FineCaption/

Large-scale video generation models have the inherent ability to realistically model natural scenes. In this paper, we demonstrate that through a careful design of a generative video propagation framework, various video tasks can be addressed in a unified way by leveraging the generative power of such models. Specifically, our framework, Gen-Prop, encodes the original video with a selective content encoder and propagates the changes made to the first frame using an image-to-video generation model. We propose a data generation scheme to cover multiple video tasks based on instance-level video segmentation datasets. Our model is trained by incorporating a mask prediction decoder head and optimizing a region-aware loss to aid the encoder to preserve the original content while the generation model propagates the modified region. This novel design opens up new possibilities: In editing scenarios, GenProp allows substantial changes to an object’s shape; for insertion, the inserted objects can exhibit independent motion; for removal, GenProp effectively removes effects like shadows and reflections from the whole video; for tracking, GenProp is capable of tracking objects and their associated effects together. Experiment results demonstrate the leading performance of our model in various video tasks, and we further provide in-depth analyses of the proposed framework.

We introduce the first generative model capable of simultaneous multi-object compositing, guided by both text and layout. Our model allows for the addition of multiple objects within a scene, capturing a range of interactions from simple positional relations (e.g., next to, in front of) to complex actions requiring reposing (e.g., hugging, playing guitar). When an interaction implies additional props, like ‘taking a selfie’, our model autonomously generates these supporting objects. By jointly training for compositing and subject-driven generation, also known as customization, we achieve a more balanced integration of textual and visual inputs for text-driven object compositing. As a result, we obtain a versatile model with state-of-the-art performance in both tasks. We further present a data generation pipeline leveraging visual and language models to effortlessly synthesize multimodal, aligned training data.

Text-to-video generative models have made significant strides, enabling diverse applications in entertainment, advertising, and education. However, generating RGBA video, which includes alpha channels for transparency, remains a challenge due to limited datasets and the difficulty of adapting existing models. Alpha channels are crucial for visual effects (VFX), allowing transparent elements like smoke and reflections to blend seamlessly into scenes. We introduce TransPixeler, a method to extend pretrained video models for RGBA generation while retaining the original RGB capabilities. TransPixeler leverages a diffusion transformer (DiT) architecture, incorporating alpha-specific tokens and using LoRA-based fine-tuning to jointly generate RGB and alpha channels with high consistency. By optimizing attention mechanisms, TransPixeler preserves the strengths of the original RGB model and achieves strong alignment between RGB and alpha channels despite limited training data. Our approach effectively generates diverse and consistent RGBA videos, advancing the possibilities for VFX and interactive content creation. The code is available at https://wileewang.github.io/TransPixeler/.

Shadows are often under-considered or even ignored in image editing applications, limiting the realism of the edited results. In this paper, we introduce MetaShadow, a three-in-one versatile framework that enables detection, removal, and controllable synthesis of shadows in natural images in an object-centered fashion. MetaShadow combines the strengths of two cooperative components: Shadow Analyzer, for object-centered shadow detection and removal, and Shadow Synthesizer, for reference-based controllable shadow synthesis. Notably, we optimize the learning of the intermediate features from Shadow Analyzer to guide Shadow Synthesizer to generate more realistic shadows that blend seamlessly with the scene. Extensive evaluations on multiple shadow benchmark datasets show significant improvements of MetaShadow over the existing state-of-the-art methods on object-centered shadow detection, removal, and synthesis. MetaShadow excels in image-editing tasks such as object removal, relocation, and insertion, pushing the boundaries of object-centered image editing.

This paper introduces TurboFill, a fast image inpainting model that enhances a few-step text-to-image diffusion model with an inpainting adapter for high-quality and efficient inpainting. While standard diffusion models generate high-quality results, they incur high computational costs. We overcome this by training an inpainting adapter on a few-step distilled text-to-image model, DMD2, using a novel 3-step adversarial training scheme to ensure realistic, structurally consistent, and visually harmonious inpainted regions. To evaluate TurboFill, we propose two benchmarks: DilationBench, which tests performance across mask sizes, and HumanBench, based on human feedback for complex prompts. Experiments show that TurboFill outperforms both multi-step BrushNet and few-step inpainting methods, setting a new benchmark for high-performance inpainting tasks. The project page is available here.

Recent advancements in large generative models, particularly diffusion-based methods, have significantly enhanced the capabilities of image editing. However, achieving precise control over image composition tasks remains a challenge. Layered representations, which allow for independent editing of image components, are essential for user-driven content creation, yet existing approaches often struggle to decompose an image into plausible layers with accurately retained transparent visual effects such as shadows and reflections. We propose LayerDecomp, a generative framework for image layer decomposition which outputs photorealistic clean backgrounds and high-quality transparent foregrounds with faithfully preserved visual effects. To enable effective training, we first introduce a dataset preparation pipeline that automatically scales up simulated multi-layer data with synthesized visual effects. To further enhance real-world applicability, we supplement this simulated dataset with camera-captured images containing natural visual effects. Additionally, we propose a consistency loss which enforces the model to learn accurate representations for the transparent foreground layer when ground-truth annotations are not available. Our method achieves superior quality in layer decomposition, outperforming existing approaches in object removal and spatial editing tasks across several benchmarks and multiple user studies, unlocking various creative possibilities for layer-wise image editing.

Diffusion Transformers (DiTs) have achieved state-of-the-art (SOTA) image generation quality but suffer from high latency and memory inefficiency, making them difficult to deploy on resource-constrained devices. One major efficiency bottleneck is that existing DiTs apply equal computation across all regions of an image. However, not all image tokens are equally important, and certain localized areas require more computation, such as objects. To address this, we propose DiffCR, a dynamic DiT inference framework with differentiable compression ratios, which automatically learns to dynamically route computation across layers and timesteps for each image token, resulting in efficient DiTs. Specifically, DiffCR integrates three features: (1) A token-level routing scheme where each DiT layer includes a router that is fine-tuned jointly with model weights to predict token importance scores. In this way, unimportant tokens bypass the entire layer’s computation; (2) A layer-wise differentiable ratio mechanism where different DiT layers automatically learn varying compression ratios from a zero initialization, resulting in large compression ratios in redundant layers while others remain less compressed or even uncompressed; (3) A timestep-wise differentiable ratio mechanism where each denoising timestep learns its own compression ratio. The resulting pattern shows higher ratios for noisier timesteps and lower ratios as the image becomes clearer. Extensive experiments on text-to-image and inpainting tasks show that DiffCR effectively captures dynamism across token, layer, and timestep axes, achieving superior tradeoffs between generation quality and efficiency compared to prior works. The project website is available here.

Simple as it seems, moving an object to another location within an image is, in fact, a challenging image-editing task that requires re-harmonizing the lighting, adjusting the pose based on perspective, accurately filling occluded regions, and ensuring coherent synchronization of shadows and reflections while maintaining the object identity. In this paper, we present ObjectMover, a generative model that can perform object movement in highly challenging scenes. Our key insight is that we model this task as a sequence-to-sequence problem and fine-tune a video generation model to leverage its knowledge of consistent object generation across video frames. We show that with this approach, our model is able to adjust to complex real-world scenarios, handling extreme lighting harmonization and object effect movement. As large-scale data for object movement are unavailable, we construct a data generation pipeline using a modern game engine to synthesize high-quality data pairs. We further propose a multi-task learning strategy that enables training on real-world video data to improve the model generalization. Through extensive experiments, we demonstrate that ObjectMover achieves outstanding results and adapts well to real-world scenarios.

Singular value decomposition (SVD) is a matrix factorization technique widely used in signal processing and recommendation systems, etc. In general, the time complexity of SVD algorithms is cubic to the problem size, making SVD algorithms difficult to meet stringent performance requirements in real-time. However, existing FPGA and GPU solutions fall short of jointly optimizing latency, throughput, and power consumption. To settle this issue, this paper proposes HeteroSVD, a heterogeneous reconfigurable accelerator for SVD computation on the Versal ACAP platform. HeteroSVD introduces a system-level SVD decomposition mechanism and proposes an algorithm-hardware co-design method to optimize SVD ordering jointly and AI engine (AIE)-centric dataflow and placement with Versal. Furthermore, in order to improve the quality of results (QoR) and facilitate micro-architecture selection, we introduce an automatic optimization framework that performs accurate performance modeling and fast design space exploration. Experiment results demonstrate that HeteroSVD reduces the latency by $1.98 \times$ over existing FPGA accelerators and outperforms GPU solutions with an improvement of up to $7.22 \times$ in latency, $1.77 \times$ in throughput, and $13.18 \times$ in energy efficiency.

Sparse general matrix-matrix multiplication (SpGEMM) serves as a fundamental operation in real-world applications such as deep learning. Different from general matrix multiplication, matrices in SpGEMM are highly sparse and therefore require a compact representation. This places an additional burden on data preprocessing and exchanging and also causes irregular memory access patterns, which can in turn lead to communication and computation bottlenecks. To break these bottlenecks, we present VSpGEMM, a hardware accelerator for SpGEMM that is tailored and optimized on Versal ACAP. Firstly, a new storage format called BCSX is proposed in VSpGEMM, which offers a unified and block-wise compression strategy to deal with both row-major and columnmajor representation of non-zero data, enabling fixed-pattern memory accesses and effective data preloading. Secondly, a multi-level tiling mechanism is introduced to decompose the holistic SpGEMM into multiple computation granularities that fit into the AI Engines (AIEs) on Versal in a hierarchical manner, enhancing data reuse. Thirdly, a hybrid partitioning scheme is presented to orchestrate both the AIEs and programmable logic (PL) for intermediate product merging, which together resolve the issues of high memory utilization and communication demand. Experimental results demonstrate a $2.65 \times$ speedup over state-of-the-art (SOTA) GEMM design on Versal and an average $33.62 \times$ improvement in energy efficiency compared to cuSPARSE on RTX 4090 GPU, showing the efficacy of VSpGEMM.

Diffusion probabilistic models have shown significant progress in video generation; however, their computational efficiency is limited by the large number of sampling steps required. Reducing sampling steps often compromises video quality or generation diversity. In this work, we introduce a distillation method that combines variational score distillation and consistency distillation to achieve few-step video generation, maintaining both high quality and diversity. We also propose a latent reward model fine-tuning approach to further enhance video generation performance according to any specified reward metric. This approach reduces memory usage and does not require the reward to be differentiable. Our method demonstrates state-of-the-art performance in few-step generation for 10-second videos (128 frames at 12 FPS). The distilled student model achieves a score of 82.57 on VBench, surpassing the teacher model as well as baseline models Gen-3, T2V-Turbo, and Kling. One-step distillation accelerates the teacher model's diffusion sampling by up to 278.6 times, enabling near real-time generation. Human evaluations further validate the superior performance of our 4-step student models compared to teacher model using 50-step DDIM sampling.

Personalized image generation has emerged from the recent advancements in generative models. However, these generated personalized images often suffer from localized artifacts such as incorrect logos, reducing fidelity and fine-grained identity details of the generated results. Furthermore, there is little prior work tackling this problem. To help improve these identity details in the personalized image generation, we introduce a new task: reference-guided artifacts refinement. We present Refine-by-Align, a first-of-its-kind model that employs a diffusion-based framework to address this challenge. Our model consists of two stages: Alignment Stage and Refinement Stage, which share weights of a unified neural network model. Given a generated image, a masked artifact region, and a reference image, the alignment stage identifies and extracts the corresponding regional features in the reference, which are then used by the refinement stage to fix the artifacts. Our model-agnostic pipeline requires no test-time tuning or optimization. It automatically enhances image fidelity and reference identity in the generated image, generalizing well to existing models on various tasks including but not limited to customization, generative compositing, view synthesis, and virtual try-on. Extensive experiments and comparisons demonstrate that our pipeline greatly pushes the boundary of fine details in the image synthesis models.

Latent Diffusion Models (LDMs) have markedly advanced the quality of image inpainting and local editing. However, the inherent latent compression often introduces pixel-level inconsistencies, such as chromatic shifts, texture mismatches, and visible seams along editing boundaries. Existing remedies, including background-conditioned latent decoding and pixel-space harmonization, usually fail to fully eliminate these artifacts in practice and do not generalize well across different latent representations or tasks. We introduce PixPerfect, a pixel‐level refinement framework that delivers seamless, high-fidelity local edits across diverse LDM architectures and tasks. PixPerfect leverages (i) a differentiable discriminative pixel space that amplifies and suppresses subtle color and texture discrepancies, (ii) a comprehensive artifact simulation pipeline that exposes the refiner to realistic local editing artifacts during training, and (iii) a direct pixel-space refinement scheme that ensures broad applicability across diverse latent representations and tasks. Extensive experiments on inpainting, object removal, and insertion benchmarks demonstrate that PixPerfect substantially enhances perceptual fidelity and downstream editing performance, establishing a new standard for robust and high-fidelity localized image editing.

Amodal scene analysis entails interpreting the occlusion relationship among scene elements and inferring the possible shapes of the invisible parts. Existing methods typically frame this task as an extended instance segmentation or a pair-wise object de-occlusion problem. In this work, we propose a new framework, which comprises a Holistic Occlusion Relation Inference (HORI) module followed by an instance-level Generative Mask Completion (GMC) module. Unlike previous approaches, which rely on mask completion results for occlusion reasoning, our HORI module directly predicts an occlusion relation matrix in a single pass. This approach is much more efficient than the pair-wise de-occlusion process and it naturally handles mutual occlusion, a common but often neglected situation. Moreover, we formulate the mask completion task as a generative process and use a diffusion-based GMC module for instance-level mask completion. This improves mask completion quality and provides multiple plausible solutions. We further introduce a large-scale amodal segmentation dataset with high-quality human annotations, including mutual occlusions. Experiments on our dataset and two public benchmarks demonstrate the advantages of our method. code public available at https://github.com/zbwxp/Amodal-AAAI.

Human image editing includes tasks like changing a person's pose, their clothing, or editing the image according to a text prompt. However, prior work often tackles these tasks separately, overlooking the benefit of mutual reinforcement from learning them jointly. In this paper, we propose UniHuman, a unified model that addresses multiple facets of human image editing in real-world settings. To enhance the model's generation quality and generalization capacity, we leverage guidance from human visual encoders and introduce a lightweight pose-warping module that can exploit different pose representations, accommodating unseen textures and patterns. Furthermore, to bridge the disparity between existing human editing benchmarks with real-world data, we curated 400K high-quality human image-text pairs for training and collected 2K human images for out-of-domain testing, both encompassing diverse clothing styles, backgrounds, and age groups. Experiments on both in-domain and out-of-domain test sets demonstrate that UniHuman outperforms task-specific models by a significant margin. In user studies, UniHuman is preferred by the users in an average of 77% of cases. Our project is available at this link.

Object inpainting is a task that involves adding objects to real images and seamlessly compositing them. With the recent commercialization of products like Stable Diffusion and Generative Fill, inserting objects into images by using prompts has achieved impressive visual results. In this paper, we propose a prompt suggestion model to simplify the process of prompt input. When the user provides an image and a mask, our model predicts suitable prompts based on the partial contextual information in the masked image, and the shape and location of the mask. Specifically, we introduce a concept-diffusion in the CLIP space that predicts CLIP-text embeddings from a masked image. These diffused embeddings can be directly injected into open-source in-painting models like Stable Diffusion and its variants. Alternatively, they can be decoded into natural language for use in other publicly available applications such as Generative Fill. Our prompt suggestion model demonstrates a balanced accuracy and diversity, showing its capability to be both contextually aware and creatively adaptive.

Video-P2P is the first framework for real-world video editing with cross-attention control. While attention control has proven effective for image editing with pre-trained image generation models, there are currently no large-scale video generation models publicly available. Video-P2P addresses this limitation by adapting an image generation diffusion model to complete various video editing tasks. Specifically, we propose to first tune a Text-to-Set (T2S) model to complete an approximate inversion and then optimize a shared unconditional embedding to achieve accurate video inversion with a small memory cost. We further prove that it is crucial for consistent video editing. For attention control, we introduce a novel decoupled-guidance strategy, which uses different guidance strategies for the source and target prompts. The optimized unconditional embedding for the source prompt improves reconstruction ability, while an initialized unconditional embedding for the target prompt enhances editability. Incorporating the attention maps of these two branches enables detailed editing. These technical designs enable various text-driven editing applications, including word swap, prompt refinement, and attention re-weighting. Video-P2P works well on real-world videos for generating new characters while optimally preserving their original poses and scenes. It significantly outperforms previous approaches.

Generative object compositing emerges as a promising new avenue for compositional image editing. However, the requirement of object identity preservation poses a significant challenge, limiting practical usage of most existing methods. In response, this paper introduces IMPRINT, a novel diffusion-based generative model trained with a two-stage learning framework that decouples learning of identity preservation from that of compositing. The first stage is targeted for context-agnostic, identity-preserving pretraining of the object encoder, enabling the encoder to learn an embedding that is both view-invariant and conducive to enhanced detail preservation. The subsequent stage leverages this representation to learn seamless harmonization of the object composited to the background. In addition, IMPRINT incorporates a shape-guidance mechanism offering user-directed control over the compositing process. Extensive experiments demonstrate that IMPRINT significantly outperforms existing methods and various baselines on identity preservation and composition quality. Project page: https://song630.github.io/IMPRINT-Project-Page/

Diffusion models (DMs) have exhibited superior performance in generating high-quality and diverse images. How-ever, this exceptional performance comes at the cost of expensive generation process, particularly due to the heavily used attention module in leading models. Existing works mainly adopt a retraining process to enhance DM efficiency. This is computationally expensive and not very scalable. To this end, we introduce the Attention-driven Training-free Efficient Diffusion Model (AT-EDM) framework that leverages attention maps to perform run-time pruning of redundant tokens, without the need for any retraining. Specifically, for single-denoising-step pruning, we develop a novel ranking algorithm, Generalized Weighted Page Rank (G-WPR), to identify redundant tokens, and a similarity-based recovery method to restore tokens for the convolution operation. In addition, we propose a Denoising-Steps-Aware Pruning (DSAP) approach to adjust the pruning budget across different denoising timesteps for better generation quality. Extensive evaluations show that AT-EDM performs favorably against prior art in terms of efficiency (e.g., 38.8% FLOPs saving and up to 1.53× speed-up over Stable Diffusion XL) while maintaining nearly the same FID and CLIP scores as the full model. Project webpage: https://atedm.github.io.

Understanding the functionality of Boolean networks is crucial for processes such as functional equivalence checking, logic synthesis and malicious logic identification. With the proliferation of deep learning in electronic design automation (EDA), graph neural networks (GNNs) are widely used for embedding the and-inverter graphs (AIGs), a standard form of Boolean networks, into vectorized representation. A key challenge in the use of GNN for Boolean representation is that although GNNs can well encapsulate the structural properties of AIGs, they usually fail to fully capture the functionality of Boolean logic. Moreover, most GNNs designed for AIGs (also called AIGNNs) either rely on a large amount of training data or require complex supervisory tasks, making it difficult to maintain high training efficiency and prediction accuracy. In this work, for the first time, we focus on breaking the bottleneck of AIGNNs by augmenting their capability of functional representation, providing an efficient solution called PolarGate, which naturally aligns the message passing process with the logical functionality of AIGs. Specifically, we map the behavior of the logic gate into an ambipolar state space, customize differentiable logical operators, and design a functionality-aware message passing strategy. Experimental results on two logically related tasks (i.e., signal probability prediction and truth-table distance prediction) show that PolarGate outperforms the state-of-the-art GNN-based methods for Boolean representation, with an improvement of 62.1% (40.6%) in learning capability and 79.5% (85.6%) in efficiency on two tasks. The code is avaliable at https://github.com/BUPT-GAMMA/PolarGate.

Generative adversarial networks (GANs) have made great success in image inpainting yet still have difficulties tackling large missing regions. In contrast, iterative probabilistic algorithms, such as autoregressive and denoising diffusion models, have to be deployed with massive computing resources for decent effect. To achieve high-quality results with low computational cost, we present a novel pixel spread model (PSM) that iteratively employs decoupled probabilistic modeling, combining the optimization efficiency of GANs with the prediction tractability of probabilistic models. As a result, our model selectively spreads informative pixels throughout the image in a few iterations, largely enhancing the completion quality and efficiency. On multiple benchmarks, we achieve new state-of-the-art performance. Our code and models will be publicly available.

Recovering textures under shadows has remained a challenging problem due to the difficulty of inferring shadow-free scenes from shadow images. In this paper, we propose the use of diffusion models as they offer a promising approach to gradually refine the details of shadow regions during the diffusion process. Our method improves this process by conditioning on a learned latent feature space that inherits the characteristics of shadow-free images, thus avoiding the limitation of conventional methods that condition on degraded images only. Additionally, we propose to alleviate potential local optima during training by fusing noise features with the diffusion network. We demonstrate the effectiveness of our approach which outperforms the previous best method by 13% in terms of RMSE on the AISTD dataset. Further, we explore instance-level shadow removal, where our model outperforms the previous best method by 82% in terms of RMSE on the DESOBA dataset.

We propose Subject-Conditional Relation Detection (SCoRD), where conditioned on an input subject, the goal is to predict all its relations to other objects in a scene along with their locations. Based on the Open Images dataset, we propose a challenging OIv6-SCoRD benchmark such that the training and testing splits have a distribution shift in terms of the occurrence statistics of subject, relation, object triplets. To solve this problem, we propose an auto-regressive model that given a subject, it predicts its relations, objects, and object locations by casting this output as a sequence of tokens. First, we show that previous scene-graph prediction methods fail to produce as exhaustive an enumeration of relation-object pairs when conditioned on a subject on this benchmark. Particularly, we obtain a recall@3 of 83.8% for our relation-object predictions compared to the 49.75% obtained by a recent scene graph detector. Then, we show improved generalization on both relation-object and object-box predictions by leveraging during training relation-object pairs obtained automatically from textual captions and for which no object-box annotations are available. Particularly, for subject, relation, object triplets for which no object locations are available during training, we are able to obtain a recall@3 of 33.80% for relation-object pairs and 26.75% for their box locations.

Structure-guided image completion aims to inpaint a local region of an image according to an input guidance map from users. While such a task enables many practical applications for interactive editing, existing methods often struggle to hallucinate realistic object instances in complex natural scenes. Such a limitation is partially due to the lack of semantic-level constraints inside the hole region as well as the lack of a mechanism to enforce realistic object generation. In this work, we propose a learning paradigm that consists of semantic discriminators and object-level discriminators for improving the generation of complex semantics and objects. Specifically, the semantic discriminators leverage pretrained visual features to improve the realism of the generated visual concepts. Moreover, the object-level discriminators take aligned instances as inputs to enforce the realism of individual objects. Our proposed scheme significantly improves the generation quality and achieves state-of-the-art results on various tasks, including segmentation-guided completion, edge-guided manipulation and panoptically-guided manipulation on Places2 datasets. Furthermore, our trained model is flexible and can support multiple editing use cases, such as object insertion, replacement, removal and standard inpainting. In particular, our trained model combined with a novel automatic image completion pipeline achieves state-of-the-art results on the standard inpainting task.

Wires and powerlines are common visual distractions that often undermine the aesthetics of photographs. The manual process of precisely segmenting and removing them is extremely tedious and may take up hours, especially on high-resolution photos where wires may span the entire space. In this paper, we present an automatic wire clean-up system that eases the process of wire segmentation and removal/inpainting to within a few seconds. We observe several unique challenges: wires are thin, lengthy, and sparse. These are rare properties of subjects that common segmentation tasks cannot handle, especially in high-resolution images. We thus propose a two-stage method that leverages both global and local contexts to accurately segment wires in high-resolution images efficiently, and a tile-based inpainting strategy to remove the wires given our predicted segmentation masks. We also introduce the first wire segmentation benchmark dataset, WireSegHR. Finally, we demonstrate quantitatively and qualitatively that our wire clean-up system enables fully automated wire removal with great generalization to various wire appearances.

In photo editing, it is common practice to remove visual distractions to improve the overall image quality and highlight the primary subject. However, manually selecting and removing these small and dense distracting regions can be a laborious and time-consuming task. In this paper, we propose an interactive distractor selection method that is optimized to achieve the task with just a single click. Our method surpasses the precision and recall achieved by the traditional method of running panoptic segmentation and then selecting the segments containing the clicks. We also showcase how a transformer-based module can be used to identify more distracting regions similar to the user's click position. Our experiments demonstrate that the model can effectively and accurately segment unknown distracting objects interactively and in groups. By significantly simplifying the photo cleaning and retouching process, our proposed model provides inspiration for exploring rare object segmentation and group selection with a single click. More information can be found at https://github.com/hmchuong/SimpSON.

Object compositing based on 2D images is a challenging problem since it typically involves multiple processing stages such as color harmonization, geometry correction and shadow generation to generate realistic results. Furthermore, annotating training data pairs for compositing requires substantial manual effort from professionals, and is hardly scalable. Thus, with the recent advances in generative models, in this work, we propose a selfsupervised framework for object compositing by leveraging the power of conditional diffusion models. Our framework can hollistically address the object compositing task in a unified model, transforming the viewpoint, geometry, color and shadow of the generated object while requiring no manual labeling. To preserve the input object's characteristics, we introduce a content adaptor that helps to maintain categori-cal semantics and object appearance. A data augmentation method is further adopted to improve the fidelity of the generator. Our method outperforms relevant baselines in both realism and faithfulness of the synthesized result images in a user study on various real-world images.

Generative models have been widely studied in computer vision. Recently, diffusion models have drawn substantial attention due to the high quality of their generated images. A key desired property of image generative models is the ability to disentangle different attributes, which should enable modification towards a style without changing the semantic content, and the modification parameters should generalize to different images. Previous studies have found that generative adversarial networks (GANs) are inherently endowed with such disentanglement capability, so they can perform disentangled image editing without re-training or fine-tuning the network. In this work, we explore whether diffusion models are also inherently equipped with such a capability. Our finding is that for stable diffusion models, by partially changing the input text embedding from a neutral description (e.g., “a photo of person”) to one with style (e.g., “a photo of person with smile”) while fixing all the Gaussian random noises introduced during the denoising process, the generated images can be modified towards the target style without changing the semantic content. Based on this finding, we further propose a simple, light-weight image editing algorithm where the mixing weights of the two text embeddings are optimized for style matching and content preservation. This entire process only involves optimizing over around 50 parameters and does not fine-tune the diffusion model itself. Experiments show that the proposed method can modify a wide range of attributes, with the performance outperforming diffusion-model-based image-editing algorithms that require fine-tuning. The optimized weights generalize well to different images. Our code is publicly available at https://github.com/UCSB-NLP-Chang/DiffusionDisentanglement.

Generic image inpainting aims to complete a corrupted image by borrowing surrounding information, which barely generates novel content. By contrast, multi-modal inpainting provides more flexible and useful controls on the inpainted content, e.g., a text prompt can be used to describe an object with richer attributes, and a mask can be used to constrain the shape of the inpainted object rather than being only considered as a missing area. We propose a new diffusion-based model named SmartBrush for completing a missing region with an object using both text and shape-guidance. While previous work such as DALLE-2 and Stable Diffusion can do text-guided inapinting they do not support shape guidance and tend to modify background texture surrounding the generated object. Our model incorporates both text and shape guidance with precision control. To preserve the background better, we propose a novel training and sampling strategy by augmenting the diffusion U-net with object-mask prediction. Lastly, we introduce a multi-task training strategy by jointly training inpainting with text-to-image generation to leverage more training data. We conduct extensive experiments showing that our model outperforms all baselines in terms of visual quality, mask controllability, and background preservation.

We propose a new framework for conditional image synthesis from semantic layouts of any precision levels, ranging from pure text to a 2D semantic canvas with precise shapes. More specifically, the input layout consists of one or more semantic regions with free-form text descriptions and adjustable precision levels, which can be set based on the desired controllability. The framework naturally reduces to text-to-image (T2I) at the lowest level with no shape information, and it becomes segmentation-to-image (S2I) at the highest level. By supporting the levels in-between, our framework is flexible in assisting users of different drawing expertise and at different stages of their creative workflow. We introduce several novel techniques to address the challenges coming with this new setup, including a pipeline for collecting training data; a precision-encoded mask pyramid and a text feature map representation to jointly encode precision level, semantics, and composition information; and a multi-scale guided diffusion model to synthesize images. To evaluate the proposed method, we collect a test dataset containing user-drawn layouts with diverse scenes and styles. Experimental results show that the proposed method can generate high-quality images following the layout at given precision, and compares favorably against existing methods. Project page https://zengxianyu.github.io/scenec/

We investigate the problem of automatically placing an object into a background image for image compositing. Given a background image and a segmented object, the goal is to train a model to predict plausible placements (location and scale) of the object for compositing. The quality of the composite image highly depends on the predicted location/scale. Existing works either generate candidate bounding boxes or apply sliding-window search using global representations from background and object images, which fail to model local information in background images. However, local clues in background images are important to determine the compatibility of placing the objects with certain locations/scales. In this paper, we propose to learn the correlation between object features and all local background features with a transformer module so that detailed information can be provided on all possible location/scale configurations. A sparse contrastive loss is further proposed to train our model with sparse supervision. Our new formulation generates a 3D heatmap indicating the plausibility of all location/scale combinations in one network forward pass, which is > 10 x faster than the previous sliding-window method. It also supports interactive search when users provide a pre-defined location or scale. The proposed method can be trained with explicit annotation or in a self-supervised manner using an off-the-shelf inpainting model, and it outperforms state-of-the-art methods significantly. User study shows that the trained model generalizes well to real-world images with diverse challenging scenes and object categories.

Dense image segmentation tasks (e.g., semantic, panoptic) are useful for image editing, but existing methods can hardly generalize well in an in-the-wild setting where there are unrestricted image domains, classes, and image resolution & quality variations. Motivated by these observations, we construct a new entity segmentation dataset, with a strong focus on high-quality dense segmentation in the wild. The dataset contains images spanning diverse image domains and entities, along with plentiful high-resolution images and high-quality mask annotations for training and testing. Given the high-quality and -resolution nature of the dataset, we propose CropFormer which is designed to tackle the intractability of instance-level segmentation on high-resolution images. It improves mask prediction by fusing high-res image crops that provides more fine-grained image details and the full image. CropFormer is the first query-based Transformer architecture that can effectively fuse mask predictions from multiple image views, by learning queries that effectively associate the same entities across the full image and its crop. With CropFormer, we achieve a significant AP gain of 1.9 on the challenging entity segmentation task. Furthermore, CropFormer consistently improves the accuracy of traditional segmentation tasks and datasets. The dataset and code are released at http://luqi.info/entityv2.github.io/.

Diffusion-based models have achieved state-of-the-art performance on text-to-image synthesis tasks. However, one critical limitation of these models is the low fidelity of generated images with respect to the text description, such as missing objects, mismatched attributes, and mislocated objects. One key reason for such inconsistencies is the inaccurate cross-attention to text in both the spatial dimension, which controls at what pixel region an object should appear, and the temporal dimension, which controls how different levels of details are added through the denoising steps. In this paper, we propose a new text-to-image algorithm that adds explicit control over spatial-temporal cross-attention in diffusion models. We first utilize a layout predictor to predict the pixel regions for objects mentioned in the text. We then impose spatial attention control by combining the attention over the entire text description and that over the local description of the particular object in the corresponding pixel region of that object. The temporal attention control is further added by allowing the combination weights to change at each denoising step, and the combination weights are optimized to ensure high fidelity between the image and the text. Experiments show that our method generates images with higher fidelity compared to diffusion-model-based baselines without fine-tuning the diffusion model. Our code is publicly available.1

Recent advancements in deep generative models have facilitated the creation of photo-realistic images across various tasks. However, these generated images often exhibit perceptual artifacts in specific regions, necessitating manual correction. In this study, we present a comprehensive empirical examination of Perceptual Artifacts Localization (PAL) spanning diverse image synthesis endeavors. We introduce a novel dataset comprising 10, 168 generated images, each annotated with per-pixel perceptual artifact labels across ten synthesis tasks. A segmentation model, trained on our proposed dataset, effectively localizes artifacts across a range of tasks. Additionally, we illustrate its proficiency in adapting to previously unseen models using minimal training samples. We further propose an innovative zoom-in inpainting pipeline that seamlessly rectifies perceptual artifacts in the generated images. Through our experimental analyses, we elucidate several invaluable downstream applications, such as automated artifact rectification, non-referential image quality evaluation, and abnormal region detection in images. The dataset and code are released here: https://owenzlz.github.io/PAL4VST

Despite the progress of image segmentation for accurate visual entity segmentation, completing the diverse requirements of image editing applications for different-level region-of-interest selections remains unsolved. In this paper, we propose a new task, All-Inclusive Multi-Level Segmentation (AIMS), which segments visual regions into three levels: part, entity, and relation (two entities with some semantic relationships). We also build a unified AIMS model through multi-dataset multi-task training to address the two major challenges of annotation inconsistency and task correlation. Specifically, we propose task complementarity, association, and prompt mask encoder for three-level predictions. Extensive experiments demonstrate the effectiveness and generalization capacity of our method compared to other state-of-the-art methods on a single dataset or the concurrent work on segment anything. We will make our code and training model publicly available.

Panoptic segmentation is the task of uniquely assigning every pixel in an image to either a semantic label or an individual object instance, generating a coherent and complete scene description. Many current panoptic segmentation methods, however, predict masks of semantic classes and object instances in separate branches, yielding inconsistent predictions. Moreover, because state-of-the-art panoptic segmentation models rely on box proposals, the instance masks predicted are often of low-resolution. To overcome these limitations, we propose the Panoptic Refinement Network (PRN), which takes masks from base panoptic segmentation models and refines them jointly to produce coherent results. PRN extends the offset map-based architecture of Panoptic-Deeplab with several novel ideas including a foreground mask and instance bounding box offsets, as well as coordinate convolutions for improved spatial prediction. Experimental results on COCO and Cityscapes show that PRN can significantly improve already accurate results from a variety of panoptic segmentation networks.

We introduce a new image segmentation task, called Entity Segmentation (ES), which aims to segment all visual entities (objects and stuffs) in an image without predicting their semantic labels. By removing the need of class label prediction, the models trained for such task can focus more on improving segmentation quality. It has many practical applications such as image manipulation and editing where the quality of segmentation masks is crucial but class labels are less important. We conduct the first-ever study to investigate the feasibility of convolutional center-based representation to segment things and stuffs in a unified manner, and show that such representation fits exceptionally well in the context of ES. More specifically, we propose a CondInst-like fully-convolutional architecture with two novel modules specifically designed to exploit the class-agnostic and non-overlapping requirements of ES. Experiments show that the models designed and trained for ES significantly outperforms popular class-specific panoptic segmentation models in terms of segmentation quality. Moreover, an ES model can be easily trained on a combination of multiple datasets without the need to resolve label conflicts in dataset merging, and the model trained for ES on one or more datasets can generalize very well to other test datasets of unseen domains. The code has been released at https://github.com/dvlab-research/Entity.

We tackle the problem of semantic image layout manipulation, which aims to manipulate an input image by editing its semantic label map. A core problem of this task is how to transfer visual details from the input images to the new semantic layout while making the resulting image visually realistic. Recent work on learning cross-domain correspondence has shown promising results for global layout transfer with dense attention-based warping. However, this method tends to lose texture details due to the resolution limitation and the lack of smoothness constraint on correspondence. To adapt this paradigm for the layout manipulation task, we propose a high-resolution sparse attention module that effectively transfers visual details to new layouts at a resolution up to 512x512. To further improve visual quality, we introduce a novel generator architecture consisting of a semantic encoder and a two-stage decoder for coarse-to-fine synthesis. Experiments on the ADE20k and Places365 datasets demonstrate that our proposed approach achieves substantial improvements over the existing inpainting and layout manipulation methods.

Sequential recommenders aim to capture users' dynamic interests from their historical action sequences, but remain challenging due to data sparsity issues, as well as the noisy and complex relationships among items in a sequence. Several approaches have sought to alleviate these issues using side-information, such as item content (e.g., images), action types (e.g., click, purchase). While useful, we argue one of the main contextual signals is largely ignored-namely users' queries. When users browse and consume products (e.g., music, movies), their sequential interactions are usually a combination of queries, clicks (etc.). Most interaction datasets discard queries, and corresponding methods simply model sequential behaviors over items and thus ignore this critical context of user interactions.

Open-vocabulary instance segmentation aims at segmenting novel classes without mask annotations. It is an important step toward reducing laborious human supervision. Most existing works first pretrain a model on captioned images covering many novel classes and then finetune it on limited base classes with mask annotations. However, the high-level textual information learned from caption pretraining alone cannot effectively encode the details required for pixelwise segmentation. To address this, we propose a cross-modal pseudo-labeling framework, which generates training pseudo masks by aligning word semantics in captions with visual features of object masks in images. Thus, our framework is capable of labeling novel classes in captions via their word semantics to self-train a student model. To account for noises in pseudo masks, we design a robust student model that selectively distills mask knowledge by estimating the mask noise levels, hence mitigating the adverse impact of noisy pseudo masks. By extensive experiments, we show the effectiveness of our framework, where we significantly improve mAP score by 4.5% on MS-COCO and 5.1 % on the large-scale Open Images & Conceptual Captions datasets compared to the state-of-the-art.11Code is available at https://github.com/hbdat/cvpr22_cross_modal_pseudo_labeling.

Depth maps are used in a wide range of applications from 3D rendering to 2D image effects such as Bokeh. However, those predicted by single image depth estimation (SIDE) models often fail to capture isolated holes in objects and/or have inaccurate boundary regions. Meanwhile, high-quality masks are much easier to obtain, using commercial auto-masking tools or off-the-shelf methods of segmentation and matting or even by manual editing. Hence, in this paper, we formulate a novel problem of mask-guided depth refinement that utilizes a generic mask to refine the depth prediction of SIDE models. Our framework performs layered refinement and inpainting/outpainting, decomposing the depth map into two separate layers signified by the mask and the inverse mask. As datasets with both depth and mask annotations are scarce, we propose a self-supervised learning scheme that uses arbitrary masks and RGB-D datasets. We empirically show that our method is robust to different types of masks and initial depth predictions, accurately refining depth values in inner and outer mask boundary regions. We further analyze our model with an ablation study and demonstrate results on real applications. More information can be found on our project page.11https://sooyekim.github.io/MaskDepth/

Recent studies have shown the importance of modeling long-range interactions in the inpainting problem. To achieve this goal, existing approaches exploit either standalone attention techniques or transformers, but usually under a low resolution in consideration of computational cost. In this paper, we present a novel transformer-based model for large hole inpainting, which unifies the merits of transformers and convolutions to efficiently process high-resolution images. We carefully design each component of our framework to guarantee the high fidelity and diversity of recovered images. Specifically, we customize an inpainting-oriented transformer block, where the attention module aggregates non-local information only from partial valid tokens, indicated by a dynamic mask. Extensive experiments demonstrate the state-of-the-art performance of the new model on multiple benchmark datasets. Code is released at https://github.com/fenglinglwb/MAT.

Cross language-image modality retrieval in E-commerce is a fundamental problem for product search, recommendation, and marketing services. Extensive efforts have been made to conquer the cross-modal retrieval problem in the general domain. When it comes to E-commerce, a com-mon practice is to adopt the pretrained model and finetune on E-commerce data. Despite its simplicity, the performance is sub-optimal due to overlooking the uniqueness of E-commerce multimodal data. A few recent efforts [10], [72] have shown significant improvements over generic methods with customized designs for handling product images. Unfortunately, to the best of our knowledge, no existing method has addressed the unique challenges in the e-commerce language. This work studies the outstanding one, where it has a large collection of special meaning entities, e.g., “Di s s e l (brand)”, “Top (category)”, “relaxed (fit)” in the fashion clothing business. By formulating such out-of-distribution finetuning process in the Causal Inference paradigm, we view the erroneous semantics of these special entities as confounders to cause the retrieval failure. To rectify these semantics for aligning with e-commerce do-main knowledge, we propose an intervention-based entity-aware contrastive learning framework with two modules, i.e., the Confounding Entity Selection Module and Entity-Aware Learning Module. Our method achieves competitive performance on the E-commerce benchmark Fashion-Gen. Particularly, in top-1 accuracy (R@l), we observe 10.3% and 10.5% relative improvements over the closest baseline in image-to-text and text-to-image retrievals, respectively.

To segment 4K or 6K ultra high-resolution images needs extra computation consideration in image segmentation. Common strategies, such as downsampling, patch cropping, and cascade model, cannot address well the balance issue between accuracy and computation cost. Motivated by the fact that humans distinguish among objects continuously from coarse to precise levels, we propose the Continuous Refinement Model (CRM) for the ultra high-resolution segmentation refinement task. CRM continuously aligns the feature map with the refinement target and aggregates features to reconstruct these image details. Besides, our CRM shows its significant generalization ability to fill the resolution gap between low-resolution training images and ultra high-resolution testing ones. We present quantitative performance evaluation and visualization to show that our proposed method is fast and effective on image segmentation refinement. Code is available at https://github.com/dvlab-research/Entity/tree/main/CRM.

Despite the impressive representation capacity of vision transformer models, current light-weight vision transformer models still suffer from inconsistent and incorrect dense predictions at local regions. We suspect that the power of their self-attention mechanism is limited in shallower and thinner networks. We propose Lite Vision Transformer (LVT), a novel light-weight transformer network with two enhanced self-attention mechanisms to improve the model performances for mobile deployment. For the low-level features, we introduce Convolutional Self-Attention (CSA). Unlike previous approaches of merging convolution and self-attention, CSA introduces local self-attention into the convolution within a kernel of size$3\times 3$to enrich low-level features in the first stage of LVT. For the high-level features, we propose Recursive Atrous Self-Attention (RASA), which utilizes the multi-scale context when calculating the similarity map and a recursive mechanism to increase the representation capability with marginal extra parameter cost. The superiority of LVT is demonstrated on ImageNet recognition, ADE20K semantic segmentation, and COCO panoptic segmentation. The code is made publicly available11https://github.com/Chenglin-Yang/LVT.

Sketch-based image manipulation is an interactive image editing task to modify an image based on input sketches from users. Existing methods typically formulate this task as a conditional inpainting problem, which requires users to draw an extra mask indicating the region to modify in addition to sketches. The masked regions are regarded as holes and filled by an inpainting model conditioned on the sketch. With this formulation, paired training data can be easily obtained by randomly creating masks and extracting edges or contours. Although this setup simplifies data preparation and model design, it complicates user interaction and discards useful information in masked regions. To this end, we investigate a new paradigm of sketch-based image manipulation: mask-free local image manipulation, which only requires sketch inputs from users and utilizes the entire original image. Given an image and sketch, our model automatically predicts the target modification region and encodes it into a structure agnostic style vector. A generator then synthesizes the new image content based on the style vector and sketch. The manipulated image is finally produced by blending the generator output into the modification region of the original image. Our model can be trained in a self-supervised fashion by learning the reconstruction of an image region from the style vector and sketch. The proposed method offers simpler and more intuitive user workflows for sketch-based image manipulation and provides better results than previous approaches. More results, code and interactive demo will be available at https://zengxianyu.github.io/sketchedit.

We present StyleBabel, a unique open access dataset of natural language captions and free-form tags describing the artistic style of over 135K digital artworks, collected via a novel participatory method from experts studying at specialist art and design schools. StyleBabel was collected via an iterative method, inspired by ‘Grounded Theory’: a qualitative approach that enables annotation while co-evolving a shared language for fine-grained artistic style attribute description. We demonstrate several downstream tasks for StyleBabel, adapting the recent ALADIN architecture for fine-grained style similarity, to train cross-modal embeddings for: 1) free-form tag generation; 2) natural language description of artistic style; 3) fine-grained text search of style. To do so, we extend ALADIN with recent advances in Visual Transformer (ViT) and cross-modal representation learning, achieving a state of the art accuracy in fine-grained style retrieval.

Recently, self-attentive models have shown promise in sequential recommendation, given their potential to capture user long-term preferences and short-term dynamics simultaneously. Despite their success, we argue that self-attention modules, as a non-local operator, often fail to capture short-term user dynamics accurately due to a lack of inductive local bias. To examine our hypothesis, we conduct an analytical experiment on controlled 'short-term' scenarios. We observe a significant performance gap between self-attentive recommenders with and without local constraints, which implies that short-term user dynamics are not sufficiently learned by existing self-attentive recommenders. Motivated by this observation, we propose a simple framework, (Locker) for self-attentive recommenders in a plug-and-play fashion. By combining the proposed local encoders with existing global attention heads, Locker enhances short-term user dynamics modeling, while retaining the long-term semantics captured by standard self-attentive encoders. We investigate Locker with five different local methods, outperforming state-of-the-art self-attentive recom- menders on three datasets by 17.19% ([email protected]) on average.

Generative adversarial networks (GANs), e.g., StyleGAN2, play a vital role in various image generation and synthesis tasks, yet their notoriously high computational cost hinders their efficient deployment on edge devices. Directly applying generic compression approaches yields poor results on GANs, which motivates a number of recent GAN compression works. While prior works mainly accelerate conditional GANs, e.g., pix2pix and Cycle-GAN, compressing state-of-the-art unconditional GANs has rarely been explored and is more challenging. In this paper, we propose novel approaches for unconditional GAN compression. We first introduce effective channel pruning and knowledge distillation schemes specialized for unconditional GANs. We then propose a novel content-aware method to guide the processes of both pruning and distillation. With content-awareness, we can effectively prune channels that are unimportant to the contents of interest, e.g., human faces, and focus our distillation on these regions, which significantly enhances the distillation quality. On StyleGAN2 and SN-GAN, we achieve a substantial improvement over the state-of-the-art compression method. Notably, we reduce the FLOPs of StyleGAN2 by 11× with visually negligible image quality loss compared to the full-size model. More interestingly, when applied to various image manipulation tasks, our compressed model forms a smoother and better disentangled latent manifold, making it more effective for image editing.

Visual attributes constitute a large portion of information contained in a scene. Objects can be described using a wide variety of attributes which portray their visual appearance (color, texture), geometry (shape, size, posture), and other intrinsic properties (state, action). Existing work is mostly limited to study of attribute prediction in specific domains. In this paper, we introduce a large-scale in-the-wild visual attribute prediction dataset consisting of over 927K attribute annotations for over 260K object instances. Formally, object attribute prediction is a multi-label classification problem where all attributes that apply to an object must be predicted. Our dataset poses significant challenges to existing methods due to large number of attributes, label sparsity, data imbalance, and object occlusion. To this end, we propose several techniques that systematically tackle these challenges, including a base model that utilizes both low- and high-level CNN features with multi-hop attention, reweighting and resampling techniques, a novel negative label expansion scheme, and a novel supervised attribute-aware contrastive learning algorithm. Using these techniques, we achieve near 3.7 mAP and 5.7 overall F1 points improvement over the current state of the art. Further details about the VAW dataset can be found at https://vawdataset.com/

In instance-level detection tasks (e.g., object detection), reducing input resolution is an easy option to improve runtime efficiency. However, this option traditionally hurts the detection performance much. This paper focuses on boosting performance of low-resolution models by distilling knowledge from a high- or multi-resolution model. We first identify the challenge of applying knowledge distillation (KD) to teacher and student networks that act on different input resolutions. To tackle it, we explore the idea of spatially aligning feature maps between models of varying input resolutions by shifting feature pyramid position and introduce aligned multi-scale training to train a multi-scale teacher that can distill its knowledge to a low-resolution student. Further, we propose crossing feature-level fusion to dynamically fuse teacher’s multi-resolution features to guide the student better. On several instance-level detection tasks and datasets, the low-resolution models trained via our approach perform competitively with high-resolution models trained via conventional multi-scale training, while outperforming the latter’s low-resolution models by 2.1% to 3.6% in terms of mAP. Our code is made publicly available at https://github.com/Jia-Research-Lab/MSAD.

We propose Mask Guided (MG) Matting, a robust matting framework that takes a general coarse mask as guidance. MG Matting leverages a network (PRN) design which encourages the matting model to provide self-guidance to progressively refine the uncertain regions through the decoding process. A series of guidance mask perturbation operations are also introduced in the training to further enhance its robustness to external guidance. We show that PRN can generalize to unseen types of guidance masks such as trimap and low-quality alpha matte, making it suitable for various application pipelines. In addition, we revisit the foreground color prediction problem for matting and propose a surprisingly simple improvement to address the dataset issue. Evaluation on real and synthetic benchmarks shows that MG Matting achieves state-of-the-art performance using various types of guidance inputs. Code and models are available at https://github.com/yucornetto/MGMatting.

We develop an approach to learning visual representations that embraces multimodal data, driven by a combination of intra- and inter-modal similarity preservation objectives. Unlike existing visual pre-training methods, which solve a proxy prediction task in a single domain, our method exploits intrinsic data properties within each modality and semantic information from cross-modal correlation simultaneously, hence improving the quality of learned visual representations. By including multimodal training in a unified framework with different types of contrastive losses, our method can learn more powerful and generic visual features. We first train our model on COCO and evaluate the learned visual representations on various downstream tasks including image classification, object detection, and instance segmentation. For example, the visual representations pre-trained on COCO by our method achieve state-of-the-art top-1 validation accuracy of 55.3% on ImageNet classification, under the common transfer protocol. We also evaluate our method on the large-scale Stock images dataset and show its effectiveness on multi-label image tagging, and cross-modal retrieval tasks.

Image harmonization aims to improve the quality of image compositing by matching the "appearance" (e.g., color tone, brightness and contrast) between foreground and background images. However, collecting large-scale annotated datasets for this task requires complex professional retouching. Instead, we propose a novel Self-Supervised Harmonization framework (SSH) that can be trained using just "free" natural images without being edited. We reformulate the image harmonization problem from a representation fusion perspective, which separately processes the foreground and background examples, to address the background occlusion issue. This framework design allows for a dual data augmentation method, where diverse [foreground, background, pseudo GT] triplets can be generated by cropping an image with perturbations using 3D color lookup tables (LUTs). In addition, we build a real-world harmonization dataset as carefully created by expert users, for evaluation and benchmarking purposes. Our results show that the proposed self-supervised method outperforms previous state-of-the-art methods in terms of reference metrics, visual quality, and subject user study. Code and dataset are available at https://github.com/VITA-Group/SSHarmonization.

We present ALADIN (All Layer AdaIN); a novel architecture for searching images based on the similarity of their artistic style. Representation learning is critical to visual search, where distance in the learned search embedding reflects image similarity. Learning an embedding that discriminates fine-grained variations in style is hard, due to the difficulty of defining and labelling style. ALADIN takes a weakly supervised approach to learning a representation for fine-grained style similarity of digital artworks, leveraging BAM-FG, a novel large-scale dataset of user generated content groupings gathered from the web. ALADIN sets a new state of the art accuracy for style-based visual search over both coarse labelled style data (BAM) and BAM-FG; a new 2.62 million image dataset of 310,000 fine-grained style groupings also contributed by this work.

Current face image retrieval solutions are limited, since they treat different facial attributes the same and cannot incorporate user’s preference for a subset of attributes in their search criteria. This paper introduces a new face image retrieval framework, where the input face query is augmented by both an adjustment vector that specifies the desired modifications to the facial attributes, and a preference vector that assigns different levels of importance to different attributes. For example, a user can ask for retrieving images similar to a query image, but with a different hair color, and no preference for absence/presence of eyeglasses in the results. To achieve this, we propose to disentangle the semantics, corresponding to various attributes, by learning a set of sparse and orthogonal basis vectors in the latent space of StyleGAN. Such basis vectors are then employed to decompose the dissimilarity between face images in terms of dissimilarity between their attributes, assign preference to the attributes, and adjust the attributes in the query. Enforcing sparsity on the basis vectors helps us to disentangle the latent space and adjust each attribute independently from other attributes, while enforcing orthogonality facilitates preference assignment and the dissimilarity decomposition. The effectiveness of our approach is illustrated by achieving state-of-the-art results for the face image retrieval task.

Recent deep generative inpainting methods use attention layers to allow the generator to explicitly borrow feature patches from the known region to complete a missing region. Due to the lack of supervision signals for the correspondence between missing regions and known regions, it may fail to find proper reference features, which often leads to artifacts in the results. Also, it computes pair-wise similarity across the entire feature map during inference bringing a significant computational overhead. To address this issue, we propose to teach such patch-borrowing behavior to an attention-free generator by joint training of an auxiliary contextual reconstruction task, which encourages the generated output to be plausible even when reconstructed by surrounding regions. The auxiliary branch can be seen as a learnable loss function, i.e. named as contextual reconstruction (CR) loss, where query-reference feature similarity and reference-based reconstructor are jointly optimized with the inpainting generator. The auxiliary branch ( i.e. CR loss) is required only during training, and only the inpainting generator is required during the inference. Experimental results demonstrate that the proposed inpainting model compares favourably against the state-of-the-art in terms of quantitative and visual performance. Code is available at https://github.com/zengxianyu/crfill.

Graph neural networks (GNNs) emerge as the state-of-the-art representation learning methods on graphs and often rely on a large amount of labeled data to achieve satisfactory performance. Recently, in order to relieve the label scarcity issues, some works propose to pre-train GNNs in a self-supervised manner by distilling transferable knowledge from the unlabeled graph structures. Unfortunately, these pre-training frameworks mainly target at homogeneous graphs, while real interaction systems usually constitute large-scale heterogeneous graphs, containing different types of nodes and edges, which leads to new challenges on structure heterogeneity and scalability for graph pre-training. In this paper, we first study the problem of pre-training on large-scale heterogeneous graph and propose a novel pre-training GNN framework, named PT-HGNN. The proposed PT-HGNN designs both the node- and schema-level pre-training tasks to contrastively preserve heterogeneous semantic and structural properties as a form of transferable knowledge for various downstream tasks. In addition, a relationbased personalized PageRank is proposed to sparsify large-scale heterogeneous graph for efficient pre-training. Extensive experiments on one of the largest public heterogeneous graphs (OAG) demonstrate that our PT-HGNN significantly outperforms various state-of-the-art baselines.

We propose a novel method for automatic object recoloring based on Generative Adversarial Networks (GANs). The user can simply give commands of the form recolortowhich will be executed without any need of manual edit. Our approach takes advantage of pre-trained object detectors and saliency mask segmentation networks. The segmented mask of the given object along with the target color and the original image form the input to the GAN. The use of cycle consistency loss ensures the realistic look of the results. To our best knowledge, this is the first algorithm where the automatic recoloring is only limited by the ability of the mask extractor to map a natural language tag to a specific object in the image (several hundred object types at the time of this writing). For a performance comparison, we also adapted other state of the art methods to perform this task. We found that our method had consistently yielded qualitatively better recoloring results.

Image compositing is a task of combining regions from different images to compose a new image. A common use case is background replacement of portrait images. To obtain high quality composites, professionals typically manually perform multiple editing steps such as segmentation, matting and foreground color decontamination, which is very time consuming even with sophisticated photo editing tools. In this paper, we propose a new method which can automatically generate high-quality image compositing with-out any user input. Our method can be trained end-to-end to optimize exploitation of contextual and color information of both foreground and background images, where the com-positing quality is considered in the optimization. Specifically, inspired by Laplacian pyramid blending, a dense-connected multi-stream fusion network is proposed to effectively fuse the information from the foreground and back-ground images at different scales. In addition, we intro-duce a self-taught strategy to progressively train from easy to complex cases to mitigate the lack of training data. Experiments show that the proposed method can automatically generate high-quality composites and outperforms existing methods both qualitatively and quantitatively.

Detecting segments of interest from videos is a common problem for many applications. And yet it is a challenging problem as it often requires not only knowledge of individual target segments, but also contextual understanding of the entire video and the relationships between the target segments. To address this problem, we propose the Sequence-to-Segments Network (S2N), a novel and general end-to-end sequential encoder-decoder architecture. S2N first encodes the input video into a sequence of hidden states that capture information progressively, as it appears in the video. It then employs the Segment Detection Unit (SDU), a novel decoding architecture, that sequentially detects segments. At each decoding step, the SDU integrates the decoder state and encoder hidden states to detect a target segment. During training, we address the problem of finding the best assignment of predicted segments to ground truth using the Hungarian Matching Algorithm with Lexicographic Cost. Additionally we propose to use the squared Earth Mover's Distance to optimize the localization errors of the segments. We show the state-of-the-art performance of S2N across numerous tasks, including video highlighting, video summarization, and human action proposal generation.

We present TDNet, a temporally distributed network designed for fast and accurate video semantic segmentation. We observe that features extracted from a certain high-level layer of a deep CNN can be approximated by composing features extracted from several shallower sub-networks. Leveraging the inherent temporal continuity in videos, we distribute these sub-networks over sequential frames. Therefore, at each time step, we only need to perform a lightweight computation to extract a sub-features group from a single sub-network. The full features used for segmentation are then recomposed by application of a novel attention propagation module that compensates for geometry deformation between frames. A grouped knowledge distillation loss is also introduced to further improve the representation power at both full and sub-feature levels. Experiments on Cityscapes, CamVid, and NYUD-v2 demonstrate that our method achieves state-of-the-art accuracy with significantly faster speed and lower latency.

While image captioning has progressed rapidly, existing works focus mainly on describing single images. In this paper, we introduce a new task, context-aware group captioning, which aims to describe a group of target images in the context of another group of related reference images. Context-aware group captioning requires not only summarizing information from both the target and reference image group but also contrasting between them. To solve this problem, we propose a framework combining self-attention mechanism with contrastive feature construction to effectively summarize common information from each image group while capturing discriminative information between them. To build the dataset for this task, we propose to group the images and generate the group captions based on single image captions using scene graphs matching. Our datasets are constructed on top of the public Conceptual Captions dataset and our new Stock Captions dataset. Experiments on the two datasets show the effectiveness of our method on this new task.

Monocular depth estimation is an ill-posed problem, and as such critically relies on scene priors and semantics. Due to its complexity, we propose a deep neural network model based on a semantic divide-and-conquer approach. Our model decomposes a scene into semantic segments, such as object instances and background stuff classes, and then predicts a scale and shift invariant depth map for each semantic segment in a canonical space. Semantic segments of the same category share the same depth decoder, so the global depth prediction task is decomposed into a series of category-specific ones, which are simpler to learn and easier to generalize to new scene types. Finally, our model stitches each local depth segment by predicting its scale and shift based on the global context of the image. The model is trained end-to-end using a multi-task loss for panoptic segmentation and depth prediction, and is therefore able to leverage large-scale panoptic segmentation datasets to boost its semantic understanding. We validate the effectiveness of our approach and show state-of-the-art performance on three benchmark datasets.

We present a scalable approach for learning powerful visual features for emotion recognition. A critical bottleneck in emotion recognition is the lack of large scale datasets that can be used for learning visual emotion features. To this end, we curate a webly derived large scale dataset, StockEmotion, which has more than a million images. StockEmotion uses 690 emotion related tags as labels giving us a fine-grained and diverse set of emotion labels, circumventing the difficulty in manually obtaining emotion annotations. We use this dataset to train a feature extraction network, EmotionNet, which we further regularize using joint text and visual embedding and text distillation. Our experimental results establish that EmotionNet trained on the StockEmotion dataset outperforms SOTA models on four different visual emotion tasks. An aded benefit of our joint embedding training approach is that EmotionNet achieves competitive zero-shot recognition performance against fully supervised baselines on a challenging visual emotion dataset, EMOTIC, which further highlights the generalizability of the learned emotion features.

We consider the problem of segmenting image regions given a natural language phrase, and study it on a novel dataset of 77,262 images and 345,486 phrase-region pairs. Our dataset is collected on top of the Visual Genome dataset and uses the existing annotations to generate a challenging set of referring phrases for which the corresponding regions are manually annotated. Phrases in our dataset correspond to multiple regions and describe a large number of object and stuff categories as well as their attributes such as color, shape, parts, and relationships with other entities in the image. Our experiments show that the scale and diversity of concepts in our dataset poses significant challenges to the existing state-of-the-art. We systematically handle the long-tail nature of these concepts and present a modular approach to combine category, attribute, and relationship cues that outperforms existing approaches.

Single image depth prediction is a challenging task due to its ill-posed nature and challenges with capturing ground truth for supervision. Large-scale disparity data generated from stereo photos and 3D videos is a promising source of supervision, however, such disparity data can only approximate the inverse ground truth depth up to an affine transformation. To more effectively learn from such pseudo-depth data, we propose to use a simple pair-wise ranking loss with a novel sampling strategy. Instead of randomly sampling point pairs, we guide the sampling to better characterize structure of important regions based on the low-level edge maps and high-level object instance masks. We show that the pair-wise ranking loss, combined with our structure-guided sampling strategies, can significantly improve the quality of depth map prediction. In addition, we introduce a new relative depth dataset of about 21K diverse high-resolution web stereo photos to enhance the generalization ability of our model. In experiments, we conduct cross-dataset evaluation on six benchmark datasets and show that our method consistently improves over the baselines, leading to superior quantitative and qualitative results.

Personalization is essential for enhancing the customer experience in retrieval tasks. In this paper, we develop a novel method CA-GCN for personalized image retrieval in the Adobe Stock image system. The proposed method CA-GCN leverages user behavior data in a Graph Convolutional Neural Network (GCN) model to learn user and image embeddings simultaneously. Standard GCN performs poorly on sparse user-image interaction graphs due to the limited knowledge gain from less representative neighbors. To address this challenge, we propose to augment the sparse user-image interaction data by considering the similarities among images. Specifically, we detect clusters of similar images and introduce a set of hidden super-nodes in the graph to represent clusters. We show that such an augmented graph structure can significantly improve the retrieval performance on real-world data collected from Adobe Stock service. In particular, when testing the proposed method on real users' stock image retrieval sessions, we get promoted average click position from 70 to 51.

People usually take short videos to record meaningful moments in their lives. However, selecting the most representative frame, which not only has high image visual quality but also captures video content, from a short video to share or keep is a time-consuming process for one may need to manually go through all the frames in a video to make a decision. In this paper, we introduce the problem of the best frame selection in a short video and aim to solve it automatically. Towards this end, we collect and will release a diverse large-scale short video dataset that includes 11, 000 videos shoot in our daily life. All videos are assumed to be short (e.g., a few seconds) and each video has human-annotated of the best frame. Then we introduce a deep convolutional neural network (CNN) based approach with ranking objective to automatically pick the best frame from frame sequences extracted via short videos. Additionally, we propose new evaluation metrics, especially for the best frame selection. In experiments, we show our approach outperforms various other methods significantly.

Describing images with text is a fundamental problem in vision-language research. Current studies in this domain mostly focus on single image captioning. However, in various real applications (e.g., image editing, difference interpretation, and retrieval), generating relational captions for two images, can also be very useful. This important problem has not been explored mostly due to lack of datasets and effective models. To push forward the research in this direction, we first introduce a new language-guided image editing dataset that contains a large number of real image pairs with corresponding editing instructions. We then propose a new relational speaker model based on an encoder-decoder architecture with static relational attention and sequential multi-head attention. We also extend the model with dynamic relational attention, which calculates visual alignment while decoding. Our models are evaluated on our newly collected and two public datasets consisting of image pairs annotated with relationship sentences. Experimental results, based on both automatic and human evaluation, demonstrate that our model outperforms all baselines and existing methods on all the datasets.

Instant photo taking and sharing has become one of the most popular forms of social networking. However, taking high-quality photos is difficult as it requires knowledge and skill in photography that most non-expert users lack. In this paper we present SmartEye, a novel mobile system to help users take photos with good compositions in-situ. The back-end of SmartEye integrates the View Proposal Network (VPN), a deep learning based model that outputs composition suggestions in real time, and a novel, interactively updated module (P-Module) that adjusts the VPN outputs to account for personalized composition preferences. We also design a novel interface with functions at the front-end to enable real-time and informative interactions for photo taking. We conduct two user studies to investigate SmartEye qualitatively and quantitatively. Results show that SmartEye effectively models and predicts personalized composition preferences, provides instant high-quality compositions in-situ, and outperforms the non-personalized systems significantly.

Deep neural network-based methods were proposed for face attribute manipulation. There still exist, however, two major issues, i.e., insufficient visual quality (or resolution) of the results and lack of user control. They limit the applicability of existing methods since users may have different editing preference on facial attributes. In this paper, we address these issues by proposing a semantic component model. The model decomposes a facial attribute into multiple semantic components, each corresponds to a specific face region. This not only allows for user control of edit strength on different parts based on their preference, but also makes it effective to remove unwanted edit effect. Further, each semantic component is composed of two fundamental elements, which determine the edit effect and region respectively. This property provides fine interactive control. As shown in experiments, our model not only produces high-quality results, but also allows effective user interaction.

Scene graph generation has received growing attention with the advancements in image understanding tasks such as object detection, attributes and relationship prediction, etc. However, existing datasets are biased in terms of object and relationship labels, or often come with noisy and missing annotations, which makes the development of a reliable scene graph prediction model very challenging. In this paper, we propose a novel scene graph generation algorithm with external knowledge and image reconstruction loss to overcome these dataset issues. In particular, we extract commonsense knowledge from the external knowledge base to refine object and phrase features for improving generalizability in scene graph generation. To address the bias of noisy object annotations, we introduce an auxiliary image reconstruction path to regularize the scene graph generation network. Extensive experiments show that our framework can generate better scene graphs, achieving the state-of-the-art performance on two benchmark datasets: Visual Relationship Detection and Visual Genome datasets.

In this paper, we study the problem of improving computational resource utilization of neural networks. Deep neural networks are usually over-parameterized for their tasks in order to achieve good performances, thus are likely to have underutilized computational resources. This observation motivates a lot of research topics, e.g. network pruning, architecture search, etc. As models with higher computational costs (e.g. more parameters or more computations) usually have better performances, we study the problem of improving the resource utilization of neural networks so that their potentials can be further realized. To this end, we propose a novel optimization method named Neural Rejuvenation. As its name suggests, our method detects dead neurons and computes resource utilization in real time, rejuvenates dead neurons by resource reallocation and reinitialization, and trains them with new training schemes. By simply replacing standard optimizers with Neural Rejuvenation, we are able to improve the performances of neural networks by a very large margin while using similar training efforts and maintaining their original resource usages. The code is available here: https://github.com/joe-siyuan-qiao/NeuralRejuvenation-CVPR19

Existing image inpainting methods typically fill holes by borrowing information from surrounding pixels. They often produce unsatisfactory results when the holes overlap with or touch foreground objects due to lack of information about the actual extent of foreground and background regions within the holes. These scenarios, however, are very important in practice, especially for applications such as distracting object removal. To address the problem, we propose a foreground-aware image inpainting system that explicitly disentangles structure inference and content completion. Specifically, our model learns to predict the foreground contour first, and then inpaints the missing region using the predicted contour as guidance. We show that by such disentanglement, the contour completion model predicts reasonable contours of objects, and further substantially improves the performance of image inpainting. Experiments show that our method significantly outperforms existing methods and achieves superior inpainting results on challenging cases with complex compositions.

Due to the significant information loss in low-resolution (LR) images, it has become extremely challenging to further advance the state-of-the-art of single image super-resolution (SISR). Reference-based super-resolution (RefSR), on the other hand, has proven to be promising in recovering high-resolution (HR) details when a reference (Ref) image with similar content as that of the LR input is given. However, the quality of RefSR can degrade severely when Ref is less similar. This paper aims to unleash the potential of RefSR by leveraging more texture details from Ref images with stronger robustness even when irrelevant Ref images are provided. Inspired by the recent work on image stylization, we formulate the RefSR problem as neural texture transfer. We design an end-to-end deep model which enriches HR details by adaptively transferring the texture from Ref images according to their textural similarity. Instead of matching content in the raw pixel space as done by previous methods, our key contribution is a multi-level matching conducted in the neural space. This matching scheme facilitates multi-scale neural transfer that allows the model to benefit more from those semantically related Ref patches, and gracefully degrade to SISR performance on the least relevant Ref inputs. We build a benchmark dataset for the general research of RefSR, which contains Ref images paired with LR inputs with varying levels of similarity. Both quantitative and qualitative evaluations demonstrate the superiority of our method over state-of-the-art.

Detecting salient objects in cluttered scenes is a big challenge. To address this problem, we argue that the model needs to learn discriminative semantic features for salient objects. To this end, we propose to leverage captioning as an auxiliary semantic task to boost salient object detection in complex scenarios. Specifically, we develop a CapSal model which consists of two sub-networks, the Image Captioning Network (ICN) and the Local-Global Perception Network (LGPN). ICN encodes the embedding of a generated caption to capture the semantic information of major objects in the scene, while LGPN incorporates the captioning embedding with local-global visual contexts for predicting the saliency map. ICN and LGPN are jointly trained to model high-level semantics as well as visual saliency. Extensive experiments demonstrate the effectiveness of image captioning in boosting the performance of salient object detection. In particular, our model performs significantly better than the state-of-the-art methods on several challenging datasets of complex scenarios.

Large scale object detection datasets are constantly increasing their size in terms of the number of classes and annotations count. Yet, the number of object-level categories annotated in detection datasets is an order of magnitude smaller than image-level classification labels. State-of-the art object detection models are trained in a supervised fashion and this limits the number of object classes they can detect. In this paper, we propose a novel weight transfer network (WTN) to effectively and efficiently transfer knowledge from classification network's weights to detection network's weights to allow detection of novel classes without box supervision. We first introduce input and feature normalization schemes to curb the under-fitting during training of a vanilla WTN. We then propose autoencoder-WTN (AE-WTN) which uses reconstruction loss to preserve classification network's information over all classes in the target latent space to ensure generalization to novel classes. Compared to vanilla WTN, AE-WTN obtains absolute performance gains of 6% on two Open Images evaluation sets with 500 seen and 57 novel classes respectively, and 25% on a Visual Genome evaluation set with 200 novel classes.

We present a generative image inpainting system to complete images with free-form mask and guidance. The system is based on gated convolutions learned from millions of images without additional labelling efforts. The proposed gated convolution solves the issue of vanilla convolution that treats all input pixels as valid ones, generalizes partial convolution by providing a learnable dynamic feature selection mechanism for each channel at each spatial location across all layers. Moreover, as free-form masks may appear anywhere in images with any shape, global and local GANs designed for a single rectangular mask are not applicable. Thus, we also present a patch-based GAN loss, named SN-PatchGAN, by applying spectral-normalized discriminator on dense image patches. SN-PatchGAN is simple in formulation, fast and stable in training. Results on automatic image inpainting and user-guided extension demonstrate that our system generates higher-quality and more flexible results than previous methods. Our system helps user quickly remove distracting objects, modify image layouts, clear watermarks and edit faces. Code, demo and models are available at: \url{https://github.com/JiahuiYu/generative_inpainting}.

Deep neural network based methods have made a significant breakthrough in salient object detection. However, they are typically limited to input images with low resolutions (400×400 pixels or less). Little effort has been made to train neural networks to directly handle salient object segmentation in high-resolution images. This paper pushes forward high-resolution saliency detection, and contributes a new dataset, named High-Resolution Salient Object Detection (HRSOD) dataset. To our best knowledge, HRSOD is the first high-resolution saliency detection dataset to date. As another contribution, we also propose a novel approach, which incorporates both global semantic information and local high-resolution details, to address this challenging task. More specifically, our approach consists of a Global Semantic Network (GSN), a Local Refinement Network (LRN) and a Global-Local Fusion Network (GLFN). The GSN extracts the global semantic information based on downsampled entire image. Guided by the results of GSN, the LRN focuses on some local regions and progressively produces high-resolution predictions. The GLFN is further proposed to enforce spatial consistency and boost performance. Experiments illustrate that our method outperforms existing state-of-the-art methods on high-resolution saliency datasets by a large margin, and achieves comparable or even better performance than them on some widely used saliency benchmarks.

An assumption widely used in recent neural style transfer methods is that image styles can be described by global statics of deep features like Gram or covariance matrices. Alternative approaches have represented styles by decomposing them into local pixel or neural patches. Despite the recent progress, most existing methods treat the semantic patterns of style image uniformly, resulting unpleasing results on complex styles. In this paper, we introduce a more flexible and general universal style transfer technique: multimodal style transfer (MST). MST explicitly considers the matching of semantic patterns in content and style images. Specifically, the style image features are clustered into sub-style components, which are matched with local content features under a graph cut formulation. A reconstruction network is trained to transfer each sub-style and render the final stylized result. We also generalize MST to improve some existing methods. Extensive experiments demonstrate the superior effectiveness, robustness, and flexibility of MST.

We propose a new model for fast and accurate video object segmentation. It consists of two convolutional neural networks, a Dynamic Targeting Network (DTN) and a Mask Refinement Network (MRN). DTN locates the object by dynamically focusing on regions of interest surrounding the target object. The target region is predicted by DTN via two sub-streams, Box Propagation (BP) and Box Re-identification (BR). The BP stream is faster but less effective at objects with large deformation or occlusion. The BR stream performs better in difficult scenarios at a higher computation cost. We propose a Decision Module (DM) to adaptively determine which sub-stream to use for each frame. Finally, MRN is exploited to predict segmentation within the target region. Experimental results on two public datasets demonstrate that the proposed model significantly outperforms existing methods without online training in both accuracy and efficiency, and is comparable to online training-based methods in accuracy with an order of magnitude faster speed.

Edges, boundaries and contours are important subjects of study in both computer graphics and computer vision. On one hand, they are the 2D elements that convey 3D shapes, on the other hand, they are indicative of occlusion events and thus separation of objects or semantic concepts. In this paper, we aim to generate contour drawings, boundary-like drawings that capture the outline of the visual scene. Prior art often cast this problem as boundary detection. However, the set of visual cues presented in the boundary detection output are different from the ones in contour drawings, and also the artistic style is ignored. We address these issues by collecting a new dataset of contour drawings and proposing a learning-based method that resolves diversity in the annotation and, unlike boundary detectors, can work with imperfect alignment of the annotation and the actual ground truth. Our method surpasses previous methods quantitatively and qualitatively. Surprisingly, when our model fine-tunes on BSDS500, we achieve the state-of-the-art performance in salient boundary detection, suggesting contour drawing might be a scalable alternative to boundary annotation, which at the same time is easier and more interesting for annotators to draw.

Approximate K-nearest neighbor search is a fundamental problem in computer science. The problem is especially important for high-dimensional and large-scale data. Recently, many techniques encoding high-dimensional data to compact codes have been proposed. The product quantization and its variations that encode the cluster index in each subspace have been shown to provide impressive accuracy. In this paper, we explore a simple question: is it best to use all the bit-budget for encoding a cluster index? We have found that as data points are located farther away from the cluster centers, the error of estimated distance becomes larger. To address this issue, we propose a novel compact code representation that encodes both the cluster index and quantized distance between a point and its cluster center in each subspace by distributing the bit-budget. We also propose two distance estimators tailored to our representation. We further extend our method to encode global residual distances in the original space. We have evaluated our proposed methods on benchmarks consisting of GIST, VLAD, and CNN features. Our extensive experiments show that the proposed methods significantly and consistently improve the search accuracy over other tested techniques. This result is achieved mainly because our methods accurately estimate distances.

It is desirable to train convolutional networks (CNNs) to run more efficiently during inference. In many cases however, the computational budget that the system has for inference cannot be known beforehand during training, or the inference budget is dependent on the changing real-time resource availability. Thus, it is inadequate to train just inference-efficient CNNs, whose inference costs are not adjustable and cannot adapt to varied inference budgets. We propose a novel approach for cost-adjustable inference in CNNs - Stochastic Downsampling Point (SDPoint). During training, SDPoint applies feature map downsampling to a random point in the layer hierarchy, with a random downsampling ratio. The different stochastic downsampling configurations known as SDPoint instances (of the same model) have computational costs different from each other, while being trained to minimize the same prediction loss. Sharing network parameters across different instances provides significant regularization boost. During inference, one may handpick a SDPoint instance that best fits the inference budget. The effectiveness of SDPoint, as both a cost-adjustable inference approach and a regularizer, is validated through extensive experiments on image classification.

Finding views with good photo composition is a challenging task for machine learning methods. A key difficulty is the lack of well annotated large scale datasets. Most existing datasets only provide a limited number of annotations for good views, while ignoring the comparative nature of view selection. In this work, we present the first large scale Comparative Photo Composition dataset, which contains over one million comparative view pairs annotated using a cost-effective crowdsourcing workflow. We show that these comparative view annotations are essential for training a robust neural network model for composition. In addition, we propose a novel knowledge transfer framework to train a fast view proposal network, which runs at 75+ FPS and achieves state-of-the-art performance in image cropping and thumbnail generation tasks on three benchmark datasets. The superiority of our method is also demonstrated in a user study on a challenging experiment, where our method significantly outperforms the baseline methods in producing diversified well-composed views.

In this paper, we address referring expression comprehension: localizing an image region described by a natural language expression. While most recent work treats expressions as a single unit, we propose to decompose them into three modular components related to subject appearance, location, and relationship to other objects. This allows us to flexibly adapt to expressions containing different types of information in an end-to-end framework. In our model, which we call the Modular Attention Network (MAttNet), two types of attention are utilized: language-based attention that learns the module weights as well as the word/phrase attention that each module should focus on; and visual attention that allows the subject and relationship modules to focus on relevant image components. Module weights combine scores from all three modules dynamically to output an overall score. Experiments show that MAttNet outperforms previous state-of-the-art methods by a large margin on both bounding-box-level and pixel-level comprehension tasks. Demo1 and code2 are provided.

Recent deep learning based approaches have shown promising results for the challenging task of inpainting large missing regions in an image. These methods can generate visually plausible image structures and textures, but often create distorted structures or blurry textures inconsistent with surrounding areas. This is mainly due to ineffectiveness of convolutional neural networks in explicitly borrowing or copying information from distant spatial locations. On the other hand, traditional texture and patch synthesis approaches are particularly suitable when it needs to borrow textures from the surrounding regions. Motivated by these observations, we propose a new deep generative model-based approach which can not only synthesize novel image structures but also explicitly utilize surrounding image features as references during network training to make better predictions. The model is a feedforward, fully convolutional neural network which can process images with multiple holes at arbitrary locations and with variable sizes during the test time. Experiments on multiple datasets including faces (CelebA, CelebA-HQ), textures (DTD) and natural images (ImageNet, Places2) demonstrate that our proposed approach generates higher-quality inpainting results than existing ones. Code, demo and models are available at: https://github.com/JiahuiYu/generative_inpainting.

While many approaches have been proposed to estimate and remove blur in a photo, few efforts were made to have an algorithm automatically understand the blur desirability: whether the blur is desired or not, and how it affects the quality of the photo. Such a task not only relies on low-level visual features to identify blurry regions, but also requires high-level understanding of the image content as well as user intent during photo capture. In this paper, we propose a unified framework to estimate a spatially-varying blur map and understand its desirability in terms of image quality at the same time. In particular, we use a dilated fully convolutional neural network with pyramid pooling and boundary refinement layers to generate high-quality blur response maps. If blur exists, we classify its desirability to three levels ranging from good to bad, by distilling high-level semantics and learning an attention map to adaptively localize the important content in the image. The whole framework is end-to-end jointly trained with both supervisions of pixel-wise blur responses and image-wise blur desirability levels. Considering the limitations of existing image blur datasets, we collected a new large-scale dataset with both annotations to facilitate training. The proposed methods are extensively evaluated on two datasets and demonstrate state-of-the-art performance on both tasks.

We study the problem of learning a navigation policy for a robot to actively search for an object of interest in an indoor environment solely from its visual inputs. While scene-driven visual navigation has been widely studied, prior efforts on learning navigation policies for robots to find objects are limited. The problem is often more challenging than target scene finding as the target objects can be very small in the view and can be in an arbitrary pose. We approach the problem from an active perceiver perspective, and propose a novel framework that integrates a deep neural network based object recognition module and a deep reinforcement learning based action prediction mechanism. To validate our method, we conduct experiments on both a simulation dataset (AI2-THOR)and a real-world environment with a physical robot. We further propose a new decaying reward function to learn the control policy specific to the object searching task. Experimental results validate the efficacy of our method, which outperforms competing methods in both average trajectory length and success rate.

Detecting segments of interest from an input sequence is a challenging problem which often requires not only good knowledge of individual target segments, but also contextual understanding of the entire input sequence and the relationships between the target segments. To address this problem, we propose the Sequence-to-Segment Network (S$^2$N), a novel end-to-end sequential encoder-decoder architecture. S$^2$N first encodes the input into a sequence of hidden states that progressively capture both local and holistic information. It then employs a novel decoding architecture, called Segment Detection Unit (SDU), that integrates the decoder state and encoder hidden states to detect segments sequentially. During training, we formulate the assignment of predicted segments to ground truth as bipartite matching and use the Earth Mover's Distance to calculate the localization errors. We experiment with S$^2$N on temporal action proposal generation and video summarization and show that S$^2$N achieves state-of-the-art performance on both tasks.

In this paper, we introduce the problem of simultaneously detecting multiple photographic defects. We aim at detecting the existence, severity, and potential locations of common photographic defects related to color, noise, blur and composition. The automatic detection of such defects could be used to provide users with suggestions for how to improve photos without the need to laboriously try various correction methods. Defect detection could also help users select photos of higher quality while filtering out those with severe defects in photo curation and summarization. To investigate this problem, we collected a large-scale dataset of user annotations on seven common photographic defects, which allows us to evaluate algorithms by measuring their consistency with human judgments. Our new dataset enables us to formulate the problem as a multi-task learning problem and train a multi-column deep convolutional neural network (CNN) to simultaneously predict the severity of all the defects. Unlike some existing single-defect estimation methods that rely on low-level statistics and may fail in many cases on natural photographs, our model is able to understand image contents and quality at a higher level. As a result, in our experiments, we show that our model has predictions with much higher consistency with human judgments than low-level methods as well as several baseline CNN models. Our model also performs better than an average human from our user study.

We aim to generate high resolution shallow depth-of-field (DoF) images from a single all-in-focus image with controllable focal distance and aperture size. To achieve this, we propose a novel neural network model comprised of a depth prediction module, a lens blur module, and a guided upsampling module. All modules are differentiable and are learned from data. To train our depth prediction module, we collect a dataset of 2462 RGB-D images captured by mobile phones with a dual-lens camera, and use existing segmentation datasets to improve border prediction. We further leverage a synthetic dataset with known depth to supervise the lens blur and guided upsampling modules. The effectiveness of our system and training strategies are verified in the experiments. Our method can generate high-quality shallow DoF images at high resolution, and produces significantly fewer artifacts than the baselines and existing solutions for single image shallow DoF synthesis. Compared with the iPhone portrait mode, which is a state-of-the-art shallow DoF solution based on a dual-lens depth camera, our method generates comparable results, while allowing for greater flexibility to choose focal points and aperture size, and is not limited to one capture setup.

The performance of image retrieval has been improved tremendously in recent years through the use of deep feature representations. Most existing methods, however, aim to retrieve images that are visually similar or semantically relevant to the query, irrespective of spatial configuration. In this paper, we develop a spatial-semantic image search technology that enables users to search for images with both semantic and spatial constraints by manipulating concept text-boxes on a 2D query canvas. We train a convolutional neural network to synthesize appropriate visual features that captures the spatial-semantic constraints from the user canvas query. We directly optimize the retrieval performance of the visual features when training our deep neural network. These visual features then are used to retrieve images that are both spatially and semantically relevant to the user query. The experiments on large-scale datasets such as MS-COCO and Visual Genome show that our method outperforms other baseline and state-of-the-art methods in spatial-semantic image search.

Compositing is one of the most common operations in photo editing. To generate realistic composites, the appearances of foreground and background need to be adjusted to make them compatible. Previous approaches to harmonize composites have focused on learning statistical relationships between hand-crafted appearance features of the foreground and background, which is unreliable especially when the contents in the two layers are vastly different. In this work, we propose an end-to-end deep convolutional neural network for image harmonization, which can capture both the context and semantic information of the composite images during harmonization. We also introduce an efficient way to collect large-scale and high-quality training data that can facilitate the training process. Experiments on the synthesized dataset and real composite images show that the proposed network outperforms previous state-of-the-art methods.

Recently, there has been a lot of interest in automatically generating descriptions for an image. Most existing language-model based approaches for this task learn to generate an image description word by word in its original word order. However, for humans, it is more natural to locate the objects and their relationships first, and then elaborate on each object, describing notable attributes. We present a coarse-to-fine method that decomposes the original image description into a skeleton sentence and its attributes, and generates the skeleton sentence and attribute phrases separately. By this decomposition, our method can generate more accurate and novel descriptions than the previous state-of-the-art. Experimental results on the MS-COCO and a larger scale Stock3M datasets show that our algorithm yields consistent improvements across different evaluation metrics, especially on the SPICE metric, which has much higher correlation with human ratings than the conventional metrics. Furthermore, our algorithm can generate descriptions with varied length, benefiting from the separate control of the skeleton and attributes. This enables image description generation that better accommodates user preferences.

We present a scene parsing method that utilizes global context information based on both the parametric and nonparametric models. Compared to previous methods that only exploit the local relationship between objects, we train a context network based on scene similarities to generate feature representations for global contexts. In addition, these learned features are utilized to generate global and spatial priors for explicit classes inference. We then design modules to embed the feature representations and the priors into the segmentation network as additional global context cues. We show that the proposed method can eliminate false positives that are not compatible with the global context representations. Experiments on both the MIT ADE20K and PASCAL Context datasets show that the proposed method performs favorably against existing methods.

Video scene parsing is challenging due to the following two reasons: firstly, it is non-trivial to learn meaningful video representations for producing the temporally consistent labeling map; secondly, such a learning process becomes more difficult with insufficient labeled video training data. In this work, we propose a unified framework to address the above two problems, which is to our knowledge the first model to employ predictive feature learning in the video scene parsing. The predictive feature learning is carried out in two predictive tasks: frame prediction and predictive parsing. It is experimentally proved that the learned predictive features in our model are able to significantly enhance the video parsing performance by combining with the standard image parsing network. Interestingly, the performance gain brought by the predictive learning is almost costless as the features are learned from a large amount of unlabeled video data in an unsupervised way. Extensive experiments over two challenging datasets, Cityscapes and Camvid, have demonstrated the effectiveness of our model by showing remarkable improvement over well-established baselines.

Parsing urban scene images benefits many applications, especially self-driving. Most of the current solutions employ generic image parsing models that treat all scales and locations in the images equally and do not consider the geometry property of car-captured urban scene images. Thus, they suffer from heterogeneous object scales caused by perspective projection of cameras on actual scenes and inevitably encounter parsing failures on distant objects as well as other boundary and recognition errors. In this work, we propose a new FoveaNet model to fully exploit the perspective geometry of scene images and address the common failures of generic parsing models. FoveaNet estimates the perspective geometry of a scene image through a convolutional network which integrates supportive evidence from contextual objects within the image. Based on the perspective geometry information, FoveaNet “undoes” the camera perspective projection - analyzing regions in the space of the actual scene, and thus provides much more reliable parsing results. Furthermore, to effectively address the recognition errors, FoveaNet introduces a new dense CRFs model that takes the perspective geometry as a prior potential. We evaluate FoveaNet on two urban scene parsing datasets, Cityspaces and CamVid, which demonstrates that FoveaNet can outperform all the well-established baselines and provide new state-of-the-art performance.

In this paper we are interested in the problem of image segmentation given natural language descriptions, i.e. referring expressions. Existing works tackle this problem by first modeling images and sentences independently and then segment images by combining these two types of representations. We argue that learning word-to-image interaction is more native in the sense of jointly modeling two modalities for the image segmentation task, and we propose convolutional multimodal LSTM to encode the sequential interactions between individual words, visual information, and spatial information. We show that our proposed model outperforms the baseline model on benchmark datasets. In addition, we analyze the intermediate output of the proposed multimodal LSTM approach and empirically explain how this approach enforces a more effective word-to-image interaction.

Automatic image aesthetics rating has received a growing interest with the recent breakthrough in deep learning. Although many studies exist for learning a generic or universal aesthetics model, investigation of aesthetics models incorporating individual user's preference is quite limited. We address this personalized aesthetics problem by showing that individual's aesthetic preferences exhibit strong correlations with content and aesthetic attributes, and hence the deviation of individual's perception from generic image aesthetics is predictable. To accommodate our study, we first collect two distinct datasets, a large image dataset from Flickr and annotated by Amazon Mechanical Turk, and a small dataset of real personal albums rated by owners. We then propose a new approach to personalized aesthetics learning that can be trained even with a small set of annotated images from a user. The approach is based on a residual-based model adaptation scheme which learns an offset to compensate for the generic aesthetics score. Finally, we introduce an active learning algorithm to optimize personalized aesthetics prediction for real-world application scenarios. Experiments demonstrate that our approach can effectively learn personalized aesthetics preferences, and outperforms existing methods on quantitative comparisons.

It is important for intelligent systems, e.g. autonomous vehicles and robotics to anticipate the future in order to plan early and make decisions accordingly. Predicting the future scene parsing and motion dynamics helps the agents better understand the visual environment better as the former provides dense semantic segmentations, i.e. what objects will be present and where they will appear, while the latter provides dense motion information, i.e. how the objects move in the future. In this paper, we propose a novel model to predict the scene parsing and motion dynamics in unobserved future video frames simultaneously. Using history information (preceding frames and corresponding scene parsing results) as input, our model is able to predict the scene parsing and motion for arbitrary time steps ahead. More importantly, our model is superior compared to other methods that predict parsing and motion separately, as the complementary relationship between the two tasks are fully utilized in our model through joint learning. To our best knowledge, this is the first attempt in jointly predicting scene parsing and motion dynamics in the future frames. On the large-scale Cityscapes dataset, it is demonstrated that our model produces significantly better parsing and motion prediction results compared to well established baselines. In addition, we also show our model can be used to predict the steering angle of the vehicles, which further verifies the ability of our model to learn underlying latent parameters.

In this paper, we introduce a novel shortlist computation algorithm for approximate, high-dimensional nearest neighbor search. Our method relies on a novel distance estimator: the residual-aware distance estimator, that accounts for the residual distances of data points to their respective quantized centroids, and uses it for accurate short-list computation. Furthermore, we perform the residual-aware distance estimation with little additional memory and computational cost through simple pre-computation methods for inverted index and multi-index schemes. Because it modifies the initial shortlist collection phase, our new algorithm is applicable to most inverted indexing methods that use vector quantization. We have tested the proposed method with the inverted index and multi-index on a diverse set of benchmarks including up to one billion data points with varying dimensions, and found that our method robustly improves the accuracy of shortlists (up to 127% relatively higher) over the state-of-the-art techniques with a comparable or even faster computational cost.

We introduce a new technique that automatically generates diverse, visually compelling stylizations for a photograph in an unsupervised manner. We achieve this by learning style ranking for a given input using a large photo collection and selecting a diverse subset of matching styles for final style transfer. We also propose an improved technique that transfers the global color and tone of the chosen exemplars to the input photograph while avoiding the common visual artifacts produced by the existing style transfer methods. Together, our style selection and transfer techniques produce compelling, artifact-free results on a wide range of input photographs, and a user study shows that our results are preferred over other techniques.

In this work, we present a new framework for person recognition in photo albums that exploits contextual cues at multiple levels, spanning individual persons, individual photos, and photo groups. Through experiments, we show that the information available at each of these distinct contextual levels provides complementary cues as to person identities. At the person level, we leverage clothing and body appearance in addition to facial appearance, and to compensate for instances where the faces are not visible. At the photo level we leverage a learned prior on the joint distribution of identities on the same photo to guide the identity assignments. Going beyond a single photo, we are able to infer natural groupings of photos with shared context in an unsupervised manner. By exploiting this shared contextual information, we are able to reduce the identity search space and exploit higher intra-personal appearance consistency within photo groups. Our new framework enables efficient use of these complementary multi-level contextual cues to improve overall recognition rates on the photo album person recognition task, as demonstrated through state-of-theart results on a challenging public dataset. Our results outperform competing methods by a significant margin, while being computationally efficient and practical in a real world application.

When creating a photo album of an event, people typically select a few important images to keep or share. There is some consistency in the process of choosing the important images, and discarding the unimportant ones. Modeling this selection process will assist automatic photo selection and album summarization. In this paper, we show that the selection of important images is consistent among different viewers, and that this selection process is related to the event type of the album. We introduce the concept of event-specific image importance. We collected a new event album dataset with human annotation of the relative image importance with each event album. We also propose a Convolutional Neural Network (CNN) based method to predict the image importance score of a given event album, using a novel rank loss function and a progressive training scheme. Results demonstrate that our method significantly outperforms various baseline methods.

We aim at detecting salient objects in unconstrained images. In unconstrained images, the number of salient objects (if any) varies from image to image, and is not given. We present a salient object detection system that directly outputs a compact set of detection windows, if any, for an input image. Our system leverages a Convolutional-Neural-Network model to generate location proposals of salient objects. Location proposals tend to be highly overlapping and noisy. Based on the Maximum a Posteriori principle, we propose a novel subset optimization framework to generate a compact set of detection windows out of noisy proposals. In experiments, we show that our subset optimization formulation greatly enhances the performance of our system, and our system attains 16-34% relative improvement in Average Precision compared with the state-of-the-art on three challenging salient object datasets.

How to jointly represent images and texts is important for tasks involving both modalities. Visual-semantic embedding models have been recently proposed and shown to be effective. The key idea is that by learning a mapping from images into a semantic text space, the algorithm is able to learn a compact and effective joint representation. However, existing approaches simply map each text concept to a single point in the semantic space. Mapping instead to a density distribution provides many interesting advantages, including better capturing uncertainty about each text concept, and enabling better geometric interpretation of concepts such as inclusion, intersection, etc. In this work, we present a novel Gaussian Visual-Semantic Embedding (GVSE) model, which leverages the visual information to model text concepts as Gaussian distributions in semantic space. Experiments in two tasks, image classification and text-based image retrieval on the large scale MIT Places205 dataset, have demonstrated the superiority of our method over existing approaches, with higher accuracy and better robustness.

In this paper, we propose a new method for detecting primary objects in unconstrained videos in a completely automatic setting. Here, we define the primary object in a video as the object that presents saliently in most of the frames. Unlike previous works considering only local saliency detection or common pattern discovery, the proposed method integrates the local visual/motion saliency extracted from each frame, global appearance consistency throughout the video, and spatiotemporal smoothness constraint on object trajectories. We first identify a temporal coherent salient region throughout the whole video, and then explicitly learn a global appearance model to distinguish the primary object against the background. In order to obtain high-quality saliency estimations from both appearance and motion cues, we propose a novel self-adaptive saliency map fusion method by learning the reliability of saliency maps from labeled data. As a whole, our method can robustly localize and track primary objects in diverse video content, and handle the challenges such as fast object and camera motion, large scale and appearance variation, background clutter, and pose deformation. Moreover, compared with some existing approaches that assume the object is present in all the frames, our approach can naturally handle the case where the object is present only in part of the frames, e.g., the object enters the scene in the middle of the video or leaves the scene before the video ends. We also propose a new video data set containing 51 videos for primary object detection with per-frame ground-truth labeling. Quantitative experiments on several challenging video data sets demonstrate the superiority of our method compared with the recent state of the arts.

Automatic segmentation of the primary object in a video clip is a challenging problem as there is no prior knowledge of the primary object. Most existing techniques thus adapt an iterative approach for foreground and background appearance modeling, i.e., fix the appearance model while optimizing the segmentation and fix the segmentation while optimizing the appearance model. However, these approaches may rely on good initialization and can be easily trapped in local optimal. In addition, they are usually time consuming for analyzing videos. To address these limitations, we propose a novel and efficient appearance modeling technique for automatic primary video object segmentation in the Markov random field (MRF) framework. It embeds the appearance constraint as auxiliary nodes and edges in the MRF structure, and can optimize both the segmentation and appearance model parameters simultaneously in one graph cut. The extensive experimental evaluations validate the superiority of the proposed approach over the state-of-the-art methods, in both efficiency and effectiveness.

Skies are common backgrounds in photos but are often less interesting due to the time of photographing. Professional photographers correct this by using sophisticated tools with painstaking efforts that are beyond the command of ordinary users. In this work, we propose an automatic background replacement algorithm that can generate realistic, artifact-free images with a diverse styles of skies. The key idea of our algorithm is to utilize visual semantics to guide the entire process including sky segmentation, search and replacement. First we train a deep convolutional neural network for semantic scene parsing, which is used as visual prior to segment sky regions in a coarse-to-fine manner. Second, in order to find proper skies for replacement, we propose a data-driven sky search scheme based on semantic layout of the input image. Finally, to re-compose the stylized sky with the original foreground naturally, an appearance transfer method is developed to match statistics locally and semantically. We show that the proposed algorithm can automatically generate a set of visually pleasing results. In addition, we demonstrate the effectiveness of the proposed algorithm with extensive user studies.

Image feature representation plays an essential role in image recognition and related tasks. The current state-of-the-art feature learning paradigm is supervised learning from labeled data. However, this paradigm requires large-scale category labels, which limits its applicability to domains where labels are hard to obtain. In this paper, we propose a new data-driven feature learning paradigm which does not rely on category labels. Instead, we learn from user behavior data collected on social media. Concretely, we use the image relationship discovered in the latent space from the user behavior data to guide the image feature learning. We collect a large-scale image and user behavior dataset from Behance.net. The dataset consists of 1.9 million images and over 300 million view records from 1.9 million users. We validate our feature learning paradigm on this dataset and find that the learned feature significantly outperforms the state-of-the-art image features in learning better image similarities. We also show that the learned feature performs competitively on various recognition benchmarks.

In real-world face detection, large visual variations, such as those due to pose, expression, and lighting, demand an advanced discriminative model to accurately differentiate faces from the backgrounds. Consequently, effective models for the problem tend to be computationally prohibitive. To address these two conflicting challenges, we propose a cascade architecture built on convolutional neural networks (CNNs) with very powerful discriminative capability, while maintaining high performance. The proposed CNN cascade operates at multiple resolutions, quickly rejects the background regions in the fast low resolution stages, and carefully evaluates a small number of challenging candidates in the last high resolution stage. To improve localization effectiveness, and reduce the number of candidates at later stages, we introduce a CNN-based calibration stage after each of the detection stages in the cascade. The output of each calibration stage is used to adjust the detection window position for input to the subsequent stage. The proposed method runs at 14 FPS on a single CPU core for VGA-resolution images and 100 FPS using a GPU, and achieves state-of-the-art detection performance on two public face detection benchmarks.

Depth estimation and semantic segmentation are two fundamental problems in image understanding. While the two tasks are strongly correlated and mutually beneficial, they are usually solved separately or sequentially. Motivated by the complementary properties of the two tasks, we propose a unified framework for joint depth and semantic prediction. Given an image, we first use a trained Convolutional Neural Network (CNN) to jointly predict a global layout composed of pixel-wise depth values and semantic labels. By allowing for interactions between the depth and semantic information, the joint network provides more accurate depth prediction than a state-of-the-art CNN trained solely for depth prediction [6]. To further obtain fine-level details, the image is decomposed into local segments for region-level depth and semantic prediction under the guidance of global layout. Utilizing the pixel-wise global prediction and region-wise local prediction, we formulate the inference problem in a two-layer Hierarchical Conditional Random Field (HCRF) to produce the final depth and semantic map. As demonstrated in the experiments, our approach effectively leverages the advantages of both tasks and provides the state-of-the-art results.

Object segmentation is highly desirable for image understanding and editing. Current interactive tools require a great deal of user effort while automatic methods are usually limited to images of special object categories or with high color contrast. In this paper, we propose a data-driven algorithm that uses examples to break through these limits. As similar objects tend to share similar local shapes, we match query image patches with example images in multiscale to enable local shape transfer. The transferred local shape masks constitute a patch-level segmentation solution space and we thus develop a novel cascade algorithm, PatchCut, for coarse-to-fine object segmentation. In each stage of the cascade, local shape mask candidates are selected to refine the estimated segmentation of the previous stage iteratively with color models. Experimental results on various datasets (Weizmann Horse, Fashionista, Object Discovery and PASCAL) demonstrate the effectiveness and robustness of our algorithm.

People can immediately and precisely identify that an image contains 1, 2, 3 or 4 items by a simple glance. The phenomenon, known as Subitizing, inspires us to pursue the task of Salient Object Subitizing (SOS), i.e. predicting the existence and the number of salient objects in a scene using holistic cues. To study this problem, we propose a new image dataset annotated using an online crowdsourcing marketplace. We show that a proposed subitizing technique using an end-to-end Convolutional Neural Network (CNN) model achieves significantly better than chance performance in matching human labels on our dataset. It attains 94% accuracy in detecting the existence of salient objects, and 42–82% accuracy (chance is 20%) in predicting the number of salient objects (1, 2, 3, and 4+), without resorting to any object localization process. Finally, we demonstrate the usefulness of the proposed subitizing technique in two computer vision applications: salient object detection and object proposal.

This paper investigates problems of image style, aesthetics, and quality estimation, which require fine-grained details from high-resolution images, utilizing deep neural network training approach. Existing deep convolutional neural networks mostly extracted one patch such as a down-sized crop from each image as a training example. However, one patch may not always well represent the entire image, which may cause ambiguity during training. We propose a deep multi-patch aggregation network training approach, which allows us to train models using multiple patches generated from one image. We achieve this by constructing multiple, shared columns in the neural network and feeding multiple patches to each of the columns. More importantly, we propose two novel network layers (statistics and sorting) to support aggregation of those patches. The proposed deep multi-patch aggregation network integrates shared feature learning and aggregation function learning into a unified framework. We demonstrate the effectiveness of the deep multi-patch aggregation network on the three problems, i.e., image style recognition, aesthetic quality categorization, and image quality estimation. Our models trained using the proposed networks significantly outperformed the state of the art in all three applications.

Segmenting semantic objects from images and parsing them into their respective semantic parts are fundamental steps towards detailed object understanding in computer vision. In this paper, we propose a joint solution that tackles semantic object and part segmentation simultaneously, in which higher object-level context is provided to guide part segmentation, and more detailed part-level localization is utilized to refine object segmentation. Specifically, we first introduce the concept of semantic compositional parts (SCP) in which similar semantic parts are grouped and shared among different objects. A two-stream fully convolutional network (FCN) is then trained to provide the SCP and object potentials at each pixel. At the same time, a compact set of segments can also be obtained from the SCP predictions of the network. Given the potentials and the generated segments, in order to explore long-range context, we finally construct an efficient fully connected conditional random field (FCRF) to jointly predict the final object and part labels. Extensive evaluation on three different datasets shows that our approach can mutually enhance the performance of object and part segmentation, and outperforms the current state-of-the-art on both tasks.

We propose a highly efficient, yet powerful, salient object detection method based on the Minimum Barrier Distance (MBD) Transform. The MBD transform is robust to pixel-value fluctuation, and thus can be effectively applied on raw pixels without region abstraction. We present an approximate MBD transform algorithm with 100X speedup over the exact algorithm. An error bound analysis is also provided. Powered by this fast MBD transform algorithm, the proposed salient object detection method runs at 80 FPS, and significantly outperforms previous methods with similar speed on four large benchmark datasets, and achieves comparable or better performance than state-of-the-art methods. Furthermore, a technique based on color whitening is proposed to extend our method to leverage the appearance-based backgroundness cue. This extended version further improves the performance, while still being one order of magnitude faster than all the other leading methods.

We present a new patch-based approach for image denoising that combines similar patches in the same image and from a set of training images. The key idea of our method is that we can partition the training samples according to the clean patches and efficiently learn a denoising operator for each partition. Given a noisy patch, we use self-similarity to compute an initial denoising result which is used to locate the relevant partitions. We apply the corresponding learned denoising operator to the original noisy patch. Our method does not suffer either from the blurring effect that commonly exists in self-similarity based methods or from the training size problem that is associated with training-based methods. We evaluate our method on three benchmark datasets as well as real mobile images. Experimental results show that our approach consistently outperforms BM3D in terms of both peak signal-to-noise ratio and visual quality.

Cropping is one of the most fundamental and common operations in image processing for improving the aesthetic quality of photographs. Instead of manually designing rules for cropping, in this paper, we propose a generative model that learns an aesthetic photo cropping cascade from a large database of well-composed images and a dataset containing images with crops generated by expert photographers. Specifically, this model includes cropping priori, intuitive likelihood, compositional likelihood and change likelihood. Our learning exploits a spatial pyramid saliency feature and a multi-level foreground segmentation. The inference is done by efficient sub window search (ESS) [10] which is benefited from the bound at conditional distribution in the cascade. Additionally, for extracting attentional subjects and capturing scene composition, we design an iterative saliency method to model the saliency moving paths, which is beyond the typical saliency model predicting a single attentional region. Experiments show that our approach outperforms the state-of-the-art cropping methods by a large margin.

Classifying large-scale image data into object categories is an important problem that has received increasing research attention. Given the huge amount of data, non-parametric approaches such as nearest neighbor classifiers have shown promising results, especially when they are underpinned by a learned distance or similarity measurement. Although metric learning has been well studied in the past decades, most existing algorithms are impractical to handle large-scale data sets. In this paper, we present an image similarity learning method that can scale well in both the number of images and the dimensionality of image descriptors. To this end, similarity comparison is restricted to each sample's local neighbors and a discriminative similarity measure is induced from large margin neighborhood embedding. We also exploit the ensemble of projections so that high-dimensional features can be processed in a set of lower-dimensional subspaces in parallel. The efficiency and scalability of our proposed model are validated on several data sets with scales varying from tens of thousands to one million images.

Abstract We present a data‐driven method for automatically cropping photographs to be well‐composed and aesthetically pleasing. Our method matches the composition of an amateur's photograph to an expert's using point correspondences. The correspondences are based on a novel high‐level local descriptor we term the ‘Object Context’. Object Context is an extension of Shape Context: it is a descriptor encoding which objects and scene elements surround a given point. By searching a database of expertly composed images, we can find a crop window which makes an amateur's photograph closely match the composition of a database exemplar. We cull irrelevant matches in the database efficiently using a global descriptor which encodes the objects in the scene. For images with similar content in the database, we efficiently search the space of possible crops using generalized Hough voting. When comparing the result of our algorithm to expert crops, our crop windows overlap the expert crops by 83.6%. We also perform a user study which shows that our crops compare favourably to an expert humans' crops.

In this letter, we introduce a subcategory-aware object detection framework to detect generic object classes with high intra-class variance. Motivated by the observation that the object appearance demonstrates some clustering property, we split the training data into subcategories and train a detector for each subcategory. Since the proposed ensemble of detectors relies heavily on subcategory clustering, we propose an effective subcategories generation method that is tuned for the detection task. More specifically, we first initialize subcategories by constrained spectral clustering based on mid-level image features used in object recognition. Then we jointly learn the ensemble detectors and the latent subcategories in an alternative manner. Our performance on the PASCAL VOC 2007 detection challenges and INRIA Person dataset is comparable with state-of-the-art, even with much less computational cost.

In this paper, we propose a novel label propagation-based method for saliency detection. A key observation is that saliency in an image can be estimated by propagating the labels extracted from the most certain background and object regions. For most natural images, some boundary superpixels serve as the background labels and the saliency of other superpixels are determined by ranking their similarities to the boundary labels based on an inner propagation scheme. For images of complex scenes, we further deploy a threecue-center-biased objectness measure to pick out and propagate foreground labels. A co-transduction algorithm is devised to fuse both boundary and objectness labels based on an inter propagation scheme. The compactness criterion decides whether the incorporation of objectness labels is necessary, thus greatly enhancing computational efficiency. Results on five benchmark data sets with pixelwise accurate annotations show that the proposed method achieves superior performance compared with the newest state-of-the-arts in terms of different evaluation metrics.

In this paper, we propose a novel adaptive metric learning algorithm (AML) for visual saliency detection. A key observation is that the saliency of a superpixel can be estimated by the distance from the most certain foreground and background seeds. Instead of measuring distance on the Euclidean space, we present a learning method based on two complementary Mahalanobis distance metrics: 1) generic metric learning (GML) and 2) specific metric learning (SML). GML aims at the global distribution of the whole training set, while SML considers the specific structure of a single image. Considering that multiple similarity measures from different views may enhance the relevant information and alleviate the irrelevant one, we try to fuse the GML and SML together and experimentally find the combining result does work well. Different from the most existing methods which are directly based on low-level features, we devise a superpixelwise Fisher vector coding approach to better distinguish salient objects from the background. We also propose an accurate seeds selection mechanism and exploit contextual and multiscale information when constructing the final saliency map. Experimental results on various image sets show that the proposed AML performs favorably against the state-of-the-arts.

Image priors are essential to many image restoration applications, including denoising, deblurring, and inpainting. Existing methods use either priors from the given image (internal) or priors from a separate collection of images (external). We find through statistical analysis that unifying the internal and external patch priors may yield a better patch prior. We propose a novel prior learning algorithm that combines the strength of both internal and external priors. In particular, we first learn a generic Gaussian mixture model from a collection of training images and then adapt the model to the given image by simultaneously adding additional components and refining the component parameters. We apply this image-specific prior to image denoising. The experimental results show that our approach yields better or competitive denoising results in terms of both the peak signal-to-noise ratio and structural similarity.

This paper investigates unified feature learning and classifier training approaches for image aesthetics assessment . Existing methods built upon handcrafted or generic image features and developed machine learning and statistical modeling techniques utilizing training examples. We adopt a novel deep neural network approach to allow unified feature learning and classifier training to estimate image aesthetics. In particular, we develop a double-column deep convolutional neural network to support heterogeneous inputs, i.e., global and local views, in order to capture both global and local characteristics of images . In addition, we employ the style and semantic attributes of images to further boost the aesthetics categorization performance . Experimental results show that our approach produces significantly better results than the earlier reported results on the AVA dataset for both the generic image aesthetics and content -based image aesthetics. Moreover, we introduce a 1.5-million image dataset (IAD) for image aesthetics assessment and we further boost the performance on the AVA test set by training the proposed deep neural networks on the IAD dataset.

Many binary code embedding techniques have been proposed for large-scale approximate nearest neighbor search in computer vision. Recently, product quantization that encodes the cluster index in each subspace has been shown to provide impressive accuracy for nearest neighbor search. In this paper, we explore a simple question: is it best to use all the bit budget for encoding a cluster index in each subspace? We have found that as data points are located farther away from the centers of their clusters, the error of estimated distances among those points becomes larger. To address this issue, we propose a novel encoding scheme that distributes the available bit budget to encoding both the cluster index and the quantized distance between a point and its cluster center. We also propose two different distance metrics tailored to our encoding scheme. We have tested our method against the-state-of-the-art techniques on several well-known benchmarks, and found that our method consistently improves the accuracy over other tested methods. This result is achieved mainly because our method accurately estimates distances between two data points with the new binary codes and distance metric.

Despite the fact that face detection has been studied intensively over the past several decades, the problem is still not completely solved. Challenging conditions, such as extreme pose, lighting, and occlusion, have historically hampered traditional, model-based methods. In contrast, exemplar-based face detection has been shown to be effective, even under these challenging conditions, primarily because a large exemplar database is leveraged to cover all possible visual variations. However, relying heavily on a large exemplar database to deal with the face appearance variations makes the detector impractical due to the high space and time complexity. We construct an efficient boosted exemplar-based face detector which overcomes the defect of the previous work by being faster, more memory efficient, and more accurate. In our method, exemplars as weak detectors are discriminatively trained and selectively assembled in the boosting framework which largely reduces the number of required exemplars. Notably, we propose to include non-face images as negative exemplars to actively suppress false detections to further improve the detection accuracy. We verify our approach over two public face detection benchmarks and one personal photo album, and achieve significant improvement over the state-of-the-art algorithms in terms of both accuracy and efficiency.

We propose a data-driven approach to facial landmark localization that models the correlations between each landmark and its surrounding appearance features. At runtime, each feature casts a weighted vote to predict landmark locations, where the weight is precomputed to take into account the feature's discriminative power. The feature voting-based landmark detection is more robust than previous local appearance-based detectors, we combine it with nonparametric shape regularization to build a novel facial landmark localization pipeline that is robust to scale, in-plane rotation, occlusion, expression, and most importantly, extreme head pose. We achieve state-of-the-art performance on two especially challenging in-the-wild datasets populated by faces with extreme head pose and expression.

Cropping is one of the most common tasks in image editing for improving the aesthetic quality of a photograph. In this paper, we propose a new, aesthetic photo cropping system which combines three models: visual composition, boundary simplicity, and content preservation. The visual composition model measures the quality of composition for a given crop. Instead of manually defining rules or score functions for composition, we learn the model from a large set of well-composed images via discriminative classifier training. The boundary simplicity model measures the clearness of the crop boundary to avoid object cutting-through. The content preservation model computes the amount of salient information kept in the crop to avoid excluding important content. By assigning a hard lower bound constraint on the content preservation and linearly combining the scores from the visual composition and boundary simplicity models, the resulting system achieves significant improvement over recent cropping methods in both quantitative and qualitative evaluation.

Effective visual features are essential for computational aesthetic quality rating systems. Existing methods used machine learning and statistical modeling techniques on handcrafted features or generic image descriptors. A recently-published large-scale dataset, the AVA dataset, has further empowered machine learning based approaches. We present the RAPID (RAting PIctorial aesthetics using Deep learning) system, which adopts a novel deep neural network approach to enable automatic feature learning. The central idea is to incorporate heterogeneous inputs generated from the image, which include a global view and a local view, and to unify the feature learning and classifier training using a double-column deep convolutional neural network. In addition, we utilize the style attributes of images to help improve the aesthetic quality categorization accuracy. Experimental results show that our approach significantly outperforms the state of the art on the AVA dataset.

One fundamental problem in object retrieval with the bag-of-words model is its lack of spatial information. Although various approaches are proposed to incorporate spatial constraints into the model, most of them are either too strict or too loose so that they are only effective in limited cases. In this paper, a new spatially-constrained similarity measure (SCSM) is proposed to handle object rotation, scaling, view point change and appearance deformation. The similarity measure can be efficiently calculated by a voting-based method using inverted files. During the retrieval process, object localization in the database images can also be simultaneously achieved using SCSM without post-processing. Furthermore, based on the retrieval and localization results of SCSM, we introduce a novel and robust re-ranking method with the k-nearest neighbors of the query for automatically refining the initial search results. Extensive performance evaluations on six public data sets show that SCSM significantly outperforms other spatial models including RANSAC-based spatial verification, while k-NN re-ranking outperforms most state-of-the-art approaches using query expansion. We also adapted SCSM for mobile product image search with an iterative algorithm to simultaneously extract the product instance from the mobile query image, identify the instance, and retrieve visually similar product images. Experiments on two product image search data sets show that our approach can robustly localize and extract the product in the query image, and hence drastically improve the retrieval accuracy over baseline methods.

We present an optical flow algorithm for large displacement motions. Most existing optical flow methods use the standard coarse-to-fine framework to deal with large displacement motions which has intrinsic limitations. Instead, we formulate the motion estimation problem as a motion segmentation problem. We use approximate nearest neighbor fields to compute an initial motion field and use a robust algorithm to compute a set of similarity transformations as the motion candidates for segmentation. To account for deviations from similarity transformations, we add local deformations in the segmentation process. We also observe that small objects can be better recovered using translations as the motion candidates. We fuse the motion results obtained under similarity transformations and under translations together before a final refinement. Experimental validation shows that our method can successfully handle large displacement motions. Although we particularly focus on large displacement motions in this work, we make no sacrifice in terms of overall performance. In particular, our method ranks at the top of the Middlebury benchmark.

Pose variation remains to be a major challenge for real-world face recognition. We approach this problem through a probabilistic elastic matching method. We take a part based representation by extracting local features (e.g., LBP or SIFT) from densely sampled multi-scale image patches. By augmenting each feature with its location, a Gaussian mixture model (GMM) is trained to capture the spatial-appearance distribution of all face images in the training corpus. Each mixture component of the GMM is confined to be a spherical Gaussian to balance the influence of the appearance and the location terms. Each Gaussian component builds correspondence of a pair of features to be matched between two faces/face tracks. For face verification, we train an SVM on the vector concatenating the difference vectors of all the feature pairs to decide if a pair of faces/face tracks is matched or not. We further propose a joint Bayesian adaptation algorithm to adapt the universally trained GMM to better model the pose variations between the target pair of faces/face tracks, which consistently improves face verification accuracy. Our experiments show that our method outperforms the state-of-the-art in the most restricted protocol on Labeled Face in the Wild (LFW) and the YouTube video face database by a significant margin.

Detecting faces in uncontrolled environments continues to be a challenge to traditional face detection methods due to the large variation in facial appearances, as well as occlusion and clutter. In order to overcome these challenges, we present a novel and robust exemplar-based face detector that integrates image retrieval and discriminative learning. A large database of faces with bounding rectangles and facial landmark locations is collected, and simple discriminative classifiers are learned from each of them. A voting-based method is then proposed to let these classifiers cast votes on the test image through an efficient image retrieval technique. As a result, faces can be very efficiently detected by selecting the modes from the voting maps, without resorting to exhaustive sliding window-style scanning. Moreover, due to the exemplar-based framework, our approach can detect faces under challenging conditions without explicitly modeling their variations. Evaluation on two public benchmark datasets shows that our new face detection approach is accurate and efficient, and achieves the state-of-the-art performance. We further propose to use image retrieval for face validation (in order to remove false positives) and for face alignment/landmark localization. The same methodology can also be easily generalized to other face-related tasks, such as attribute recognition, as well as general object detection.

In this work, we propose an exemplar-based face image segmentation algorithm. We take inspiration from previous works on image parsing for general scenes. Our approach assumes a database of exemplar face images, each of which is associated with a hand-labeled segmentation map. Given a test image, our algorithm first selects a subset of exemplar images from the database, Our algorithm then computes a nonrigid warp for each exemplar image to align it with the test image. Finally, we propagate labels from the exemplar images to the test image in a pixel-wise manner, using trained weights to modulate and combine label maps from different exemplars. We evaluate our method on two challenging datasets and compare with two face parsing algorithms and a general scene parsing algorithm. We also compare our segmentation results with contour-based face alignment results, that is, we first run the alignment algorithms to extract contour points and then derive segments from the contours. Our algorithm compares favorably with all previous works on all datasets evaluated.

We propose a fast regression model for practical single image super-resolution based on in-place examples, by leveraging two fundamental super-resolution approaches- learning from an external database and learning from self-examples. Our in-place self-similarity refines the recently proposed local self-similarity by proving that a patch in the upper scale image have good matches around its origin location in the lower scale image. Based on the in-place examples, a first-order approximation of the nonlinear mapping function from low-to high-resolution image patches is learned. Extensive experiments on benchmark and real-world images demonstrate that our algorithm can produce natural-looking results with sharp edges and preserved fine details, while the current state-of-the-art algorithms are prone to visual artifacts. Furthermore, our model can easily extend to deal with noise by combining the regression results on multiple in-place examples for robust estimation. The algorithm runs fast and is particularly useful for practical applications, where the input images typically contain diverse textures and they are potentially contaminated by noise or compression artifacts.

In this paper, we present a new approach for text localization in natural images, by discriminating text and non-text regions at three levels: pixel, component and text line levels. Firstly, a powerful low-level filter called the Stroke Feature Transform (SFT) is proposed, which extends the widely-used Stroke Width Transform (SWT) by incorporating color cues of text pixels, leading to significantly enhanced performance on inter-component separation and intra-component connection. Secondly, based on the output of SFT, we apply two classifiers, a text component classifier and a text-line classifier, sequentially to extract text regions, eliminating the heuristic procedures that are commonly used in previous approaches. The two classifiers are built upon two novel Text Covariance Descriptors (TCDs) that encode both the heuristic properties and the statistical characteristics of text stokes. Finally, text regions are located by simply thresholding the text-line confident map. Our method was evaluated on two benchmark datasets: ICDAR 2005 and ICDAR 2011, and the corresponding F-measure values are 0.72 and 0.73, respectively, surpassing previous methods in accuracy by a large margin.

We propose an unsupervised detector adaptation algorithm to adapt any offline trained face detector to a specific collection of images, and hence achieve better accuracy. The core of our detector adaptation algorithm is a probabilistic elastic part (PEP) model, which is offline trained with a set of face examples. It produces a statistically aligned part based face representation, namely the PEP representation. To adapt a general face detector to a collection of images, we compute the PEP representations of the candidate detections from the general face detector, and then train a discriminative classifier with the top positives and negatives. Then we re-rank all the candidate detections with this classifier. This way, a face detector tailored to the statistics of the specific image collection is adapted from the original detector. We present extensive results on three datasets with two state-of-the-art face detectors. The significant improvement of detection accuracy over these state of-the-art face detectors strongly demonstrates the efficacy of the proposed face detector adaptation algorithm.

Localizing facial landmarks is a fundamental step in facial image analysis. However, the problem is still challenging due to the large variability in pose and appearance, and the existence of occlusions in real-world face images. In this paper, we present exemplar-based graph matching (EGM), a robust framework for facial landmark localization. Compared to conventional algorithms, EGM has three advantages: (1) an affine-invariant shape constraint is learned online from similar exemplars to better adapt to the test face, (2) the optimal landmark configuration can be directly obtained by solving a graph matching problem with the learned shape constraint, (3) the graph matching problem can be optimized efficiently by linear programming. To our best knowledge, this is the first attempt to apply a graph matching technique for facial landmark localization. Experiments on several challenging datasets demonstrate the advantages of EGM over state-of-the-art methods.

A label consistent K-SVD (LC-KSVD) algorithm to learn a discriminative dictionary for sparse coding is presented. In addition to using class labels of training data, we also associate label information with each dictionary item (columns of the dictionary matrix) to enforce discriminability in sparse codes during the dictionary learning process. More specifically, we introduce a new label consistency constraint called "discriminative sparse-code error" and combine it with the reconstruction error and the classification error to form a unified objective function. The optimal solution is efficiently obtained using the K-SVD algorithm. Our algorithm learns a single overcomplete dictionary and an optimal linear classifier jointly. The incremental dictionary learning algorithm is presented for the situation of limited memory resources. It yields dictionaries so that feature points with the same class labels have similar sparse codes. Experimental results demonstrate that our algorithm outperforms many recently proposed sparse-coding techniques for face, action, scene, and object category recognition under the same learning conditions.

One fundamental problem in object retrieval with the bag-of-visual words (BoW) model is its lack of spatial information. Although various approaches are proposed to incorporate spatial constraints into the BoW model, most of them are either too strict or too loose so that they are only effective in limited cases. We propose a new spatially-constrained similarity measure (SCSM) to handle object rotation, scaling, view point change and appearance deformation. The similarity measure can be efficiently calculated by a voting-based method using inverted files. Object retrieval and localization are then simultaneously achieved without post-processing. Furthermore, we introduce a novel and robust re-ranking method with the k-nearest neighbors of the query for automatically refining the initial search results. Extensive performance evaluations on six public datasets show that SCSM significantly outperforms other spatial models, while k-NN re-ranking outperforms most state-of-the-art approaches using query expansion.

In this paper, we propose a bilevel sparse coding model for coupled feature spaces, where we aim to learn dictionaries for sparse modeling in both spaces while enforcing some desired relationships between the two signal spaces. We first present our new general sparse coding model that relates signals from the two spaces by their sparse representations and the corresponding dictionaries. The learning algorithm is formulated as a generic bilevel optimization problem, which is solved by a projected first-order stochastic gradient descent algorithm. This general sparse coding model can be applied to many specific applications involving coupled feature spaces in computer vision and signal processing. In this work, we tailor our general model to learning dictionaries for compressive sensing recovery and single image super-resolution to demonstrate its effectiveness. In both cases, the new sparse coding model remarkably outperforms previous approaches in terms of recovery accuracy.

We introduce an efficient computational framework to extract multi-scale feature descriptors. The framework is based on sharing of descriptor elements across the image and scale space to minimize redundant computation. Any type of local patch or grid-based features can be computed through this framework for capturing coarse-to-fine object appearances. We apply it to human detection by boosting a strong soft cascade classifier. Our experiments demonstrate that the proposed descriptors achieve superior performance both in computational efficiency and detection accuracy.

A shape-motion prototype-based approach is introduced for action recognition. The approach represents an action as a sequence of prototypes for efficient and flexible action matching in long video sequences. During training, an action prototype tree is learned in a joint shape and motion space via hierarchical K-means clustering and each training sequence is represented as a labeled prototype sequence; then a look-up table of prototype-to-prototype distances is generated. During testing, based on a joint probability model of the actor location and action prototype, the actor is tracked while a frame-to-prototype correspondence is established by maximizing the joint probability, which is efficiently performed by searching the learned prototype tree; then actions are recognized using dynamic prototype sequence matching. Distance measures used for sequence matching are rapidly obtained by look-up table indexing, which is an order of magnitude faster than brute-force computation of frame-to-frame distances. Our approach enables robust action matching in challenging situations (such as moving cameras, dynamic backgrounds) and allows automatic alignment of action sequences. Experimental results demonstrate that our approach achieves recognition rates of 92.86 percent on a large gesture data set (with dynamic backgrounds), 100 percent on the Weizmann action data set, 95.77 percent on the KTH action data set, 88 percent on the UCF sports data set, and 87.27 percent on the CMU action data set.

One fundamental problem of object tracking is the convergence of estimates to local maxima not corresponding to target objects. To mitigate this problem, constructing a good posterior distribution of the target state is important. In this letter, we propose a robust tracking approach by building a new posterior distribution model from multiple independent estimates of a target state. For each candidate of the target state, we compute a confidence score based on its spatial consistency with other estimates and photometric similarities with target models. Our posterior distribution model reflects tracking uncertainties well and adaptively defines the search region for the next frame. We validate the robustness of our approach on a number of challenging datasets.

In this paper, we propose a novel coupled dictionary training method for single image super-resolution based on patchwise sparse recovery, where the learned couple dictionaries relate the low- and high-resolution image patch spaces via sparse representation. The learning process enforces that the sparse representation of a low-resolution image patch in terms of the low-resolution dictionary can well reconstruct its underlying high-resolution image patch with the dictionary in the highresolution image patch space. We model the learning problem as a bilevel optimization problem, where the optimization includes an 1-norm minimization problem in its constraints. Implicit differentiation is employed to calculate the desired gradient for stochastic gradient descent. We demonstrate that our coupled dictionary learning method can outperform the existing joint dictionary training method both quantitatively and qualitatively. Furthermore, for real applications, we speed up the algorithm approximately 10 times by learning a neural network model for fast sparse inference and selectively processing only those visually salient regions. Extensive experimental comparisons with stateof- the-art super-resolution algorithms validate the effectiveness of our proposed approach.

A label consistent K-SVD (LC-KSVD) algorithm to learn a discriminative dictionary for sparse coding is presented. In addition to using class labels of training data, we also associate label information with each dictionary item (columns of the dictionary matrix) to enforce discriminability in sparse codes during the dictionary learning process. More specifically, we introduce a new label consistent constraint called `discriminative sparse-code error' and combine it with the reconstruction error and the classification error to form a unified objective function. The optimal solution is efficiently obtained using the K-SVD algorithm. Our algorithm learns a single over-complete dictionary and an optimal linear classifier jointly. It yields dictionaries so that feature points with the same class labels have similar sparse codes. Experimental results demonstrate that our algorithm outperforms many recently proposed sparse coding techniques for face and object category recognition under the same learning conditions.

We propose a shape-based, hierarchical part-template matching approach to simultaneous human detection and segmentation combining local part-based and global shape-template-based schemes. The approach relies on the key idea of matching a part-template tree to images hierarchically to detect humans and estimate their poses. For learning a generic human detector, a pose-adaptive feature computation scheme is developed based on a tree matching approach. Instead of traditional concatenation-style image location-based feature encoding, we extract features adaptively in the context of human poses and train a kernel-SVM classifier to separate human/nonhuman patterns. Specifically, the features are collected in the local context of poses by tracing around the estimated shape boundaries. We also introduce an approach to multiple occluded human detection and segmentation based on an iterative occlusion compensation scheme. The output of our learned generic human detector can be used as an initial set of human hypotheses for the iterative optimization. We evaluate our approaches on three public pedestrian data sets (INRIA, MIT-CBCL, and USC-B) and two crowded sequences from Caviar Benchmark and Munich Airport data sets.

Feature misalignment in object detection refers to the phenomenon that features which fire up in some positive detection windows do not fire up in other positive detection windows. Most often it is caused by pose variation and local part deformation. Previous work either totally ignores this issue, or naively performs a local exhaustive search to better position each feature. We propose a learning framework to mitigate this problem, where a boosting algorithm is performed to seed the position of the object part, and a multiple instance boosting algorithm further pursues an aggregated feature for this part, namely multiple instance feature. Unlike most previous boosting based object detectors, where each feature value produces a single classification result, the value of the proposed multiple instance feature is the Noisy-OR integration of a bag of classification results. Our approach is applied to the task of human detection and is tested on two popular benchmarks. The proposed approach brings significant improvement in performance, i.e., smaller number of features used in the cascade and better detection accuracy.

A prototype-based approach is introduced for action recognition. The approach represents an action as a sequence of prototypes for efficient and flexible action matching in long video sequences. During training, first, an action prototype tree is learned in a joint shape and motion space via hierarchical k-means clustering; then a lookup table of prototype-to-prototype distances is generated. During testing, based on a joint likelihood model of the actor location and action prototype, the actor is tracked while a frame-to-prototype correspondence is established by maximizing the joint likelihood, which is efficiently performed by searching the learned prototype tree; then actions are recognized using dynamic prototype sequence matching. Distance matrices used for sequence matching are rapidly obtained by look-up table indexing, which is an order of magnitude faster than brute-force computation of frame-to-frame distances. Our approach enables robust action matching in very challenging situations (such as moving cameras, dynamic backgrounds) and allows automatic alignment of action sequences. Experimental results demonstrate that our approach achieves recognition rates of 91.07% on a large gesture dataset (with dynamic backgrounds), 100% on the Weizmann action dataset and 95.77% on the KTH action dataset.

Local part-based human detectors are capable of handling partial occlusions efficiently and modeling shape articulations flexibly, while global shape template-based human detectors are capable of detecting and segmenting human shapes simultaneously. We describe a Bayesian approach to human detection and segmentation combining local part-based and global template-based schemes. The approach relies on the key ideas of matching a part-template tree to images hierarchically to generate a reliable set of detection hypotheses and optimizing it under a Bayesian MAP framework through global likelihood re-evaluation and fine occlusion analysis. In addition to detection, our approach is able to obtain human shapes and poses simultaneously. We applied the approach to human detection and segmentation in crowded scenes with and without background subtraction. Experimental results show that our approach achieves good performance on images and video sequences with severe occlusion.

An interactive human segmentation approach is described. Given regions of interest provided by users, the approach iteratively estimates segmentation via a generalized EM algorithm. Specifically, it encodes both spatial and color information in a nonparametric kernel density estimator, and incorporates local MRF constraints and global pose inferences to propagate beliefs over image space iteratively to determine a coherent segmentation. This ensures the segmented humans resemble the shapes of human poses. Additionally, a layered occlusion model and a probabilistic occlusion reasoning method are proposed to handle segmentation of multiple humans in occlusion. The approach is tested on a wide variety of images containing single or multiple occluded humans, and the segmentation performance is evaluated quantitatively.

In this paper, we present a recognition-based autonomous navigation system for mobile robots. The system is based on our previously proposed robust invariant feature (RIF) detector. This detector extracts highly robust and repeatable features based on the key idea of tracking multi-scale interest points and selecting unique representative local structures with the strongest response in both spatial and scale domains. Weighted Zernike moments are used as the feature descriptor and applied to the place recognition. The navigation system is composed of on-line and off-line two stages. In the off-line learning stage, we train the robot in its workspace by just taking several images of representative places as landmarks. Then, in the on-line navigation stage, the robot recognizes scenes, obtains robust feature correspondences, and navigates the environment autonomously using the iterative pose converging (IPC) algorithm which is based on the idea of the visual servoing technique. The experimental results and the performance evaluation show that the proposed navigation system can achieve excellent performance in complex indoor environments.