Despite the remarkable developments achieved by recent 3D generation works, scaling these methods to geographic extents, such as modeling thousands of square kilometers of Earth’s surface, remains an open challenge. We address this through a dual innovation in data infrastructure and model architecture. First, we introduce Aerial-Earth3D, the largest 3D aerial dataset to date, consisting of 50k curated scenes (each measuring 600m) captured across the U.S. mainland, comprising 45M multi-view Google Earth frames. Each scene provides pose-annotated multi-view images, depth maps, normals, semantic segmentation, and camera poses, with explicit quality control to ensure terrain diversity. Building on this foundation, we propose EarthCrafter, a tailored framework for large-scale 3D Earth generation via sparse-decoupled latent diffusion. Our architecture separates structural and textural generation: 1) Dual sparse 3D-VAEs compress high-resolution geometric voxels and textural 2D Gaussian Splats (2DGS) into compact latent spaces, largely alleviating the costly computation suffering from vast geographic scales while preserving critical information. 2) We propose condition-aware flow matching models trained on mixed inputs (semantics, images, or neither) to flexibly model latent geometry and texture features independently. Extensive experiments demonstrate that EarthCrafter performs substantially better in extremely large-scale generation. The framework further supports versatile applications, from semantic-guided urban layout generation to unconditional terrain synthesis, while maintaining geographic plausibility through our rich data priors from Aerial-Earth3D.

Despite the remarkable progress of 3D generation, achieving controllability, i.e., ensuring consistency between generated 3D content and input conditions like edge and depth, remains a significant challenge. Existing methods often struggle to maintain accurate alignment, leading to noticeable discrepancies. To address this issue, we propose CyC3D, a new framework that enhances controllable 3D generation by explicitly encouraging cyclic consistency between the second-order 3D content, generated based on extracted signals from the first-order generation, and its original input controls. Specifically, we employ an efficient feed-forward backbone that can generate a 3D object from an input condition and a text prompt. Given an initial viewpoint and a control signal, a novel view is rendered from the generated 3D content, from which the extracted condition is used to regenerate the 3D content. This re-generated output is then rendered back to the initial viewpoint, followed by another round of control signal extraction, forming a cyclic process with two consistency constraints. View consistency ensures coherence between the two generated 3D objects, measured by semantic similarity to accommodate generative diversity. Condition consistency aligns the final extracted signal with the original input control, preserving structural or geometric details throughout the process. Extensive experiments on popular benchmarks demonstrate that CyC3D significantly improves controllability, especially for fine-grained details, outperforming existing methods across various conditions (e.g., +14.17% PSNR for edge, +6.26% PSNR for sketch).

Diffusion Transformer (DiT), an emerging diffusion model for visual generation, has demonstrated superior performance but suffers from substantial computational costs. Our investigations reveal that these costs primarily stem from the static inference paradigm, which inevitably introduces redundant computation in certain diffusion timesteps and spatial regions. To overcome this inefficiency, we propose Dynamic Diffusion Transformer (DyDiT), an architecture that dynamically adjusts its computation along both timestep and spatial dimensions. Specifically, we introduce a Timestep-wise Dynamic Width (TDW) approach that adapts model width conditioned on the generation timesteps. In addition, we design a Spatial-wise Dynamic Token (SDT) strategy to avoid redundant computation at unnecessary spatial locations. TDW and SDT can be seamlessly integrated into DiT and significantly accelerate the generation process. Building on these designs, we present an extended version, DyDiT++, with improvements in three key aspects. First, it extends the generation mechanism of DyDiT beyond diffusion to flow matching, demonstrating that our method can also accelerate flow-matching-based generation, enhancing its versatility. Furthermore, we enhance DyDiT to tackle more complex visual generation tasks, including video generation and text-to-image generation, thereby broadening its real-world applications. Finally, to address the high cost of full fine-tuning and democratize technology access, we investigate the feasibility of training DyDiT in a parameter-efficient manner and introduce timestep-based dynamic LoRA (TD-LoRA). Extensive experiments on diverse visual generation models, including DiT, SiT, Latte, and FLUX, demonstrate the effectiveness of DyDiT++. Remarkably, with $< $<3% additional fine-tuning iterations, our approach reduces the FLOPs of DiT-XL by 51%, yielding 1.73× realistic speedup on hardware, and achieves a competitive FID score of 2.07 on ImageNet.

In recent years, diffusion models have revolutionized visual generation, outperforming traditional frameworks like Generative Adversarial Networks (GANs). However, generating images of humans with realistic semantic parts, such as hands and faces, remains a significant challenge due to their intricate structural complexity. To address this issue, we propose a novel post-processing solution named RealisHuman. The RealisHuman framework operates in two stages. First, it generates realistic human parts, such as hands or faces, using the original malformed parts as references, ensuring consistent details with the original image. Second, it seamlessly integrates the rectified human parts back into their corresponding positions by repainting the surrounding areas to ensure smooth and realistic blending. The RealisHuman framework significantly enhances the realism of human generation, as demonstrated by notable improvements in both qualitative and quantitative metrics.

We introduce MVGenMaster, a multi-view diffusion model enhanced with 3D priors to address versatile Novel View Synthesis (NVS) tasks. MVGenMaster leverages 3D priors that are warped using metric depth and camera poses, significantly enhancing both generalization and 3D consistency in NVS. Our model features a simple yet effective pipeline that can generate up to 100 novel views conditioned on variable reference views and camera poses with a single forward process. Additionally, we have developed a comprehensive large-scale multi-view image dataset called MvD-1M, comprising up to 1.6 million scenes, equipped with well-aligned metric depth to train MVGenMaster. Moreover, we present several training and model modifications to strengthen the model with scaled-up datasets. Extensive evaluations across in- and out- of- domain benchmarks demonstrate the effectiveness of our proposed method and data formulation.

Transparent videos with alpha channels play a crucial role in film production, advertising, and augmented reality fields. However, there is currently no available method for producing transparent videos. Traditional methods are time-consuming and labor-intensive, and employing alternative approaches for this task will result in inaccurate transparent regions, constrained motion, and artifacts. To address these challenges, we propose Layer-Animate, the first method capable of generating transparent videos. Our method comprises two stages: in the first stage, transparent images are generated as the base images to provide content and transparency information for the next stage. In the second stage, Inter-Frame Attention is applied to decouple content from motion, enabling the motion module to focus better on action. Layer-Animate is the first method used to generate transparent videos with accurate transparent regions, sufficient motion, and no artifacts, as demonstrated by notable improvements in qualitative and quantitative metrics.

Recent advances in 4D content generation have attracted increasing attention, yet creating high-quality animated 3D models remains challenging due to the complexity of modeling spatio-temporal distributions and the scarcity of 4D training data. In this paper, we present AnimateAnyMesh, the first feed-forward framework that enables efficient text-driven animation of arbitrary 3D meshes. Our approach leverages a novel DyMeshVAE architecture that effectively compresses and reconstructs dynamic mesh sequences by disentangling spatial and temporal features while preserving local topological structures. To enable high-quality text-conditional generation, we employ a Rectified Flow-based training strategy in the compressed latent space. Additionally, we contribute the DyMesh Dataset, containing over 4M diverse dynamic mesh sequences with text annotations. Experimental results demonstrate that our method generates semantically accurate and temporally coherent mesh animations in a few seconds, significantly outperforming existing approaches in both quality and efficiency. Our work marks a substantial step forward in making 4D content creation more accessible and practical. All the data, code, and models will be open-released.

Diffusion Transformer (DiT), an emerging diffusion model for image generation, has demonstrated superior performance but suffers from substantial computational costs. Our investigations reveal that these costs stem from the static inference paradigm, which inevitably introduces redundant computation in certain diffusion timesteps and spatial regions. To address this inefficiency, we propose Dynamic Diffusion Transformer (DyDiT), an architecture that dynamically adjusts its compu- tation along both timestep and spatial dimensions during generation. Specifically, we introduce a Timestep-wise Dynamic Width (TDW) approach that adapts model width conditioned on the generation timesteps. In addition, we design a Spatial- wise Dynamic Token (SDT) strategy to avoid redundant computation at unnecessary spatial locations. Extensive experiments on various datasets and different-sized models verify the superiority of DyDiT. Notably, with <3% additional fine-tuning it- erations, our method reduces the FLOPs of DiT-XL by 51%, accelerates generation by 1.73×, and achieves a competitive FID score of 2.07 on ImageNet.

Recent advancements in video generation have primarily leveraged diffusion models for short-duration content. However, these approaches often fall short in modeling complex narratives and maintaining character consistency over extended periods, which is essential for long-form video production like movies. We propose MovieDreamer, a novel hierarchical framework that integrates the strengths of autoregressive models with diffusion-based rendering to pioneer long-duration video generation with intricate plot progressions and high visual fidelity. Our approach utilizes autoregressive models for global narrative coherence, predicting sequences of visual tokens that are subsequently transformed into high-quality video frames through diffusion rendering. This method is akin to traditional movie production processes, where complex stories are factorized down into manageable scene capturing. Further, we employ a multimodal script that enriches scene descriptions with detailed character information and visual style, enhancing continuity and character identity across scenes. We present extensive experiments across various movie genres, demonstrating that our approach not only achieves superior visual and narrative quality but also effectively extends the duration of generated content significantly beyond current capabilities.

In this work, we focus on the alignment problem of diffusion models with a continuous reward function, which represents specific objectives for downstream tasks, such as increasing darkness or improving the aesthetics of images. The central goal of the alignment problem is to adjust the distribution learned by diffusion models such that the generated samples maximize the target reward function. We propose a novel alignment approach, named Direct Noise Optimization (DNO), that optimizes the injected noise during the sampling process of diffusion models. By design, DNO operates at inference-time, and thus is tuning-free and prompt-agnostic, with the alignment occurring in an online fashion during generation. We rigorously study the theoretical properties of DNO and also propose variants to deal with non-differentiable reward functions. Furthermore, we identify that naive implementation of DNO occasionally suffers from the out-of-distribution reward hacking problem, where optimized samples have high rewards but are no longer in the support of the pretrained distribution. To remedy this issue, we leverage classical high-dimensional statistics theory to an effective probability regularization technique. We conduct extensive experiments on several important reward functions and demonstrate that the proposed DNO approach can achieve state-of-the-art reward scores within a reasonable time budget for generation.

Video try-on replaces clothing in videos with target garments. Existing methods struggle to generate high-quality and temporally consistent results when handling complex clothing patterns and diverse body poses. We present 3DV-TON, a novel diffusion-based framework for generating high-fidelity and temporally consistent video try-on results. Our approach employs generated animatable textured 3D meshes as explicit frame-level guidance, alleviating the issue of models over-focusing on appearance fidelity at the expanse of motion coherence. This is achieved by enabling direct reference to consistent garment texture movements throughout video sequences. The proposed method features an adaptive pipeline for generating dynamic 3D guidance: (1) selecting a keyframe for initial 2D image try-on, followed by (2) reconstructing and animating a textured 3D mesh synchronized with original video poses. We further introduce a robust rectangular masking strategy that successfully mitigates artifact propagation caused by leaking clothing information during dynamic human and garment movements. To advance video try-on research, we introduce HR-VVT, a high-resolution benchmark dataset containing 130 videos with diverse clothing types and scenarios. Quantitative and qualitative results demonstrate our superior performance over existing methods.

Recent advances in video generation have enabled the synthesis of high-quality and visually realistic clips using diffusion transformer models. However, most existing approaches operate purely in the 2D pixel space and lack explicit mechanisms for modeling 3D structures, often resulting in temporally inconsistent geometries, implausible motions, and structural artifacts. In this work, we introduce geometric regularization losses into video generation by augmenting latent diffusion models with per-frame depth prediction. We adopted depth as the geometric representation because of the great progress in depth prediction and its compatibility with image-based latent encoders. Specifically, to enforce structural consistency over time, we propose a multi-view geometric loss that aligns the predicted depth maps across frames within a shared 3D coordinate system. Our method bridges the gap between appearance generation and 3D structure modeling, leading to improved spatio-temporal coherence, shape consistency, and physical plausibility. Experiments across multiple datasets show that our approach produces significantly more stable and geometrically consistent results than existing baselines.

Diffusion Transformers (DiT) are renowned for their impressive generative performance; however, they are significantly constrained by considerable computational costs due to the quadratic complexity in self-attention and the extensive sampling steps required. While advancements have been made in expediting the sampling process, the underlying architectural inefficiencies within DiT remain underexplored. We introduce SparseDiT, a novel framework that implements token sparsification across spatial and temporal dimensions to enhance computational efficiency while preserving generative quality. Spatially, SparseDiT employs a tri-segment architecture that allocates token density based on feature requirements at each layer: Poolingformer in the bottom layers for efficient global feature extraction, Sparse-Dense Token Modules (SDTM) in the middle layers to balance global context with local detail, and dense tokens in the top layers to refine high-frequency details. Temporally, SparseDiT dynamically modulates token density across denoising stages, progressively increasing token count as finer details emerge in later timesteps. This synergy between SparseDiT’s spatially adaptive architecture and its temporal pruning strategy enables a unified framework that balances efficiency and fidelity throughout the generation process. Our experiments demonstrate SparseDiT’s effectiveness, achieving a 55\% reduction in FLOPs and a 175\% improvement in inference speed on DiT-XL with similar FID score on 512$\times$512 ImageNet, a 56\% reduction in FLOPs across video generation datasets, and a 69\% improvement in inference speed on PixArt-$\alpha$ on text-to-image generation task with a 0.24 FID score decrease. SparseDiT provides a scalable solution for high-quality diffusion-based generation compatible with sampling optimization techniques. Code is available at https://github.com/changsn/SparseDiT.

Current text-to-image (T2I) generation models struggle to align spatial composition with the input text, especially in complex scenes. Even layout-based approaches yield suboptimal spatial control, as their generation process is decoupled from layout planning, making it difficult to refine the layout during synthesis. We present CoT-Diff, a framework that brings step-by-step CoT-style reasoning into T2I generation by tightly integrating Multimodal Large Language Model (MLLM)-driven 3D layout planning with the diffusion process. CoT-Diff enables layout-aware reasoning inline within a single diffusion round: at each denoising step, the MLLM evaluates intermediate predictions, dynamically updates the 3D scene layout, and continuously guides the generation process. The updated layout is converted into semantic conditions and depth maps, which are fused into the diffusion model via a condition-aware attention mechanism, enabling precise spatial control and semantic injection. Experiments on 3D Scene benchmarks show that CoT-Diff significantly improves spatial alignment and compositional fidelity, and outperforms the state-of-the-art method by 34.7% in complex scene spatial accuracy, thereby validating the effectiveness of this entangled generation paradigm.

Relighting is a crucial task with both practical demand and artistic value, and recent diffusion models have shown strong potential by enabling rich and controllable lighting effects. However, as they are typically optimized in semantic latent space, where proximity does not guarantee physical correctness in visual space, they often produce unrealistic results—such as overexposed highlights, misaligned shadows, and incorrect occlusions. We address this with **UniLumos**, a unified relighting framework for both images and videos that brings RGB-space geometry feedback into a flow-matching backbone. By supervising the model with depth and normal maps extracted from its outputs, we explicitly align lighting effects with the scene structure, enhancing physical plausibility. Nevertheless, this feedback requires high-quality outputs for supervision in visual space, making standard multi-step denoising computationally expensive. To mitigate this, we employ path consistency learning, allowing supervision to remain effective even under few-step training regimes. To enable fine-grained relighting control and supervision, we design a structured six-dimensional annotation protocol capturing core illumination attributes. Building upon this, we propose **LumosBench**, a disentangled attribute-level benchmark that evaluates lighting controllability via large vision-language models, enabling automatic and interpretable assessment of relighting precision across individual dimensions. Extensive experiments demonstrate that UniLumos achieves state-of-the-art relighting quality with significantly improved physical consistency, while delivering a 20x speedup for both image and video relighting. Code is available at https://github.com/alibaba-damo-academy/Lumos-Custom.

Diffusion generative models have become the standard for producing high-quality, coherent video content, yet their slow inference speeds and high computational demands hinder practical deployment. Although both quantization and sparsity can independently accelerate inference while maintaining generation quality, naively combining these techniques in existing training-free approaches leads to significant performance degradation, as they fail to achieve proper joint optimization. We introduce FPSAttention, a novel training-aware co-design of FP8 quantization and Sparsity for video generation, with a focus on the 3D bi-directional attention mechanism. Our approach features three key innovations: 1) A unified 3D tile-wise granularity that simultaneously supports both quantization and sparsity. 2) A denoising step-aware strategy that adapts to the noise schedule, addressing the strong correlation between quantization/sparsity errors and denoising steps. 3) A native, hardware-friendly kernel that leverages FlashAttention and is implemented with optimized Hopper architecture features, enabling highly efficient execution. Trained on Wan2.1's 1.3B and 14B models and evaluated on the vBench benchmark, FPSAttention achieves a 7.09$\times$ kernel speedup for attention operations and a 4.96$\times$ end-to-end speedup for video generation compared to the BF16 baseline at 720p resolution—without sacrificing generation quality.

We introduce PlayerOne, the first egocentric realistic world simulator, facilitating immersive and unrestricted exploration within vividly dynamic environments. Given an egocentric scene image from the user, PlayerOne can accurately construct the corresponding world and generate egocentric videos that are strictly aligned with the real-scene human motion of the user captured by an exocentric camera. PlayerOne is trained in a coarse-to-fine pipeline that first performs pretraining on large-scale egocentric text-video pairs for coarse-level egocentric understanding, followed by finetuning on synchronous motion-video data extracted from egocentric-exocentric video datasets with our automatic construction pipeline. Besides, considering the varying importance of different components, we design a part-disentangled motion injection scheme, enabling precise control of part-level movements. In addition, we devise a joint reconstruction framework that progressively models both the 4D scene and video frames, ensuring scene consistency in the long-form video generation. Experimental results demonstrate its great generalization ability in precise control of varying human movements and world-consistent modeling of diverse scenarios. It marks the first endeavor into egocentric real-world simulation and can pave the way for the community to delve into fresh frontiers of world modeling and its diverse applications.

The emergence of multimodal large language models (MLLMs) has driven breakthroughs in egocentric vision applications. These applications necessitate persistent, context-aware understanding of objects, as users interact with tools in dynamic and cluttered environments. However, existing embodied benchmarks primarily focus on static scene exploration, emphasizing object's appearance and spatial attributes while neglecting the assessment of dynamic changes arising from users' interactions.capabilities in object-level spatiotemporal reasoning required for real-world interactions.To address this gap, we introduce EOC-Bench, an innovative benchmark designed to systematically evaluate object-centric embodied cognition in dynamic egocentric scenarios.Specially, EOC-Bench features 3,277 meticulously annotated QA pairs categorized into three temporal categories: Past, Present, and Future, covering 11 fine-grained evaluation dimensions and 3 visual object referencing types.To ensure thorough assessment, we develop a mixed-format human-in-the-loop annotation frameworkBased on EOC-Bench, we conduct comprehensive evaluations of various proprietary, open-source, and object-level MLLMs. EOC-Bench serves as a crucial tool for advancing the embodied object cognitive capabilities of MLLMs, establishing a robust foundation for developing reliable core models for embodied systems.

Camera and human motion controls have been extensively studied for video generation, but existing approaches typically address them separately, suffering from limited data with high-quality annotations for both aspects. To overcome this, we present Uni3C, a unified 3D-enhanced framework for precise control of both camera and human motion in video generation. Uni3C includes two key contributions. First, we propose a plug-and-play control module trained with a frozen video generative backbone, PCDController, which utilizes unprojected point clouds from monocular depth to achieve accurate camera control. By leveraging the strong 3D priors of point clouds and the powerful capacities of video foundational models, PCDController shows impressive generalization, performing well regardless of whether the inference backbone is frozen or fine-tuned. This flexibility enables different modules of Uni3C to be trained in specific domains, i.e., either camera control or human motion control, reducing the dependency on jointly annotated data. Second, we propose a jointly aligned 3D world guidance for the inference phase that seamlessly integrates both scenic point clouds and SMPL-X characters to unify the control signals for camera and human motion, respectively. Extensive experiments confirm that PCDController enjoys strong robustness in driving camera motion for fine-tuned backbones of video generation. Uni3C substantially outperforms competitors in both camera controllability and human motion quality. Additionally, we collect tailored validation sets featuring challenging camera movements and human actions to validate the effectiveness of our method. Codes are released at https://github.com/alibaba-damo-academy/Uni3C.

Recently, camera-controlled video generation has seen rapid development, offering more precise control over video generation. However, existing methods predominantly focus on camera control in perspective projection video generation, while geometrically consistent panoramic video generation remains challenging. This limitation is primarily due to the inherent complexities in panoramic pose representation and spherical projection. To address this issue, we propose CamPVG, the first diffusion-based framework for panoramic video generation guided by precise camera poses. We achieve camera position encoding for panoramic images and cross-view feature aggregation based on spherical projection. Specifically, we propose a panoramic Plücker embedding that encodes camera extrinsic parameters through spherical coordinate transformation. This pose encoder effectively captures panoramic geometry, overcoming the limitations of traditional methods when applied to equirectangular projections. Additionally, we introduce a spherical epipolar module that enforces geometric constraints through adaptive attention masking along epipolar lines. This module enables fine-grained cross-view feature aggregation, substantially enhancing the quality and consistency of generated panoramic videos. Extensive experiments demonstrate that our method generates high-quality panoramic videos consistent with camera trajectories, far surpassing existing methods in panoramic video generation.

Locating 3D objects from a single RGB image via Perspective-n-Point (PnP) is a long-standing problem in computer vision. Driven by end-to-end deep learning, recent studies suggest interpreting PnP as a differentiable layer, allowing for partial learning of 2D-3D point correspondences by backpropagating the gradients of pose loss. Yet, learning the entire correspondences from scratch is highly challenging, particularly for ambiguous pose solutions, where the globally optimal pose is theoretically non-differentiable w.r.t. the points. In this paper, we propose the EPro-PnP, a probabilistic PnP layer for general end-to-end pose estimation, which outputs a distribution of pose with differentiable probability density on the SE(3) manifold. The 2D-3D coordinates and corresponding weights are treated as intermediate variables learned by minimizing the KL divergence between the predicted and target pose distribution. The underlying principle generalizes previous approaches, and resembles the attention mechanism. EPro-PnP can enhance existing correspondence networks, closing the gap between PnP-based method and the task-specific leaders on the LineMOD 6DoF pose estimation benchmark. Furthermore, EPro-PnP helps to explore new possibilities of network design, as we demonstrate a novel deformable correspondence network with the state-of-the-art pose accuracy on the nuScenes 3D object detection benchmark.

Synthesizing 3D content from single image has great potential in many real-world applications. To deal with the inherent ambiguity of single image, existing methods usually leverage pre-trained 2D diffusion models for computational intensive per-instance optimization. Although having been able to create 3D assets in a feed-forward manner, the efficacy of recent advances in 3D foundation models is still limited due to neglecting geometric cues from images. To address this issue, we propose an efficient 3D foundation model named LPM to synthesize 3D content from an image. Like the masked modeling in the 2D image domain, the key of our approach is to learn 3D representations from incomplete visible shapes. By taking advantage of a synthesis-by-analysis paradigm, we establish an efficient pipeline to first estimate the visible portions and then generate the complete 3D representations. Based on the principle that an image is the projection of 3D model, we initially estimate partial 3D voxel features from single image, which are further projected onto orthogonal planes to form an incomplete yet efficient triplane representation. Subsequently, an autoencoder is employed to model a complete triplane representation based on the incomplete parts. We train our model on massive data with over 250 million parameters to enhance its generalization capability. The experimental results show that LPM can generate high-fidelity 3D objects from an image within 0.1 seconds, which is more effective than the existing feed-forward approaches. Our implementation and pre-trained models will be made publicly available.

Deep learning-based semantic segmentation has been the dominant solution to quickly capture regions of interest (ROIs) in remote sensing images. However, the annotation and training cost of a fully-supervised segmentation model is often too high due to the requirement for elaborate masks. Additionally, trained models are limited to recognize only those classes defined in the training set. This has led to increased interest in how to cheaply adapt learned knowledge to new unseen objects. In this paper, we propose a meta-learning-based few-shot method called Learnable Prototype Few-Shot Segmentation (LPFS) to quickly adapt models to previously unseen geographic categories with only a few support examples of remote sensing images. Specifically, we first build a learnable prototype module based on variational auto-encoder (VAE) to eliminate inter-class ambiguity and extract high-level semantic prototypes from the support set effectively. We then design a global-attention correlation map to achieve low-level structural feature alignment between the support and query images. Additionally, we introduce a base learner to alleviate the bias caused by the meta-learning network on base classes. The extensive experiments on the public few-shot segmentation benchmark iSAID-5idemonstrate that our method sets a new strong baseline for few-shot semantic segmentation on remote sensing images.

As a compression method that can significantly reduce the cost of calculations and memories, model binarization has been extensively studied in convolutional neural networks. However, the recently popular vision transformer models pose new challenges to such a technique, in which the binarized models suffer from serious performance drops. In this paper, an attention shifting is observed in the binary multi-head self-attention module, which can influence the information fusion between tokens and thus hurts the model performance. From the perspective of information theory, we find a correlation between attention scores and the information quantity, further indicating that a reason for such a phenomenon may be the loss of the information quantity induced by constant moduli of binarized tokens. Finally, we reveal the information quantity hidden in the attention maps of binary vision transformers and propose a simple approach to modify the attention values with look-up information tables so that improve the model performance. Extensive experiments on CIFAR-100/TinyImageNet/ImageNet-1k demonstrate the effectiveness of the proposed information-modified attention on binary vision transformers.

Cross-lingual cross-modal retrieval has garnered increasing attention recently, which aims to achieve the alignment between vision and target language (V-T) without using any annotated V-T data pairs. Current methods employ machine translation (MT) to construct pseudo-parallel data pairs, which are then used to learn a multi-lingual and multi-modal embedding space that aligns visual and target-language representations. However, the large heterogeneous gap between vision and text, along with the noise present in target language translations, poses significant challenges in effectively aligning their representations. To address these challenges, we propose a general framework, Cross-Lingual to Cross-Modal (CL2CM), which improves the alignment between vision and target language using cross-lingual transfer. This approach allows us to fully leverage the merits of multi-lingual pre-trained models (e.g., mBERT) and the benefits of the same modality structure, i.e., smaller gap, to provide reliable and comprehensive semantic correspondence (knowledge) for the cross-modal network. We evaluate our proposed approach on two multilingual image-text datasets, Multi30K and MSCOCO, and one video-text dataset, VATEX. The results clearly demonstrate the effectiveness of our proposed method and its high potential for large-scale retrieval.

Numerous self-supervised learning paradigms, such as contrastive learning and masked image modeling, have been proposed to acquire powerful and general representations from unlabeled data. However, these models are commonly pretrained within their specific framework alone, failing to consider the complementary nature of visual representations. To tackle this issue, we introduce Comprehensive Distillation with Multiple Self-supervised Teachers (DMT) for pretrained model compression, which leverages the strengths of multiple off-the-shelf self-supervised models. Our experimental results on prominent benchmark datasets exhibit that the proposed method significantly surpasses state-of-the-art competitors while retaining favorable efficiency metrics. On classification tasks, our DMT framework utilizing three different self-supervised ViT-Base teachers enhances the performance of both small/tiny models and the base model itself. For dense tasks, DMT elevates the AP/mIoU of standard SSL models on MS-COCO and ADE20K datasets by 4.0%.

Few-shot learning is a promising way for reducing the label cost in new categories adaptation with the guidance of a small, well labeled support set. But for few-shot semantic segmentation, the pixel-level annotations of support images are still expensive. In this paper, we propose an innovative solution to tackle the challenge of few-shot semantic segmentation using only language information, i.e.image-level text labels. Our approach involves a vision-language-driven mask distillation scheme, which contains a vision-language pretraining (VLP) model and a mask refiner, to generate high quality pseudo-semantic masks from text prompts. We additionally introduce a distributed prototype supervision method and complementary correlation matching module to guide the model in digging precise semantic relations among support and query images. The experiments on two benchmark datasets demonstrate that our method establishes a new baseline for language-guided few-shot semantic segmentation and achieves competitive results to recent vision-guided methods.

Image outpainting aims to generate the content of an input sub-image beyond its original boundaries. It is an important task in content generation yet remains an open problem for generative models. This paper pushes the technical frontier of image outpainting in two directions that have not been resolved in literature: 1) outpainting with arbitrary and continuous multiples (without restriction), and 2) outpainting in a single step (even for large expansion multiples). Moreover, we develop a method that does not depend on a pre-trained backbone network, which is in contrast commonly required by the previous SOTA outpainting methods. The arbitrary multiple outpainting is achieved by utilizing randomly cropped views from the same image during training to capture arbitrary relative positional information. Specifically, by feeding one view and positional embeddings as queries, we can reconstruct another view. At inference, we generate images with arbitrary expansion multiples by inputting an anchor image and its corresponding positional embeddings. The one-step outpainting ability here is particularly noteworthy in contrast to previous methods that need to be performed for $N$ times to obtain a final multiple which is $N$ times of its basic and fixed multiple. We evaluate the proposed approach (called PQDiff as we adopt a diffusion-based generator as our embodiment, under our proposed \textbf{P}ositional \textbf{Q}uery scheme) on public benchmarks, demonstrating its superior performance over state-of-the-art approaches. Specifically, PQDiff achieves state-of-the-art FID scores on the Scenery (\textbf{21.512}), Building Facades (\textbf{25.310}), and WikiArts (\textbf{36.212}) datasets. Furthermore, under the 2.25x, 5x and 11.7x outpainting settings, PQDiff only takes \textbf{40.6\%}, \textbf{20.3\%} and \textbf{10.2\%} of the time of the benchmark state-of-the-art (SOTA) method.

Diffusion models have emerged as state-of-the-art generative models for image generation. However, sampling from diffusion models is usually time-consuming due to the inherent autoregressive nature of their sampling process. In this work, we propose a novel approach that accelerates the sampling of diffusion models by parallelizing the autoregressive process. Specifically, we reformulate the sampling process as solving a system of triangular nonlinear equations through fixed-point iteration. With this innovative formulation, we explore several systematic techniques to further reduce the iteration steps required by the solving process. Applying these techniques, we introduce ParaTAA, a universal and training-free parallel sampling algorithm that can leverage extra computational and memory resources to increase the sampling speed. Our experiments demonstrate that ParaTAA can decrease the inference steps required by common sequential sampling algorithms such as DDIM and DDPM by a factor of 4$\sim$14 times. Notably, when applying ParaTAA with 100 steps DDIM for Stable Diffusion, a widely-used text-to-image diffusion model, it can produce the same images as the sequential sampling in only 7 inference steps. The code is available at https://github.com/TZW1998/ParaTAA-Diffusion.

Unsupervised Contrastive learning has gained prominence in fields such as vision, and biology, leveraging predefined positive/negative samples for representation learning. Data augmentation, categorized into hand-designed and model-based methods, has been identified as a crucial component for enhancing contrastive learning. However, hand-designed methods require human expertise in domain-specific data while sometimes distorting the meaning of the data. In contrast, generative model-based approaches usually require supervised or large-scale external data, which has become a bottleneck constraining model training in many domains. To address the problems presented above, this paper proposes DiffAug, a novel unsupervised contrastive learning technique with diffusion mode-based positive data generation. DiffAug consists of a semantic encoder and a conditional diffusion model; the conditional diffusion model generates new positive samples conditioned on the semantic encoding to serve the training of unsupervised contrast learning. With the help of iterative training of the semantic encoder and diffusion model, DiffAug improves the representation ability in an uninterrupted and unsupervised manner. Experimental evaluations show that DiffAug outperforms hand-designed and SOTA model-based augmentation methods on DNA sequence, visual, and bio-feature datasets. The code for review is released at DiffAug CODE.

Camouflaged instance segmentation is a challenging task due to the various aspects such as color, structure, lighting, etc., of object instances embedded in complex backgrounds. Although the current DETR-based scheme simplifies the pipeline, it suffers from a large number of object queries, leading to many false positive instances. To address this issue, we propose an adaptive query selection mechanism. Our research reveals that a large number of redundant queries scatter the extracted features of the camouflaged instances. To remove these redundant queries with weak correlation, we evaluate the importance of the object query from the perspectives of information entropy and volatility. Moreover, we observed that occlusion and overlapping instances significantly impact the accuracy of the selection mechanism. Therefore, we design a boundary location embedding mechanism that incorporates fake instance boundaries to obtain better location information for more accurate query instance matching. We conducted extensive experiments on two challenging camouflaged instance segmentation datasets, namely COD10K and NC4K, and demonstrated the effectiveness of our proposed model. Compared with the OSFormer, our model significantly improves the performance by 3.8% AP and 5.6% AP with less computational cost, achieving the state-of-the-art of 44.8 AP and 48.1 AP with ResNet-50 on the COD10K and NC4K test-dev sets, respectively.

Novel View Synthesis (NVS) and 3D generation have recently achieved prominent improvements. However, these works mainly focus on confined categories or synthetic 3D assets, which are discouraged from generalizing to challenging in-the-wild scenes and fail to be employed with 2D synthesis directly. Moreover, these methods heavily depended on camera poses, limiting their real-world applications. To overcome these issues, we propose MVInpainter, re-formulating the 3D editing as a multi-view 2D inpainting task. Specifically, MVInpainter partially inpaints multi-view images with the reference guidance rather than intractably generating an entirely novel view from scratch, which largely simplifies the difficulty of in-the-wild NVS and leverages unmasked clues instead of explicit pose conditions. To ensure cross-view consistency, MVInpainter is enhanced by video priors from motion components and appearance guidance from concatenated reference key\&value attention. Furthermore, MVInpainter incorporates slot attention to aggregate high-level optical flow features from unmasked regions to control the camera movement with pose-free training and inference. Sufficient scene-level experiments on both object-centric and forward-facing datasets verify the effectiveness of MVInpainter, including diverse tasks, such as multi-view object removal, synthesis, insertion, and replacement. The project page is https://ewrfcas.github.io/MVInpainter/.

Recent advances in 4D generation mainly focus on generating 4D content by distilling pre-trained text or single-view image conditioned models. It is inconvenient for them to take advantage of various off-the-shelf 3D assets with multi-view attributes, and their results suffer from spatiotemporal inconsistency owing to the inherent ambiguity in the supervision signals. In this work, we present Animate3D, a novel framework for animating any static 3D model. The core idea is two-fold: 1) We propose a novel multi-view video diffusion model (MV-VDM) conditioned on multi-view renderings of the static 3D object, which is trained on our presented large-scale multi-view video dataset (MV-Video). 2) Based on MV-VDM, we introduce a framework combining reconstruction and 4D Score Distillation Sampling (4D-SDS) to leverage the multi-view video diffusion priors for animating 3D objects. Specifically, for MV-VDM, we design a new spatiotemporal attention module to enhance spatial and temporal consistency by integrating 3D and video diffusion models. Additionally, we leverage the static 3D model’s multi-view renderings as conditions to preserve its identity. For animating 3D models, an effective two-stage pipeline is proposed: we first reconstruct coarse motions directly from generated multi-view videos, followed by the introduced 4D-SDS to model fine-level motions. Benefiting from accurate motion learning, we could achieve straightforward mesh animation. Qualitative and quantitative experiments demonstrate that Animate3D significantly outperforms previous approaches. Data, code, and models are open-released.

Existing parameter-efficient fine-tuning (PEFT) methods have achieved significant success on vision transformers (ViTs) adaptation by improving parameter efficiency. However, the exploration of enhancing inference efficiency during adaptation remains underexplored. This limits the broader application of pre-trained ViT models, especially when the model is computationally extensive. In this paper, we propose Dynamic Tuning (DyT), a novel approach to improve both parameter and inference efficiency for ViT adaptation. Specifically, besides using the lightweight adapter modules, we propose a token dispatcher to distinguish informative tokens from less important ones, allowing the latter to dynamically skip the original block, thereby reducing the redundant computation during inference. Additionally, we explore multiple design variants to find the best practice of DyT. Finally, inspired by the mixture-of-experts (MoE) mechanism, we introduce an enhanced adapter to further boost the adaptation performance. We validate DyT across various tasks, including image/video recognition and semantic segmentation. For instance, DyT achieves superior performance compared to existing PEFT methods while evoking only 71% of their FLOPs on the VTAB-1K benchmark.

Vision transformers (ViT) usually extract features via forwarding all the tokens in the self-attention layers from top to toe. In this paper, we introduce dynamic token-pass vision transformers (DoViT) for semantic segmentation, which can adaptively reduce the inference cost for images with different complexity. DoViT gradually stops partial easy tokens from self-attention calculation and keeps the hard tokens forwarding until meeting the stopping criteria. We employ lightweight auxiliary heads to make the token-pass decision and divide the tokens into keeping/stopping parts. With a token separate calculation, the self-attention layers are speeded up with sparse tokens and still work friendly with hardware. A token reconstruction module is built to collect and reset the grouped tokens to their original position in the sequence, which is necessary to predict correct semantic masks. We conduct extensive experiments on two common semantic segmentation tasks, and demonstrate that our method greatly reduces about 40% ∼ 60% FLOPs and the drop of mIoU is within 0.8% for various segmentation transformers. The throughput and inference speed of ViT-L/B are increased to more than 2× on Cityscapes. Code is available at https://github.com/FLHonker/DoViT-code.

Person Re-identification (ReID) plays a more and more crucial role in recent years with a wide range of applications. Existing ReID methods are suffering from the challenges of misalignment and occlusions, which degrade the performance dramatically. Most methods tackle such challenges by utilizing external tools to locate body parts or exploiting matching strategies. Nevertheless, the inevitable domain gap between the datasets utilized for external tools and the ReID datasets and the complicated matching process make these methods unreliable and sensitive to noises. In this paper, we propose a Region Generation and Assessment Network (RGANet) to effectively and efficiently detect the human body regions and highlight the important regions. In the proposed RGANet, we first devise a Region Generation Module (RGM) which utilizes the pre-trained CLIP to locate the human body regions using semantic prototypes extracted from text descriptions. Learnable prompt is designed to eliminate domain gap between CLIP datasets and ReID datasets. Then, to measure the importance of each generated region, we introduce a Region Assessment Module (RAM) that assigns confidence scores to different regions and reduces the negative impact of the occlusion regions by lower scores. The RAM consists of a discrimination-aware indicator and an invariance-aware indicator, where the former indicates the capability to distinguish from different identities and the latter represents consistency among the images of the same class of human body regions. Extensive experimental results for six widely-used benchmarks including three tasks (occluded, partial, and holistic) demonstrate the superiority of RGANet against state-of-the-art methods.

Current research on cross-modal retrieval is mostly English-oriented, as the availability of a large number of English-oriented human-labeled vision-language corpora. In order to break the limit of non-English labeled data, cross-lingual cross-modal retrieval (CCR) has attracted increasing attention. Most CCR methods construct pseudo-parallel vision-language corpora via Machine Translation (MT) to achieve cross-lingual transfer. However, the translated sentences from MT are generally imperfect in describing the corresponding visual contents. Improperly assuming the pseudo-parallel data are correctly correlated will make the networks overfit to the noisy correspondence. Therefore, we propose Dual-view Curricular Optimal Transport (DCOT) to learn with noisy correspondence in CCR. In particular, we quantify the confidence of the sample pair correlation with optimal transport theory from both the cross-lingual and cross-modal views, and design dual-view curriculum learning to dynamically model the transportation costs according to the learning stage of the two views. Extensive experiments are conducted on two multilingual image-text datasets and one video-text dataset, and the results demonstrate the effectiveness and robustness of the proposed method. Besides, our proposed method also shows a good expansibility to cross-lingual image-text baselines and a decent generalization on out-of-domain data.

Visual retrieval tasks such as image retrieval and person re-identification (Re-ID) aim at effectively and thoroughly searching images with similar content or the same identity. After obtaining retrieved examples, re-ranking is a widely adopted post-processing step to reorder and improve the initial retrieval results by making use of the contextual information from semantically neighboring samples. Prevailing re-ranking approaches update distance metrics and mostly rely on inefficient crosscheck set comparison operations while computing expanded neighbors based distances. In this work, we present an efficient re-ranking method which refines initial retrieval results by updating features. Specifically, we reformulate re-ranking based on Graph Convolution Networks (GCN) and propose a novel Graph Convolution based Re-ranking (GCR) for visual retrieval tasks via feature propagation. To accelerate computation for large-scale retrieval, a decentralized and synchronous feature propagation algorithm which supports parallel or distributed computing is introduced. In particular, the plain GCR is extended for cross-camera retrieval and an improved feature propagation formulation is presented to leverage affinity relationships across different cameras. It is also extended for video-based retrieval, and Graph Convolution based Re-ranking for Video (GCRV) is proposed by mathematically deriving a novel profile vector generation method for the tracklet. Without bells and whistles, the proposed approaches achieve state-of-the-art performances on seven benchmark datasets from three different tasks, i.e., image retrieval, person Re-ID and video-based person Re-ID.

Data-driven medium-range weather forecasting has attracted much attention in recent years. However, the forecasting accuracy at high resolution is unsatisfactory currently. Pursuing high-resolution and high-quality weather forecasting, we develop a data-driven model SwinRDM which integrates an improved version of SwinRNN with a diffusion model. SwinRDM performs predictions at 0.25-degree resolution and achieves superior forecasting accuracy to IFS (Integrated Forecast System), the state-of-the-art operational NWP model, on representative atmospheric variables including 500 hPa geopotential (Z500), 850 hPa temperature (T850), 2-m temperature (T2M), and total precipitation (TP), at lead times of up to 5 days. We propose to leverage a two-step strategy to achieve high-resolution predictions at 0.25-degree considering the trade-off between computation memory and forecasting accuracy. Recurrent predictions for future atmospheric fields are firstly performed at 1.40625-degree resolution, and then a diffusion-based super-resolution model is leveraged to recover the high spatial resolution and finer-scale atmospheric details. SwinRDM pushes forward the performance and potential of data-driven models for a large margin towards operational applications.

Existing semantic segmentation works have been mainly focused on designing effective decoders; however, the computational load introduced by the overall structure has long been ignored, which hinders their applications on resource-constrained hardwares. In this paper, we propose a head-free lightweight architecture specifically for semantic segmentation, named Adaptive Frequency Transformer (AFFormer). AFFormer adopts a parallel architecture to leverage prototype representations as specific learnable local descriptions which replaces the decoder and preserves the rich image semantics on high-resolution features. Although removing the decoder compresses most of the computation, the accuracy of the parallel structure is still limited by low computational resources. Therefore, we employ heterogeneous operators (CNN and vision Transformer) for pixel embedding and prototype representations to further save computational costs. Moreover, it is very difficult to linearize the complexity of the vision Transformer from the perspective of spatial domain. Due to the fact that semantic segmentation is very sensitive to frequency information, we construct a lightweight prototype learning block with adaptive frequency filter of complexity O(n) to replace standard self attention with O(n^2). Extensive experiments on widely adopted datasets demonstrate that AFFormer achieves superior accuracy while retaining only 3M parameters. On the ADE20K dataset, AFFormer achieves 41.8 mIoU and 4.6 GFLOPs, which is 4.4 mIoU higher than Segformer, with 45% less GFLOPs. On the Cityscapes dataset, AFFormer achieves 78.7 mIoU and 34.4 GFLOPs, which is 2.5 mIoU higher than Segformer with 72.5% less GFLOPs. Code is available at https://github.com/dongbo811/AFFormer.

Arbitrary neural style transfer has been a popular research topic due to its rich application scenarios. Effective disentanglement of content and style is the critical factor for synthesizing an image with arbitrary style. The existing methods focus on disentangling feature representations of content and style in the spatial domain where the content and style components are innately entangled and difficult to be disentangled clearly. Therefore, these methods always suffer from low-quality results because of the sub-optimal disentanglement. To address such a challenge, this paper proposes the frequency mixer (FreMixer) module that disentangles and re-entangles the frequency spectrum of content and style components in the frequency domain. Since content and style components have different frequency-domain characteristics (frequency bands and frequency patterns), the FreMixer could well disentangle these two components. Based on the FreMixer module, we design a novel Frequency Domain Disentanglement (FDD) framework for arbitrary neural style transfer. Qualitative and quantitative experiments verify that the proposed method can render better stylized results compared to the state-of-the-art methods.

The quadratic computational complexity to the number of tokens limits the practical applications of Vision Transformers (ViTs). Several works propose to prune redundant tokens to achieve efficient ViTs. However, these methods generally suffer from (i) dramatic accuracy drops, (ii) application difficulty in the local vision transformer, and (iii) non-general-purpose networks for downstream tasks. In this work, we propose a novel Semantic Token ViT (STViT), for efficient global and local vision transformers, which can also be revised to serve as backbone for downstream tasks. The semantic tokens represent cluster centers, and they are initialized by pooling image tokens in space and recovered by attention, which can adaptively represent global or local semantic information. Due to the cluster properties, a few semantic tokens can attain the same effect as vast image tokens, for both global and local vision transformers. For instance, only 16 semantic tokens on DeiT-(Tiny,Small,Base) can achieve the same accuracy with more than 100% inference speed improvement and nearly 60% FLOPs reduction; on Swin-(Tiny,Small,Base), we can employ 16 semantic tokens in each window to further speed it up by around 20% with slight accuracy increase. Besides great success in image classification, we also extend our method to video recognition. In addition, we design a STViT-R(ecovery) network to restore the detailed spatial information based on the STViT, making it work for downstream tasks, which is powerless for previous token sparsification methods. Experiments demonstrate that our method can achieve competitive results compared to the original networks in object detection and instance segmentation, with over 30% FLOPs reduction for backbone.

Human-centric visual tasks have attracted increasing research attention due to their widespread applications. In this paper, we aim to learn a general human representation from massive unlabeled human images which can benefit downstream human-centric tasks to the maximum extent. We call this method SOLIDER, a Semantic cOntrollable seLf-supervIseD lEaRning framework. Unlike the existing self-supervised learning methods, prior knowledge from human images is utilized in SOLIDER to build pseudo semantic labels and import more semantic information into the learned representation. Meanwhile, we note that different downstream tasks always require different ratios of semantic information and appearance information. For example, human parsing requires more semantic information, while person re-identification needs more appearance information for identification purpose. So a single learned representation cannot fit for all requirements. To solve this problem, SOLIDER introduces a conditional network with a semantic controller. After the model is trained, users can send values to the controller to produce representations with different ratios of semantic information, which can fit different needs of downstream tasks. Finally, SOLIDER is verified on six downstream human-centric visual tasks. It outperforms state of the arts and builds new baselines for these tasks. The code is released in https://github.com/tinyvision/SOLIDER.

The goal of click-based interactive image segmentation is to extract target masks with the input of positive/negative clicks. Every time a new click is placed, existing methods run the whole segmentation network to obtain a corrected mask, which is inefficient since several clicks may be needed to reach satisfactory accuracy. To this end, we propose an efficient method to correct the mask with a lightweight mask correction network. The whole network remains a low computational cost from the second click, even if we have a large backbone. However, a simple correction network with limited capacity is not likely to achieve comparable performance with a classic segmentation network. Thus, we propose a click-guided self-attention module and a click-guided correlation module to effectively exploits the click information to boost performance. First, several tem-plates are selected based on the semantic similarity with click features. Then the self-attention module propagates the template information to other pixels, while the correlation module directly uses the templates to obtain target out-lines. With the efficient architecture and two click-guided modules, our method shows preferable performance and efficiency compared to existing methods. The code will be released at https://github.com/feiaxyt/EMC-Click.

Modern incremental learning for semantic segmentation methods usually learn new categories based on dense annotations. Although achieve promising results, pixel-by-pixel labeling is costly and time-consuming. Weakly incremental learning for semantic segmentation (WILSS) is a novel and attractive task, which aims at learning to segment new classes from cheap and widely available image-level labels. Despite the comparable results, the image-level labels can not provide details to locate each segment, which limits the performance of WILSS. This inspires us to think how to improve and effectively utilize the supervision of new classes given image-level labels while avoiding forgetting old ones. In this work, we propose a novel and data-efficient frame-work for WILSS, named FMWISS. Specifically, we propose pre-training based co-segmentation to distill the knowledge of complementary foundation models for generating dense pseudo labels. We further optimize the noisy pseudo masks with a teacher-student architecture, where a plug-in teacher is optimized with a proposed dense contrastive loss. Moreover, we introduce memory-based copy-paste augmentation to improve the catastrophic forgetting problem of old classes. Extensive experiments on Pascal VOC and COCO datasets demonstrate the superior performance of our framework, e.g., FMWISS achieves 70.7% and 73.3% in the 15–5 VOC setting, outperforming the state-of-the-art method by 3.4% and 6.1%, respectively.

Despite the promising results, existing oriented object detection methods usually involve heuristically designed rules, e.g., RRoI generation, rotated NMS. In this paper, we propose an end-to-end framework for oriented object detection, which simplifies the model pipeline and obtains superior performance. Our framework is based on DETR, with the box regression head replaced with a points prediction head. The learning of points is more flexible, and the distribution of points can reflect the angle and size of the target rotated box. We further propose to decouple the query features into classification and regression features, which significantly improves the model precision. Aerial images usually contain thousands of instances. To better balance model precision and efficiency, we propose a novel dynamic query design, which reduces the number of object queries in stacked decoder layers without sacrificing model performance. Finally, we rethink the label assignment strategy of existing DETR-like detectors and propose an effective label re-assignment strategy for improved performance. We name our method D2Q-DETR. Experiments on the largest and challenging DOTA-v1.0 and DOTA-v1.5 datasets show that D2Q-DETR outperforms existing NMS-based and NMS-free oriented object detection methods and achieves the new state-of-the-art.

Vision Transformers (ViTs) are normally regarded as a stack of transformer layers. In this work, we propose a novel view of ViTs showing that they can be seen as ensemble networks containing multiple parallel paths with different lengths. Specifically, we equivalently transform the traditional cascade of multi-head self-attention (MSA) and feed-forward network (FFN) into three parallel paths in each transformer layer. Then, we utilize the identity connection in our new transformer form and further transform the ViT into an explicit multi-path ensemble network. From the new perspective, these paths perform two functions: the first is to provide the feature for the classifier directly, and the second is to provide the lower-level feature representation for subsequent longer paths. We investigate the influence of each path for the final prediction and discover that some paths even pull down the performance. Therefore, we propose the path pruning and EnsembleScale skills for improvement, which cut out the underperforming paths and reweight the ensemble components, respectively, to optimize the path combination and make the short paths focus on providing high-quality representation for subsequent paths. We also demonstrate that our path combination strategies can help ViTs go deeper and act as high-pass filters to filter out partial low-frequency signals. To further enhance the representation of paths served for subsequent paths, self-distillation is applied to transfer knowledge from the long paths to the short paths. This work calls for more future research to explain and design ViTs from new perspectives.

Dense contrastive learning (DCL) has been recently explored for learning localized information for dense prediction tasks (e.g., detection and segmentation). It still suffers the difficulty of mining pixels/patches correspondence between two views. A simple way is inputting the same view twice and aligning the pixel/patch representation. However, it would reduce the variance of inputs, and hurts the performance. We propose a plug-in method PQCL (Positional Query for patch-level Contrastive Learning), which allows performing patch-level contrasts between two views with exact patch correspondence. Besides, by using positional queries, PQCL increases the variance of inputs, to enhance training. We apply PQCL to popular transformer-based CL frameworks (DINO and iBOT, and evaluate them on classification, detection and segmentation tasks, where our method obtains stable improvements, especially for dense tasks. It achieves new state-of-the-art in most settings. Code is available at https://github.com/Sherrylone/Query_Contrastive.

Vision Transformers have shown great potential in computer vision tasks. Most recent works have focused on elaborating the spatial token mixer for performance gains. However, we observe that a well-designed general architecture can significantly improve the performance of the entire backbone, regardless of which spatial token mixer is equipped. In this paper, we propose UniNeXt, an improved general architecture for the vision backbone. To verify its effectiveness, we instantiate the spatial token mixer with various typical and modern designs, including both convolution and attention modules. Compared with the architecture in which they are first proposed, our UniNeXt architecture can steadily boost the performance of all the spatial token mixers, and narrows the performance gap among them. Surprisingly, our UniNeXt equipped with naive local window attention even outperforms the previous state-of-the-art. Interestingly, the ranking of these spatial token mixers also changes under our UniNeXt, suggesting that an excellent spatial token mixer may be stifled due to a suboptimal general architecture, which further shows the importance of the study on the general architecture of vision backbone. Code is available at UniNeXt.

Text-to-3D generation has recently garnered significant attention, fueled by 2D diffusion models trained on billions of image-text pairs. Existing methods primarily rely on score distillation to leverage the 2D diffusion priors to supervise the generation of 3D models, e.g., NeRF. However, score distillation is prone to suffer the view inconsistency problem, and implicit NeRF modeling can also lead to an arbitrary shape, thus leading to less realistic and uncontrollable 3D generation. In this work, we propose a flexible framework of Points-to-3D to bridge the gap between sparse yet freely available 3D points and realistic shape-controllable 3D generation by distilling the knowledge from both 2D and 3D diffusion models. The core idea of Points-to-3D is to introduce controllable sparse 3D points to guide the text-to-3D generation. Specifically, we use the sparse point cloud generated from the 3D diffusion model, Point-E, as the geometric prior, conditioned on a single reference image. To better utilize the sparse 3D points, we propose an efficient point cloud guidance loss to adaptively drive the NeRF's geometry to align with the shape of the sparse 3D points. In addition to controlling the geometry, we propose to optimize the NeRF for a more view-consistent appearance. To be specific, we perform score distillation to the publicly available 2D image diffusion model ControlNet, conditioned on text as well as depth map of the learned compact geometry. Qualitative and quantitative comparisons demonstrate that Points-to-3D improves view consistency and achieves good shape controllability for text-to-3D generation. Points-to-3D provides users with a new way to improve and control text-to-3D generation.

In this paper, we propose a novel data-pruning approach called moving-one-sample-out (MoSo), which aims to identify and remove the least informative samples from the training set. The core insight behind MoSo is to determine the importance of each sample by assessing its impact on the optimal empirical risk. This is achieved by measuring the extent to which the empirical risk changes when a particular sample is excluded from the training set. Instead of using the computationally expensive leaving-one-out-retraining procedure, we propose an efficient first-order approximator that only requires gradient information from different training stages. The key idea behind our approximation is that samples with gradients that are consistently aligned with the average gradient of the training set are more informative and should receive higher scores, which could be intuitively understood as follows: if the gradient from a specific sample is consistent with the average gradient vector, it implies that optimizing the network using the sample will yield a similar effect on all remaining samples. Experimental results demonstrate that MoSo effectively mitigates severe performance degradation at high pruning ratios and achieves satisfactory performance across various settings. Experimental results demonstrate that MoSo effectively mitigates severe performance degradation at high pruning ratios and outperforms state-of-the-art methods by a large margin across various settings.

Motion recognition is a promising direction in computer vision, but the training of video classification models is much harder than images due to insufficient data and considerable parameters. To get around this, some works strive to explore multimodal cues from RGB-D data. Although improving motion recognition to some extent, these methods still face sub-optimal situations in the following aspects: (i) Data augmentation, i.e., the scale of the RGB-D datasets is still limited, and few efforts have been made to explore novel data augmentation strategies for videos; (ii) Optimization mechanism, i.e., the tightly space-time-entangled network structure brings more challenges to spatiotemporal information modeling; And (iii) cross-modal knowledge fusion, i.e., the high similarity between multimodal representations leads to insufficient late fusion. To alleviate these drawbacks, we propose to improve RGB-D-based motion recognition both from data and algorithm perspectives in this article. In more detail, firstly, we introduce a novel video data augmentation method dubbed ShuffleMix, which acts as a supplement to MixUp, to provide additional temporal regularization for motion recognition. Secondly, a Unified Multimodal De-coupling and multi-stage Re-coupling framework, termed UMDR, is proposed for video representation learning. Finally, a novel cross-modal Complement Feature Catcher (CFCer) is explored to mine potential commonalities features in multimodal information as the auxiliary fusion stream, to improve the late fusion results. The seamless combination of these novel designs forms a robust spatiotemporal representation and achieves better performance than state-of-the-art methods on four public motion datasets. Specifically, UMDR achieves unprecedented improvements of ↑ 4.5% on the Chalearn IsoGD dataset.

With the advancement of geo-systems and the increased availability of satellite data, a plethora of Land-Use and Land-Cover (LULC) products have been developed. The existing LULC products primarily relied on time-series imagery to classify land by pixel-based classifiers, allowing for local analysis and accurate boundary detection. However, the advent of deep learning has shifted towards the use of patch-based CNN models for generating land cover maps. In this paper, (1) we create a training dataset for China using a voting strategy based on three off-the-shelf available LULC products, avoiding the labor-intensive manual annotation. (2) We design a novel CNN-based model for LULC task, called Multi-modal Fine-grained Dual Network (dubbed as Dual-Net), which takes dual-date images to generate final maps, and reduces the need for gap-free temporal sequences or separate cloud detection. To leverage the correlation between location, date, and category, we embed multi-modal information (dates and geo-locations) to the model. Further, by incorporating low-level constraints and using pseudo-label refinement, we continually improve the performance and achieve more refined segmentation. (3) Due to the lack of a suitable validation dataset for China, we create a new validation dataset called China Sentinel2 Validation Dataset (CSVD) by manually annotating 733 finely labeled images of 1024 × 1024 pixels of China-specific Sentinel2 data. (4) Extensive experiments demonstrate that our model outperforms existing LULC products and produces more fine-grained segmentation results comparable to other patch-based products. Finally, we release annual LULC maps for China in 2020-2022 and also make our model accessible online for real-time results export.

Image-text retrieval is a central problem for understanding the semantic relationship between vision and language, and serves as the basis for various visual and language tasks. Most previous works either simply learn coarse-grained representations of the overall image and text, or elaborately establish the correspondence between image regions or pixels and text words. However, the close relations between coarse- and fine-grained representations for each modality are important for image-text retrieval but almost neglected. As a result, such previous works inevitably suffer from low retrieval accuracy or heavy computational cost. In this work, we address image-text retrieval from a novel perspective by combining coarse- and fine-grained representation learning into a unified framework. This framework is consistent with human cognition, as humans simultaneously pay attention to the entire sample and regional elements to understand the semantic content. To this end, a Token-Guided Dual Transformer (TGDT) architecture which consists of two homogeneous branches for image and text modalities, respectively, is proposed for image-text retrieval. The TGDT incorporates both coarse- and fine-grained retrievals into a unified framework and beneficially leverages the advantages of both retrieval approaches. A novel training objective called Consistent Multimodal Contrastive (CMC) loss is proposed accordingly to ensure the intra- and inter-modal semantic consistencies between images and texts in the common embedding space. Equipped with a two-stage inference method based on the mixed global and local cross-modal similarity, the proposed method achieves state-of-the-art retrieval performances with extremely low inference time when compared with representative recent approaches. Code is publicly available: github.com/LCFractal/TGDT.

Vision transformers (ViTs) have been an alternative design paradigm to convolutional neural networks (CNNs). However, the training of ViTs is much harder than CNNs, as it is sensitive to the training parameters, such as learning rate, optimizer and warmup epoch. The reasons for training difficulty are empirically analysed in the paper Early Convolutions Help Transformers See Better, and the authors conjecture that the issue lies with the patchify-stem of ViT models. In this paper, we further investigate this problem and extend the above conclusion: only early convolutions do not help for stable training, but the scaled ReLU operation in the convolutional stem (conv-stem) matters. We verify, both theoretically and empirically, that scaled ReLU in conv-stem not only improves training stabilization, but also increases the diversity of patch tokens, thus boosting peak performance with a large margin via adding few parameters and flops. In addition, extensive experiments are conducted to demonstrate that previous ViTs are far from being well trained, further showing that ViTs have great potential to be a better substitute of CNNs.

Locating 3D objects from a single RGB image via Perspective-n-Points (PnP) is a long-standing problem in computer vision. Driven by end-to-end deep learning, recent studies suggest interpreting PnP as a differentiable layer, so that 2D-3D point correspondences can be partly learned by backpropagating the gradient w.r.t. object pose. Yet, learning the entire set of unrestricted 2D-3D points from scratch fails to converge with existing approaches, since the deterministic pose is inherently non-differentiable. In this paper, we propose the EPro-PnP a probabilistic PnP layer for general end-to-end pose estimation, which outputs a distribution of pose on the SE(3) manifold, essentially bringing categorical Softmax to the continuous domain. The 2D-3D coordinates and corresponding weights are treated as intermediate variables learned by minimizing the KL divergence between the predicted and target pose distribution. The underlying principle unifies the existing approaches and resembles the attention mechanism. EPro-PnP significantly outperforms competitive baselines, closing the gap between PnP-based method and the task-specific leaders on the LineMOD 6DoF pose estimation and nuScenes 3D object detection benchmarks.3

Decoupling spatiotemporal representation refers to decomposing the spatial and temporal features into dimension-independent factors. Although previous RGB-D-based motion recognition methods have achieved promising performance through the tightly coupled multi-modal spatiotemporal representation, they still suffer from (i) optimization difficulty under small data setting due to the tightly spatiotemporal-entangled modeling; (ii) information redundancy as it usually contains lots of marginal information that is weakly relevant to classification; and (iii) low interaction between multi-modal spatiotemporal information caused by insufficient late fusion. To alleviate these drawbacks, we propose to decouple and recouple spatiotemporal representation for RGB-D-based motion recognition. Specifically, we disentangle the task of learning spatiotemporal representation into 3 sub-tasks: (1) Learning high-quality and dimension independent features through a decoupled spatial and temporal modeling network. (2) Recoupling the decoupled representation to establish stronger space-time dependency. (3) Introducing a Cross-modal Adaptive Posterior Fusion (CAPF) mechanism to capture cross-modal spatiotemporal information from RGB-D data. Seamless combination of these novel designs forms a robust spatiotemporal representation and achieves better performance than state-of-the-art methods on four public motion datasets. Our code is available at https://github.com/damo-cv/MotionRGBD.

Multi-Target Multi-Camera Tracking has a wide range of applications and is the basis for many high-level inference and prediction tasks. How to make the system perform efficiently on a large number of cameras is a crucial research issue. Previous works have proposed many matching strategies to reduce the matching range and improve the matching accuracy. However, these works require human participation when formulating matching strategies, which becomes infeasible as the scale of the camera system increases. To tackle this problem, we propose an adaptive matching strategy to replace manual rules when guiding the matching between cameras. Specifically, we use the Markov decision process to model the tracklets matching problem between cameras. Reinforcement learning and imitation learning are combined to predict a set of cameras where the tracking target might be located. The predicted candidate camera set can be used for intercamera matching and association between tracklets. Moreover, our method can be trained with or without ground truth inter-camera trajectories, making it more practical in real scenarios. We evaluate our method on the city-scale tracking dataset Cityflow, and the proposed method is sufficient to replace manual rules, and finally improve the performance of the overall MTMCT system.

The gap in representations between image and video makes Image-to-Video Re-identification (I2V Re-ID) challenging, and recent works formulate this problem as a knowledge distillation (KD) process. In this paper, we propose a mutual discriminative knowledge distillation framework to transfer a video-based richer representation to an image based representation more effectively. Specifically, we propose the triplet contrast loss (TCL), a novel loss designed for KD. During the KD process, the TCL loss transfers the local structure, exploits the higher order information, and mitigates the misalignment of the heterogeneous output of teacher and student networks. Compared with other losses for KD, the proposed TCL loss selectively transfers the local discriminative features from teacher to student, making it effective in the ReID. Besides the TCL loss, we adopt mutual learning to regularize both the teacher and student networks training. Extensive experiments demonstrate the effectiveness of our method on the MARS, DukeMTMC-VideoReID and VeRi-776 benchmarks.

Nowadays, deep learning is widely applied to extract features for similarity computation in person re-identification (re-ID). However, the difference between the training data and testing data makes the performance of learned feature degraded during testing. Hence, re-ranking is proposed to mitigate this issue and various algorithms have been developed. However, most of existing re-ranking methods focus on replacing the Euclidean distance with sophisticated distance metrics, which are not friendly to downstream tasks and hard to be used for fast retrieval of massive data in real applications. In this work, we propose a graph-based re-ranking method to improve learned features while still keeping Euclidean distance as the similarity metric. Inspired by graph convolution networks, we develop an operator to propagate features over an appropriate graph. Since graph is the essential key for the propagation, two important criteria are considered for designing the graph, and different graphs are explored accordingly. Furthermore, a simple yet effective method is proposed to generate a profile vector for each tracklet in videos, which helps extend our method to video re-ID. Extensive experiments on three benchmark data sets, e.g., Market-1501, Duke, and MARS, demonstrate the effectiveness of our proposed approach.

Nowadays, real data in person re-identification (ReID) task is facing privacy issues, e.g., the banned dataset DukeMTMC-ReID. Thus it becomes much harder to collect real data for ReID task. Meanwhile, the labor cost of labeling ReID data is still very high and further hinders the development of the ReID research. Therefore, many methods turn to generate synthetic images for ReID algorithms as alternatives instead of real images. However, there is an inevitable domain gap between synthetic and real images. In previous methods, the generation process is based on virtual scenes, and their synthetic training data can not be changed according to different target real scenes automatically. To handle this problem, we propose a novel Target-Aware Generation pipeline to produce synthetic person images, called TAGPerson. Specifically, it involves a parameterized rendering method, where the parameters are controllable and can be adjusted according to the target scenes. In TAGPerson, we extract information from target scenes and use them to control our parameterized rendering process to generate target-aware synthetic images, which would hold a smaller gap to the real images in the specific target domain. In our experiments, our target-aware synthetic images can achieve a much higher performance than the generalized synthetic images on MSMT17, i.e. 47.5% vs. 40.9% for rank-1 accuracy. We will release this toolkit for the ReID community to generate synthetic images at any desired taste. The code is available at: https://github.com/tagperson/tagperson-blender

Although Vision transformers (ViTs) have recently dominated many vision tasks, deploying ViT models on resource-limited devices remains a challenging problem. To address such a challenge, several methods have been proposed to compress ViTs. Most of them borrow experience in convolutional neural networks (CNNs) and mainly focus on the spatial domain. However, the compression only in the spatial domain suffers from a dramatic performance drop without fine-tuning and is not robust to noise, as the noise in the spatial domain can easily confuse the pruning criteria, leading to some parameters/channels being pruned incorrectly. Inspired by recent findings that self-attention is a low-pass filter and low-frequency signals/components are more informative to ViTs, this paper proposes compressing ViTs with low-frequency components. Two metrics named low-frequency sensitivity (LFS) and low-frequency energy (LFE) are proposed for better channel pruning and token pruning. Additionally, a bottom-up cascade pruning scheme is applied to compress different dimensions jointly. Extensive experiments demonstrate that the proposed method could save 40% ～ 60% of the FLOPs in ViTs, thus significantly increasing the throughput on practical devices with less than 1% performance drop on ImageNet-1K.

Recent progress in video object detection (VOD) has shown that aggregating features from other frames to capture long-range contextual information is very important to deal with the challenges in VOD, such as partial occlusion, motion blur, etc. To exploit more effective feature aggregation, we propose several improvements over previous works in this paper: (1) a class-aware pixel-level feature aggregation module, which characterizes a pixel by exploiting the context information lying in the instances from both the current frame and other frames. Different from the previous non-local operation, the proposed class-aware pixel-level feature aggregation filters out most of the noisy information from the large scope of background and objects in different classes, and only enhances representation of a foreground pixel with the same class instances with limited ambiguous information; (2) a class-aware instance-level feature aggregation module, which aggregates features for object proposals by learning two kinds of relations: the temporal dependencies among the same class object proposals from support frames sampled in a long time range or even the whole sequence, and spatial topology relation among proposals of different objects in the target frame. The homogeneity constraint in instance-level feature aggregation filters out many defective proposals, making the feature aggregation more accurate; and (3) a correlation-based feature alignment module embedded in the instance-level feature aggregation, which aligns the feature maps of the support and target proposals. Without bells or whistles, the proposed method achieves state-of-the-art performance on the ImageNet VID dataset without any post-processing methods. This project is publicly availablehttps://github.com/LiangHann/Class-aware-Feature-Aggregation-Network-for-Video-Object-Detection.

Clustering-based approaches have been successfully applied to unsupervised domain adaptation (UDA) tasks for person re-identification (Re-ID), where no annotations are provided in target domain. However, the clustering process is sensitive to noises, leading to imperfect pseudo labels that could damage the training performance. In this work, we propose a Multi-view Evolutionary Training (MET) method to effectively reduce noises in clustering results from two dimensions. First, to improve the clustering accuracy at each time frame (i.e. snapshot quality), a Multi-view Diffusion (MvD) module is proposed. Through capturing data relationships from multiple viewpoints and aggregating their information, noises and bias from each individual viewpoint can be eliminated, and more reliable similarity matrix can be produced for clustering. Second, to improve the temporal consistency between clustering at different iterations, i.e. temporal consistency, we propose an Evolutionary Local Refinement (ELR) module, which utilizes the previous clustering results to guide and improve current results, and further make the training process more stable and robust. Extensive experiments demonstrate that our method can provide clustering results with high quality, and achieve state-of-the-art performance on UDA Re-ID.

Extracting robust feature representation is one of the key challenges in object re-identification (ReID). Although convolution neural network (CNN)-based methods have achieved great success, they only process one local neighborhood at a time and suffer from information loss on details caused by convolution and downsampling operators (e.g. pooling and strided convolution). To overcome these limitations, we propose a pure transformer-based object ReID framework named TransReID. Specifically, we first encode an image as a sequence of patches and build a transformer-based strong baseline with a few critical improvements, which achieves competitive results on several ReID benchmarks with CNN-based methods. To further enhance the robust feature learning in the context of transformers, two novel modules are carefully designed. (i) The jigsaw patch module (JPM) is proposed to rearrange the patch embeddings via shift and patch shuffle operations which generates robust features with improved discrimination ability and more diversified coverage. (ii) The side information embeddings (SIE) is introduced to mitigate feature bias towards camera/view variations by plugging in learnable embeddings to incorporate these non-visual clues. To the best of our knowledge, this is the first work to adopt a pure transformer for ReID research. Experimental results of TransReID are superior promising, which achieve state-of-the-art performance on both person and vehicle ReID benchmarks. Code is available at https://github.com/heshuting555/TransReID.

Recently, GAN based method has demonstrated strong effectiveness in generating augmentation data for person re-identification (ReID), on account of its ability to bridge the gap between domains and enrich the data variety in feature space. However, most of the ReID works pick all the GAN generated data as additional training samples or evaluate the quality of GAN generation at the entire data set level, ignoring the image-level essential feature of data in ReID task. In this paper, we analyze the in-depth characteristics of ReID sample and solve the problem of "What makes a GAN-generated image good for ReID''. Specifically, we propose to examine each data sample with id-consistency and diversity constraints by mapping image onto different spaces. With a metric-based sampling method, we demonstrate that not every GAN-generated data is beneficial for augmentation. Models trained with data filtered by our quality evaluation outperform those trained with the full augmentation set by a large margin. Extensive experiments show the effectiveness of our method on both supervised ReID task and unsupervised domain adaptation ReID task.

Video object detection (VOD) has been a rising topic in recent years due to the challenges such as occlusion, motion blur, etc. To deal with these challenges, feature aggregation from local or global support frames is verified effective. To exploit better feature aggregation, in this paper, we propose two improvements over previous works: a class-constrained spatial-temporal relation network and a correlation-based feature alignment module. For the class constrained spatial-temporal relation network, it operates on object region proposals, and learns two kinds of relations: (1) the dependencies among region proposals of the same object class from support frames sampled in a long time range or even the whole sequence, and (2) spatial relations among proposals of different objects in the target frame. The homogeneity constraint in spatial-temporal relation network not only filters out many defective proposals but also implicitly embeds the traditional post-processing strategies (e.g., Seq-NMS), leading to a unified end-to-end training networks. In the feature alignment module, we propose a correlation based feature alignment method to align the support and target frames for feature aggregation in the temporal domain. Our experiments show that the proposed method improves the accuracy of single-frame detectors significantly, and outperforms previous temporal or spatial relation networks. Without bells or whistles, the proposed method achieves state-of-the-art performance on the ImageNet VID dataset (84.80% with ResNet-101) without any post-processing methods.

Comparing two images from different views has been a long-standing challenging problem in computer vision, as visual features are not stable under large view point changes. In this paper, given a single input image of an object, we synthesize its features for other views, leveraging an existing modestly-sized 3D model collection of related but not identical objects. To accomplish this, we study the relationship of image patches between different views of the same object, seeking what we call surrogate patches -- patches in one view whose feature content predicts well the features of a patch in another view. Based upon these surrogate relationships, we can create feature sets for all views of the latent object on a per patch basis, providing us an augmented multi-view representation of the object. We provide theoretical and empirical analysis of the feature synthesis process, and evaluate the augmented features in fine-grained image retrieval/recognition and instance retrieval tasks. Experimental results show that our synthesized features do enable view-independent comparison between images and perform significantly better than other traditional approaches in this respect.

Joint segmentation of image sets is a challenging problem, especially when there are multiple objects with variable appearance shared among the images in the collection and the set of objects present in each particular image is itself varying and unknown. In this paper, we present a novel method to jointly segment a set of images containing objects from multiple classes. We first establish consistent functional maps across the input images, and introduce a formulation that explicitly models partial similarity across images instead of global consistency. Given the optimized maps between pairs of images, multiple groups of consistent segmentation functions are found such that they align with segmentation cues in the images, agree with the functional maps, and are mutually exclusive. The proposed fully unsupervised approach exhibits a significant improvement over the state-of-the-art methods, as shown on the co-segmentation data sets MSRC, Flickr, and PASCAL.

The construction of networks of maps among shapes in a collection enables a variety of applications in data-driven geometry processing. A key task in network construction is to make the maps consistent with each other. This consistency constraint, when properly defined, leads not only to a concise representation of such networks, but more importantly, it serves as a strong regularizer for correcting and improving noisy initial maps computed between pairs of shapes in isolation. Up-to-now, however, the consistency constraint has only been fully formulated for point-based maps or for shape collections that are fully similar. In this paper, we introduce a framework for computing consistent functional maps within heterogeneous shape collections. In such collections not all shapes share the same structure --- different types of shared structure may be present within different (but possibly overlapping) sub-collections. Unlike point-based maps, functional maps can encode similarities at multiple levels of detail (points or parts), and thus are particularly suitable for coping with such diversity within a shape collection. We show how to rigorously formulate the consistency constraint in the functional map setting. The formulation leads to a powerful tool for computing consistent functional maps, and also for discovering shared structures, such as meaningful shape parts. We also show how to adapt the procedure for handling very large-scale shape collections. Experimental results on benchmark datasets show that the proposed framework significantly improves upon state-of-the-art data-driven techniques. We demonstrate the usefulness of the framework in shape co-segmentation and various shape exploration tasks.

Joint segmentation of image sets has great importance for object recognition, image classification, and image retrieval. In this paper, we aim to jointly segment a set of images starting from a small number of labeled images or none at all. To allow the images to share segmentation information with each other, we build a network that contains segmented as well as unsegmented images, and extract functional maps between connected image pairs based on image appearance features. These functional maps act as general property transporters between the images and, in particular, are used to transfer segmentations. We define and operate in a reduced functional space optimized so that the functional maps approximately satisfy cycle-consistency under composition in the network. A joint optimization framework is proposed to simultaneously generate all segmentation functions over the images so that they both align with local segmentation cues in each particular image, and agree with each other under network transportation. This formulation allows us to extract segmentations even with no training data, but can also exploit such data when available. The collective effect of the joint processing using functional maps leads to accurate information sharing among images and yields superior segmentation results, as shown on the iCoseg, MSRC, and PASCAL data sets.