Hair editing is a long-standing problem in computer vision that demands both fine-grained local control and intuitive user interactions across diverse modalities. Despite the remarkable progress of GANs and diffusion models, existing methods still lack a unified framework that simultaneously supports arbitrary interaction modes (e.g., text, sketch, mask, and reference image) while ensuring precise editing and faithful preservation of irrelevant attributes. In this work, we introduce a novel paradigm that reformulates hair editing as proxy-based hair transfer. Specifically, we leverage the dense and semantically disentangled latent space of StyleGAN for precise manipulation and exploit its feature space for disentangled attribute preservation, thereby decoupling the objectives of editing and preservation. Our framework unifies different modalities by converting editing conditions into distinct transfer proxies, whose features are seamlessly blended to achieve global or local edits. Beyond 2D, we extend our paradigm to 3D-aware settings by incorporating EG3D and PanoHead, where we propose a multi-view boosted hair feature localization strategy together with 3D-tailored proxy generation methods that exploit the inherent properties of 3D-aware generative models. Extensive experiments demonstrate that our method consistently outperforms prior approaches in editing effects, attribute preservation, visual naturalness, and multi-view consistency, while offering unprecedented support for multimodal and mixed-modal interactions.

We present X2Video, the first diffusion model for rendering photorealistic videos guided by a sequence of intrinsic channels including albedo, normal, roughness, metallicity, and irradiance, while supporting intuitive multi-modal controls with reference images and text prompts for both global and local regions. The intrinsic guidance allows accurate manipulation of color, material, geometry, and lighting, while reference images and text prompts provide intuitive adjustments in the absence of intrinsic information. To enable these functionalities, we extend the intrinsic-guided image generation model XRGB to video generation by employing a novel and efficient Hybrid Self-Attention, which ensures temporal consistency across video frames and also enhances fidelity to reference images. We further develop a Masked Cross-Attention to disentangle global and local text prompts, applying them effectively onto respective local and global regions. For generating long videos, our novel Recursive Sampling method incorporates progressive frame sampling, combining keyframe prediction and frame interpolation to maintain long-range temporal consistency while preventing error accumulation. To support the training of X2Video, we assembled a video dataset named InteriorVideo, featuring 1,154 rooms from 295 interior scenes, complete with reliable ground-truth intrinsic channel sequences and smooth camera trajectories. Both qualitative and quantitative evaluations demonstrate that X2Video can produce long, temporally consistent, and photorealistic videos guided by intrinsic conditions. Additionally, X2Video effectively accommodates multi-modal controls with reference images, global and local text prompts, and simultaneously supports editing on color, material, geometry, and lighting through parametric tuning. Upon acceptance, we will publicly release our model and dataset.

Automatic furniture layout is long desired for convenient interior design. Leveraging the remarkable visual reasoning capabilities of multimodal large language models (MLLMs), recent methods address layout generation in a static manner, lacking the feedback-driven refinement essential for interactive user engagement. We introduce Chat2Layout, a novel interactive furniture layout generation system that extends the functionality of MLLMs into the realm of interactive layout design. To achieve this, we establish a unified vision-question paradigm for in-context learning, enabling seamless communication with MLLMs to steer their behavior without altering model weights. Within this framework, we present a novel training-free visual prompting mechanism. This involves a visual-text prompting technique that assist MLLMs in reasoning about plausible layout plans, followed by an Offline-to-Online search (O2O-Search) method, which identifies the minimal set of informative references to provide exemplars for visual-text prompting. By employing an agent system with MLLMs as the core controller, we enable bidirectional interaction. The agent not only comprehends the 3D environment and user requirements through linguistic and visual perception but also plans tasks and reasons about actions to generate and arrange furniture within the virtual space. Furthermore, the agent iteratively updates based on visual feedback from execution results. Experimental results demonstrate that our approach facilitates language-interactive generation and arrangement for diverse and complex 3D furniture.

Video inpainting modifies local regions in video while ensuring spatial and temporal coherence. However, existing methods-both traditional and recent diffusion-based ones-face key limitations: they lack unified support for both insertion and completion, and are restricted to single-object inpainting, making it difficult to handle multi-object scenarios involving grounding and interaction. In this article, we propose MultiPaint, a unified framework for multi-task, multi-object, and multi-condition video inpainting. First, we introduce dual-branch adapters to unify the insertion and completion tasks within a single model. Moreover, we propose a test-time scheduled feature composition strategy that enables multi-object inpainting with user-specified locations while better preserving interactions among objects, a setting that has been insufficiently addressed in prior work. Additionally, we introduce a multi-condition inpainting scheme that integrates text-guided, image-guided, and keyframe-guided modes via dynamic frame masking, providing more controllability in appearance customization. Extensive experiments show that MultiPaint achieves state-of-the-art performance on object insertion and scene completion among the recent works. We further demonstrate its versatility in downstream tasks including grounded video generation, object editing, object removal, image-guided inpainting, and long video inpainting.

Although significant progress has been made in the field of speech-driven 3D facial animation recently, the speech-driven animation of an indispensable facial component, eye gaze, has been overlooked by recent research. This is primarily due to the weak correlation between speech and eye gaze, as well as the scarcity of audio-gaze data, making it very challenging to generate 3D eye gaze motion from speech alone. In this paper, we propose a novel data-driven method which can generate diverse 3D eye gaze motions in harmony with the speech. To achieve this, we firstly construct an audio-gaze dataset that contains about 14 hours of audio-mesh sequences featuring high-quality eye gaze motion, head motion and facial motion simultaneously. The motion data is acquired by performing lightweight eye gaze fitting and face reconstruction on videos from existing audio-visual datasets. We then tailor a novel speech-to-motion translation framework in which the head motions and eye gaze motions are jointly generated from speech but are modeled in two separate latent spaces. This design stems from the physiological knowledge that the rotation range of eyeballs is less than that of head. Through mapping the speech embedding into the two latent spaces, the difficulty in modeling the weak correlation between speech and non-verbal motion is thus attenuated. Finally, our TalkingEyes, integrated with a speech-driven 3D facial motion generator, can synthesize eye gaze motion, eye blinks, head motion and facial motion collectively from speech. Qualitative and quantitative evaluations, along with a perceptual user study, demonstrate the superiority of the proposed method in generating diverse and natural 3D eye gaze motions from speech.

This qualitative paper examines the needs of residents to remember a local cultural heritage site collaboratively.The study observes and then designs for intangible affordances supporting this memory recall using the photo-elicitation method with generative artificial intelligence imagery.Specifically, collaboration was observed when editing a panoramic photograph using generative artificial intelligence.These instances were rare, and were analyzed to highlight intangible affordances aiding collaborative memory recall and content creation.Afterward, five examples were correlated to influence the design of an immersive and responsive 360° theatre system using specific combinations of artificial intelligence models to aid subjective recall.In this immersive space, storyteller preferences for edited content are finally made available for new users, thereby affording new collaborative storytelling about a cultural heritage site.As a contribution, this study aids the work of designers and sociologists by showing the photo-elicitation method's crossdisciplinary relevance to designing for collaborative, yet intangible storytelling affordances.

We present a novel approach for indoor scene synthesis, which learns to arrange decomposed cuboid primitives to represent 3D objects within a scene. Unlike conventional methods that use bounding boxes to determine the placement and scale of 3D objects, our approach leverages cuboids as a straightforward yet highly effective alternative for modeling objects. This allows for compact scene generation while minimizing object intersections. Our approach, coined CasaGPT for Cuboid Arrangement and Scene Assembly, employs an autoregressive model to sequentially arrange cuboids, producing physically plausible scenes. By applying rejection sampling during the fine-tuning stage to filter out scenes with object collisions, our model further reduces intersections and enhances scene quality. Additionally, we introduce a refined dataset, 3DFRONT-NC, which eliminates significant noise presented in the original dataset, 3D-FRONT. Extensive experiments on the 3D-FRONT dataset as well as our dataset demonstrate that our approach consistently outperforms the state-of-the-art methods, enhancing the realism of generated scenes, and providing a promising direction for 3D scene synthesis. Code is available at https://github.com/CASAGPT/CASA-GPT

Scalable Vector Graphics (SVG) has become the de facto standard for vector graphics in digital design, offering resolution independence and precise control over individual elements. Despite their advantages, creating high-quality SVG content remains challenging, as it demands technical expertise with professional editing software and a considerable time investment to craft complex shapes. Recent text-to-SVG generation methods aim to make vector graphics creation more accessible, but they still encounter limitations in shape regularity, generalization ability, and expressiveness. To address these challenges, we introduce Chat2SVG, a hybrid framework that combines the strengths of Large Language Models (LLMs) and image diffusion models for text-to-SVG generation. Our approach first uses an LLM to generate semantically meaningful SVG templates from basic geometric primitives. Guided by image diffusion models, a dual-stage optimization pipeline refines paths in latent space and adjusts point coordinates to enhance geometric complexity. Extensive experiments show that Chat2SVG outperforms existing methods in visual fidelity, path regularity, and semantic alignment. Additionally, our system enables intuitive editing through natural language instructions, making professional vector graphics creation accessible to all users. Our code is available at https://chat2svg.github.io/.

Image steganography can hide information in a host image and obtain a stego image that is perceptually indistinguishable from the original one. This technique has tremendous potential in scenarios like copyright protection and information retrospection. Some previous studies have proposed to enhance the robustness of the methods against image disturbances to increase their applicability. However, they generally cannot achieve a satisfying balance between the steganography quality and robustness. Instead of image-in-image steganography, we focus on the issue of message-in-image embedding that is robust to various real- world image distortions. This task aims to embed information into a natural image and the decoding result is required to be completely accurate, which increases the difficulty of data concealing and revealing. Inspired by the recent developments in transformer-based vision models, we discover that the tokenized representation of image is naturally suitable for steganography task. In this paper, we propose a novel message embedding framework, called Robust Message Steganography (RMSteg), which is competent to hide message via QR Code in a host image based on an normalizing flow-based model. The stego image derived by our method has imperceptible changes and the encoded message can be accurately restored even if the image is printed out and photographed. To our best knowledge, this is the first work that integrates the advantages of transformer models into normalizing flow. The code is available at https://github.com/huayuan4396/RMSteg.

Recent advancements in image and video synthesis have opened up new promise in generative games. One particularly intriguing application is transforming characters from anime films into interactive, playable entities. This allows players to immerse themselves in the dynamic anime world as their favorite characters for life simulation through language instructions. Such games are defined as infinite game since they eliminate predetermined boundaries and fixed gameplay rules, where players can interact with the game world through open-ended language and experience ever-evolving storylines and environments. Recently, a pioneering approach for infinite anime life simulation employs large language models (LLMs) to translate multi-turn text dialogues into language instructions for image generation. However, it neglects historical visual context, leading to inconsistent gameplay. Furthermore, it only generates static images, failing to incorporate the dynamics necessary for an engaging gaming experience. In this work, we propose AnimeGamer, which is built upon Multimodal Large Language Models (MLLMs) to generate each game state, including dynamic animation shots that depict character movements and updates to character states, as illustrated in Figure 1. We introduce novel action-aware multimodal representations to represent animation shots, which can be decoded into high-quality video clips using a video diffusion model. By taking historical animation shot representations as context and predicting subsequent representations, AnimeGamer can generate games with contextual consistency and satisfactory dynamics. Extensive evaluations using both automated metrics and human evaluations demonstrate that AnimeGamer outperforms existing methods in various aspects of the gaming experience. Codes and checkpoints are available at https://github.com/TencentARC/AnimeGamer.

We present I2V3D, a novel framework for animating static images into dynamic videos with precise 3D control, leveraging the strengths of both 3D geometry guidance and advanced generative models. Our approach combines the precision of a computer graphics pipeline, enabling accurate control over elements such as camera movement, object rotation, and character animation, with the visual fidelity of generative AI to produce high-quality videos from coarsely rendered inputs. To support animations with any initial start point and extended sequences, we adopt a two-stage generation process guided by 3D geometry: 1) 3D-Guided Keyframe Generation, where a customized image diffusion model refines rendered keyframes to ensure consistency and quality, and 2) 3D-Guided Video Interpolation, a training-free approach that generates smooth, high-quality video frames between keyframes using bidirectional guidance. Experimental results highlight the effectiveness of our framework in producing controllable, high-quality animations from single input images by harmonizing 3D geometry with generative models. The code for our framework will be publicly released.

In recent years, the increasing demand for dynamic 3D assets in design and gaming applications has given rise to powerful generative pipelines capable of synthesizing high-quality 4D objects. Previous methods generally rely on score distillation sampling (SDS) algorithm to infer the unseen views and motion of 4D objects, thus leading to unsatisfactory results with defects like over-saturation and Janus problem. Therefore, inspired by recent progress of video diffusion models, we propose to optimize a 4D representation by explicitly generating multi-view videos from one input image. However, it is far from trivial to handle practical challenges faced by such a pipeline, including dramatic temporal inconsistency, inter-frame geometry and texture diversity, and semantic defects brought by video generation results. To address these issues, we propose EG4D, a novel multi-stage framework that generates high-quality and consistent 4D assets without score distillation. Specifically, collaborative techniques and solutions are developed, including an attention injection strategy to synthesize temporal-consistent multi-view videos, a robust and efficient dynamic reconstruction method based on Gaussian Splatting, and a refinement stage with diffusion prior for semantic restoration. The qualitative comparisons and quantitative results demonstrate that our framework outperforms the baselines in generation quality by a considerable margin.

We present Animus3D , a text-driven 3D animation framework that generates motion field given a static 3D asset and text prompt. Previous methods mostly leverage the vanilla Score Distillation Sampling (SDS) objective to distill motion from pretrained text-to-video diffusion, leading to animations with minimal movement or noticeable jitter. To address this, our approach introduces a novel SDS alternative, Motion Score Distillation (MSD). Specifically, we introduce a LoRA-enhanced video diffusion model that defines a static source distribution rather than pure noise as in SDS, while another inversion-based noise estimation technique ensures appearance preservation when guiding motion. To further improve motion fidelity, we incorporate explicit temporal and spatial regularization terms that mitigate geometric distortions across time and space. Additionally, we propose a motion refinement module to upscale the temporal resolution and enhance fine-grained details, overcoming the fixed-resolution constraints of the underlying video model. Extensive experiments demonstrate that Animus3D successfully animates static 3D assets from diverse text prompts, generating significantly more substantial and detailed motion than state-of-the-art baselines while maintaining high visual integrity. Code will be released upon acceptance.

Image vectorization is a powerful technique that converts raster images into vector graphics, enabling enhanced flexibility and interactivity. However, popular image vectorization tools struggle with occluded regions, producing incomplete or fragmented shapes that hinder editability. While recent advancements have explored optimization-based and learning-based layer-wise image vectorization, these methods face limitations in vectorization quality and flexibility. In this paper, we introduce LayerPeeler, a novel layer-wise image vectorization approach that addresses these challenges through a progressive simplification paradigm. The key to LayerPeeler’s success lies in its autoregressive peeling strategy: by identifying and removing the topmost non-occluded layers while recovering underlying content, we generate vector graphics with complete paths and coherent layer structures. Our method leverages vision-language models to construct a layer graph that captures occlusion relationships among elements, enabling precise detection and description for non-occluded layers. These descriptive captions are used as editing instructions for a finetuned image diffusion model to remove the identified layers. To ensure accurate removal, we employ localized attention control that precisely guides the model to target regions while faithfully preserving the surrounding content. To support this, we contribute a large-scale dataset specifically designed for layer peeling tasks. Extensive quantitative and qualitative experiments demonstrate that LayerPeeler significantly outperforms existing techniques, producing vectorization results with superior path semantics, geometric regularity, and visual fidelity. Our code and dataset will be available at https://layerpeeler.github.io/.

Abstract Clipart, a pre-made graphic art form, offers a convenient and efficient way of illustrating visual content. Traditional workflows to convert static clipart images into motion sequences are laborious and time-consuming, involving numerous intricate steps like rigging, key animation and in-betweening. Recent advancements in text-to-video generation hold great potential in resolving this problem. Nevertheless, direct application of text-to-video generation models often struggles to retain the visual identity of clipart images or generate cartoon-style motions, resulting in unsatisfactory animation outcomes. In this paper, we introduce AniClipart, a system that transforms static clipart images into high-quality motion sequences guided by text-to-video priors. To generate cartoon-style and smooth motion, we first define Bézier curves over keypoints of the clipart image as a form of motion regularization. We then align the motion trajectories of the keypoints with the provided text prompt by optimizing the Video Score Distillation Sampling (VSDS) loss, which encodes adequate knowledge of natural motion within a pretrained text-to-video diffusion model. With a differentiable As-Rigid-As-Possible shape deformation algorithm, our method can be end-to-end optimized while maintaining deformation rigidity. Experimental results show that the proposed AniClipart consistently outperforms existing image-to-video generation models, in terms of text-video alignment, visual identity preservation, and motion consistency. Furthermore, we showcase the versatility of AniClipart by adapting it to generate a broader array of animation formats, such as layered animation, which allows topological changes.

Generating a 3D human model from a single reference image is a challenging task as it involves inferring textures and geometries in unseen views while maintaining consistency with the reference image. Existing methods that rely on 3D generative models are limited by the availability of 3D training data. Optimization-based approaches that distill text-to-image diffusion models into 3D models often struggle to preserve the intricate texture details of the reference image, resulting in inconsistent appearances across different views. In this paper, we propose HumanRef-GS, a novel method for single image-to-3D clothed human generation based on 3D Gaussian Splatting (3DGS). To ensure the generated 3D model is both photorealistic and consistent with the input image, HumanRef-GS employs a unique technique called reference-guided score distillation sampling (Ref-SDS). This method effectively incorporates image guidance into the generation process, enhancing the quality of the results. Additionally, we introduce region-aware attention to Ref-SDS, which ensures accurate correspondence between different body regions. To mitigate the impact of view dependence in 3DGS and enhance the view-consistency of the generated results, we substitute the anisotropic Gaussians in the vanilla representation with isotropic Gaussians. By utilizing the 3D Gaussian representation, our method significantly enhances the generation efficiency and rendering speed of 3D clothed human models. This improvement allows for faster and more efficient generation of high-quality results. Experimental results demonstrate that HumanRef-GS surpasses state-of-the-art methods in generating 3D clothed humans with fine geometry, photorealistic textures, and view-consistent appearances. We are committed to making our code and model available upon acceptance for further research and exploration.

Accurate medical image segmentation is critical to effective treatment strategies. Existing transformer-based methods for image segmentation mostly split the input image into a fixed and regular grid and regard cells in the grid as the vision tokens. However, not all tokens are of equal importance in the medical segmentation tasks, e.g., the tokens in tumor areas must be processed in a higher resolution than the background tokens which can be easily predicted with fewer transformer layers. In this paper, we propose a simple yet efficient segmentation framework called Top-Down Transformer (TDFormer), which incorporates a spatially adaptive token generation scheme into the transformer. The proposed top-down token generation comprises the following three components: attentiveness calculation, token splitting, and token fusion, where the collaboration of these components gradually fuses redundant background tokens and focuses only on the most critical areas. This allows for allocating more computation to process tokens containing delicate details in a finer resolution. Extensive experiments are conducted to demonstrate the robustness and effectiveness of the proposed TDFormer, that our method are superior to other state-of-the-art methods on the following publicly accessible datasets: BTCV Challenge, LiTS and BraTS 2020. We also dissect our method and evaluate the performance of each component.

Creating fine-retouched portrait images is tedious and time-consuming even for professional artists. There exist automatic retouching methods, but they either suffer from over-smoothing artifacts or lack generalization ability. To address such issues, we present StyleRetoucher, a novel automatic portrait image retouching framework, leveraging StyleGAN's generation and generalization ability to improve an input portrait image's skin condition while preserving its facial details. Harnessing the priors of pretrained StyleGAN, our method shows superior robustness: a). performing stably with fewer training samples and b). generalizing well on the out-domain data. Moreover, by blending the spatial features of the input image and intermediate features of the StyleGAN layers, our method preserves the input characteristics to the largest extent. We further propose a novel blemish-aware feature selection mechanism to effectively identify and remove the skin blemishes, improving the image skin condition. Qualitative and quantitative evaluations validate the great generalization capability of our method. Further experiments show StyleRetoucher's superior performance to the alternative solutions in the image retouching task. We also conduct a user perceptive study to confirm the superior retouching performance of our method over the existing state-of-the-art alternatives.

The speech-driven facial animation technology is generally categorized into two main types: 3D and 2D talking face. Both of these have garnered considerable research attention in recent years. However, to our knowledge, the research into 3D talking face has not progressed as deeply as that of 2D talking face, particularly in terms of lip-sync and perceptual mouth movements. The lip-sync necessitates an impeccable synchronization between mouth motion and speech audio. The speech perception derived from the perceptual mouth movements should resemble that of the driving audio. To mind the gap between the two sub-fields, we propose Learn2Talk, a learning framework that enhances 3D talking face network by integrating two key insights from the field of 2D talking face. First, drawing inspiration from the audio-video sync network, we develop a 3D sync-lip expert model for the pursuit of lip-sync between audio and 3D facial motions. Second, we utilize a teacher model, carefully chosen from among 2D talking face methods, to guide the training of the audio-to-3D motions regression network, thereby increasing the accuracy of 3D vertex movements. Extensive experiments demonstrate the superiority of our proposed framework over state-of-the-art methods in terms of lip-sync, vertex accuracy and perceptual movements. Finally, we showcase two applications of our framework: audio-visual speech recognition and speech-driven 3D Gaussian Splatting-based avatar animation.

Generating and inserting new objects into 3D content is a compelling approach for achieving versatile scene recreation. Existing methods, which rely on SDS optimization or single-view inpainting, often struggle to produce high-quality results. To address this, we propose a novel method for object insertion in 3D content represented by Gaussian Splatting. Our approach introduces a multi-view diffusion model, dubbed MVInpainter, which is built upon a pre-trained stable video diffusion model to facilitate view-consistent object inpainting. Within MVInpainter, we incorporate a ControlNet-based conditional injection module to enable controlled and more predictable multi-view generation. After generating the multi-view inpainted results, we further propose a mask-aware 3D reconstruction technique to refine Gaussian Splatting reconstruction from these sparse inpainted views. By leveraging these fabricate techniques, our approach yields diverse results, ensures view-consistent and harmonious insertions, and produces better object quality. Extensive experiments demonstrate that our approach outperforms existing methods.

The increased demand for 3D data in AR/VR, robotics and gaming applications, gave rise to powerful generative pipelines capable of synthesizing high-quality 3D objects. Most of these models rely on the Score Distillation Sampling (SDS) algorithm to optimize a 3D representation such that the rendered image maintains a high likelihood as evaluated by a pre-trained diffusion model. However, finding a correct mode in the high-dimensional distribution produced by the diffusion model is challenging and often leads to issues such as over-saturation, over-smoothing, and Janus-like artifacts. In this paper, we propose a novel learning paradigm for 3D synthesis that utilizes pre-trained diffusion models. Instead of focusing on mode-seeking, our method directly models the distribution discrepancy between multi-view renderings and diffusion priors in an adversarial manner, which unlocks the generation of high-fidelity and photorealistic 3D content, conditioned on a single image and prompt. Moreover, by harnessing the latent space of GANs and expressive diffusion model priors, our method facilitates a wide variety of 3D applications including single-view reconstruction, high diversity generation and continuous 3D interpolation in the open domain. The experiments demonstrate the superiority of our pipeline compared to previous works in terms of generation quality and diversity.

Generating a 3D human model from a single reference image is challenging because it requires inferring textures and geometries in invisible views while maintaining consistency with the reference image. Previous methods utilizing 3D generative models are limited by the availability of 3D training data. Optimization-based methods that lift text-to-image diffusion models to 3D generation often fail to preserve the texture details of the reference image, resulting in inconsistent appearances in different views. In this paper, we propose HumanRef, a 3D human generation framework from a single-view input. To ensure the generated 3D model is photorealistic and consistent with the input image, HumanRef introduces a novel method called reference-guided score distillation sampling (Ref-SDS), which effectively incorporates image guidance into the generation process. Furthermore, we introduce region-aware attention to Ref-SDS, ensuring accurate correspondence between different body regions. Experimental results demonstrate that HumanRef outper-forms state-of-the-art methods in generating 3D clothed humans with fine geometry, photorealistic textures, and view-consistent appearances. Code and model are available at https./reckcrtrhang.github.io/HumanRef.github.io/.

Face manipulation has ignited the interests of both academia and industry in very recent years. Existing face manipulation methods can be roughly categorized into two types: face attribute editing and face swapping. In this paper, we focus on swapping the identity. But unlike face swapping which only changes the face region, we attempt at a more challenging task: attribute-aware head swapping. Given a source video and a target video, we replace the whole target head with the whole source head while keeping the original target attributes. To address the inherent appearance gap (e.g., hairstyle, face shape), accompanying background incompatibility and lighting difference, our method consists of three key components: 1) a generative rendering-to-real-head model for source head modeling and attribute transfer; 2) a background modeling network to fix the background incompatibility during head swapping; 3) a deep harmonization network to fix remaining issues and makes the final composited result more realistic. We compare our approach to different face manipulation methods and the experimental results demonstrate its superiority for a lot of challenging cases.

Image completion has made tremendous progress with convolutional neural networks (CNNs), because of their powerful texture modeling capacity. However, due to some inherent properties (e.g., local inductive prior, spatial-invariant kernels), CNNs do not perform well in understanding global structures or naturally support pluralistic completion. Recently, transformers demonstrate their power in modeling the long-term relationship and generating diverse results, but their computation complexity is quadratic to input length, thus hampering the application in processing high-resolution images. This paper brings the best of both worlds to pluralistic image completion: appearance prior reconstruction with transformer and texture replenishment with CNN. The former transformer recovers pluralistic coherent structures together with some coarse textures, while the latter CNN enhances the local texture details of coarse priors guided by the high-resolution masked images. To decode diversified outputs from transformers, auto-regressive sampling is the most common method, but with extremely low efficiency. We further overcome this issue by proposing a new decoding strategy, temperature annealing probabilistic sampling (TAPS), which firstly achieves more than 70× speedup of inference at most, meanwhile maintaining the high quality and diversity of the sampled global structures. Moreover, we find the full CNN architecture will lead to suboptimal solutions for guided upsampling. To render more realistic and coherent contents, we design a novel module, named texture-aware guided attention, to concurrently consider the procedures of texture copy and generation, meanwhile raising several important modifications to solve the boundary artifacts. Through dense experiments, we found the proposed method vastly outperforms state-of-the-art methods in terms of four aspects: 1) large performance boost on image fidelity even compared to deterministic completion methods; 2) better diversity and higher fidelity for pluralistic completion; 3) exceptional generalization ability on large masks and generic dataset, like ImageNet. 4) Much higher decoding efficiency over previous auto-regressive based methods.

Image matting is a fundamental and challenging problem in computer vision and graphics. Most existing matting methods leverage a user-supplied trimap as an auxiliary input to produce good alpha matte. However, obtaining high-quality trimap itself is arduous. Recently, some hint-free methods have emerged, however, the matting quality is still far behind the trimap-based methods. The main reason is that, some hints for removing semantic ambiguity and improving matting quality are essential. Apparently, there is a trade-off between interaction cost and matting quality. To balance performance and user-friendliness, we propose an improved deep image matting framework which is trimap-free and only needs sparse user click or scribble interaction to minimize the needed auxiliary constraints while still allowing interactivity. Moreover, we introduce uncertainty estimation that predicts which parts need polishing and conduct uncertainty-guided refinement. To trade off runtime against refinement quality, users can also choose different refinement modes. Experimental results show that our method performs better than existing trimap-free methods and comparably to state-of-the-art trimap-based methods with minimal user effort. Finally, we demonstrate the extensibility of our framework to video human matting without any structure modification, by adding optical flow-based sparse hint propagation and temporal consistency regularization imposed on the single frame.

The intellectual property of deep networks can be easily "stolen" by surrogate model attack. There has been significant progress in protecting the model IP in classification tasks. However, little attention has been devoted to the protection of image processing models. By utilizing consistent invisible spatial watermarks, the work (Zhang et al. 2020) first considered model watermarking for deep image processing networks and demonstrated its efficacy in many downstream tasks. Its success depends on the hypothesis that if a consistent watermark exists in all prediction outputs, that watermark will be learned into the attacker's surrogate model. However, when the attacker uses common data augmentation attacks (e.g., rotate, crop, and resize) during surrogate model training, it will fail because the underlying watermark consistency is destroyed. To mitigate this issue, we propose a new watermarking methodology, "structure consistency", based on which a new deep structure-aligned model watermarking algorithm is designed. Specifically, the embedded watermarks are designed to be aligned with physically consistent image structures, such as edges or semantic regions. Experiments demonstrate that our method is more robust than the baseline in resisting data augmentation attacks. Besides that, we test the generalization ability and robustness of our method to a broader range of adaptive attacks.

Semantic alignment aims to establish pixel correspondences between images based on semantic consistency. It can serve as a fundamental component for various downstream computer vision tasks, such as style transfer and exemplar-based colorization, etc. Many existing methods use local features and their cosine similarities to infer semantic alignment. However, they struggle with significant intra-class variation of objects, such as appearance, size, etc. In other words, contents with the same semantics tend to be significantly different in vision. To address this issue, we propose a novel deep neural network of which the core lies in global feature enhancement and adaptive multi-scale inference. Specifically, two modules are proposed: an enhancement transformer for enhancing semantic features with global awareness; a probabilistic correlation module for adaptively fusing multi-scale information based on the learned confidence scores. We use the unified network architecture to achieve two types of semantic alignment, namely, cross-object semantic alignment and cross-domain semantic alignment. Experimental results demonstrate that our method achieves competitive performance on five standard cross-object semantic alignment benchmarks, and outperforms the state of the arts in cross-domain semantic alignment.

Robust segmenting with noisy labels is an important problem in medical imaging due to the difficulty of acquiring high-quality annotations. Despite the enormous success of recent developments, these developments still require multiple networks to construct their frameworks and focus on limited application scenarios, which leads to inflexibility in practical applications. They also do not explicitly consider the coarse boundary label problem, which results in sub-optimal results. To overcome these challenges, we propose a novel Simultaneous Edge Alignment and Memory-Assisted Learning (SEAMAL) framework for noisy-label robust segmentation. It achieves single-network robust learning, which is applicable for both 2D and 3D segmentation, in both Set-HQ-knowable and Set-HQ-agnostic scenarios. Specifically, to achieve single-model noise robustness, we design a Memory-assisted Selection and Correction module (MSC) that utilizes predictive history consistency from the Prediction Memory Bank to distinguish between reliable and non-reliable labels pixel-wisely, and that updates the reliable ones at the superpixel level. To overcome the coarse boundary label problem, which is common in practice, and to better utilize shape-relevant information at the boundary, we propose an Edge Detection Branch (EDB) that explicitly learns the boundary via an edge detection layer with only slight additional computational cost, and we improve the sharpness and precision of the boundary with a thinning loss. Extensive experiments verify that SEAMAL outperforms previous works significantly.

Open set recognition (OSR) aims to accurately classify known diseases and recognize unseen diseases as the unknown class in medical scenarios. However, in existing OSR approaches, gathering data from distributed sites to construct large-scale centralized training datasets usually leads to high privacy and security risk, which could be alleviated elegantly via the popular cross-site training paradigm, federated learning (FL). To this end, we represent the first effort to formulate federated open set recognition (FedOSR), and meanwhile propose a novel Federated Open Set Synthesis (FedOSS) framework to address the core challenge of FedOSR: the unavailability of unknown samples for all anticipated clients during the training phase. The proposed FedOSS framework mainly leverages two modules, i.e., Discrete Unknown Sample Synthesis (DUSS) and Federated Open Space Sampling (FOSS), to generate virtual unknown samples for learning decision boundaries between known and unknown classes. Specifically, DUSS exploits inter-client knowledge inconsistency to recognize known samples near decision boundaries and then pushes them beyond decision boundaries to synthesize discrete virtual unknown samples. FOSS unites these generated unknown samples from different clients to estimate the class-conditional distributions of open data space near decision boundaries and further samples open data, thereby improving the diversity of virtual unknown samples. Additionally, we conduct comprehensive ablation experiments to verify the effectiveness of DUSS and FOSS. FedOSS shows superior performance on public medical datasets in comparison with state-of-the-art approaches. The source code is available at https://github.com/CityU-AIM-Group/FedOSS.

Recent facial texture generation methods prefer to use deep networks to synthesize image content and then fill in the UV map, thus generating a compelling full texture from a single image. Nevertheless, the synthesized texture UV map usually comes from a space constructed by the training data or the 2D face generator, which limits the methods' generalization ability for in-the-wild input images. Consequently, their facial details, structures and identity may not be consistent with the input. In this paper, we address this issue by proposing a style transfer-based facial texture refinement method named FaceRefiner. FaceRefiner treats the 3D sampled texture asstyleand the output of a texture generation method ascontent. The photo-realistic style is then expected to be transferred from the style image to the content image. Different from current style transfer methods that only transfer high and middle level information to the result, our style transfer method integrates differentiable rendering to also transfer low level (or pixel level) information in the visible face regions. The main benefit of suchmulti-levelinformation transfer is that, the details, structures and semantics in the input can thus be well preserved. The extensive experiments on Multi-PIE, CelebA and FFHQ datasets demonstrate that our refinement method can improve the texture quality and the face identity preserving ability, compared with state-of-the-arts.

Visual In-Context Learning (ICL) has emerged as a promising research area due to its capability to accomplish various tasks with limited example pairs through analogical reasoning. However, training-based visual ICL has limitations in its ability to generalize to unseen tasks and requires the collection of a diverse task dataset. On the other hand, existing methods in the inference-based visual ICL category solely rely on textual prompts, which fail to capture fine-grained contextual information from given examples and can be time-consuming when converting from images to text prompts. To address these challenges, we propose Analogist, a novel inference-based visual ICL approach that exploits both visual and textual prompting techniques using a text-to-image diffusion model pretrained for image inpainting. For visual prompting, we propose a self-attention cloning (SAC) method to guide the fine-grained structural-level analogy between image examples. For textual prompting, we leverage GPT-4V's visual reasoning capability to efficiently generate text prompts and introduce a cross-attention masking (CAM) operation to enhance the accuracy of semantic-level analogy guided by text prompts. Our method is out-of-the-box and does not require fine-tuning or optimization. It is also generic and flexible, enabling a wide range of visual tasks to be performed in an in-context manner. Extensive experiments demonstrate the superiority of our method over existing approaches, both qualitatively and quantitatively. Our project webpage is available at https://analogist2d.github.io.

We propose the first video diffusion framework for reference-based lineart video colorization. Unlike previous works that rely solely on image generative models to colorize lineart frame by frame, our approach leverages a large-scale pretrained video diffusion model to generate colorized animation videos. This approach leads to more temporally consistent results and is better equipped to handle large motions. Firstly, we introduce Sketch-guided ControlNet which provides additional control to finetune an image-to-video diffusion model for controllable video synthesis, enabling the generation of animation videos conditioned on lineart. We then propose Reference Attention to facilitate the transfer of colors from the reference frame to other frames containing fast and expansive motions. Finally, we present a novel scheme for sequential sampling, incorporating the Overlapped Blending Module and Prev-Reference Attention , to extend the video diffusion model beyond its original fixed-length limitation for long video colorization. Both qualitative and quantitative results demonstrate that our method significantly outperforms state-of-the-art techniques in terms of frame and video quality, as well as temporal consistency. Moreover, our method is capable of generating high-quality, long temporal-consistent animation videos with large motions, which is not achievable in previous works. Our code and model are available at https://luckyhzt.github.io/lvcd.

Scene graphs offer a structured, hierarchical representation of images, with nodes and edges symbolizing objects and the relationships among them. It can serve as a natural interface for image editing, dramatically improving precision and flexibility. Leveraging this benefit, we introduce a new framework that integrates large language model (LLM) with Text2Image generative model for scene graph-based image editing. This integration enables precise modifications at the object level and creative recomposition of scenes without compromising overall image integrity. Our approach involves two primary stages: 1) Utilizing a LLM-driven scene parser, we construct an image's scene graph, capturing key objects and their interrelationships, as well as parsing fine-grained attributes such as object masks and descriptions. These annotations facilitate concept learning with a fine-tuned diffusion model, representing each object with an optimized token and detailed description prompt. 2) During the image editing phase, a LLM editing controller guides the edits towards specific areas. These edits are then implemented by an attention-modulated diffusion editor, utilizing the fine-tuned model to perform object additions, deletions, replacements, and adjustments. Through extensive experiments, we demonstrate that our framework significantly outperforms existing image editing methods in terms of editing precision and scene aesthetics. Our code is available at https://bestzzhang.github.io/SGEdit.

Vector graphics are widely used in digital art and highly favored by designers due to their scalability and layer-wise properties. However, the process of creating and editing vector graphics requires creativity and design expertise, making it a time-consuming task. Recent advancements in text-to-vector (T2V) generation have aimed to make this process more accessible. However, existing T2V methods directly optimize control points of vector graphics paths, often resulting in intersecting or jagged paths due to the lack of geometry constraints. To overcome these limitations, we propose a novel neural path representation by designing a dual-branch Variational Autoencoder (VAE) that learns the path latent space from both sequence and image modalities. By optimizing the combination of neural paths, we can incorporate geometric constraints while preserving expressivity in generated SVGs. Furthermore, we introduce a two-stage path optimization method to improve the visual and topological quality of generated SVGs. In the first stage, a pre-trained text-to-image diffusion model guides the initial generation of complex vector graphics through the Variational Score Distillation (VSD) process. In the second stage, we refine the graphics using a layer-wise image vectorization strategy to achieve clearer elements and structure. We demonstrate the effectiveness of our method through extensive experiments and showcase various applications. The project page is https://intchous.github.io/T2V-NPR.

As a powerful representation of 3D scenes, the neural radiance field (NeRF) enables high-quality novel view synthesis from multi-view images. Stylizing NeRF, however, remains challenging, especially in simulating a text-guided style with both the appearance and the geometry altered simultaneously. In this paper, we present NeRF-Art, a text-guided NeRF stylization approach that manipulates the style of a pre-trained NeRF model with a simple text prompt. Unlike previous approaches that either lack sufficient geometry deformations and texture details or require meshes to guide the stylization, our method can shift a 3D scene to the target style characterized by desired geometry and appearance variations without any mesh guidance. This is achieved by introducing a novel global-local contrastive learning strategy, combined with the directional constraint to simultaneously control both the trajectory and the strength of the target style. Moreover, we adopt a weight regularization method to effectively suppress cloudy artifacts and geometry noises which arise easily when the density field is transformed during geometry stylization. Through extensive experiments on various styles, we demonstrate that our method is effective and robust regarding both single-view stylization quality and cross-view consistency.

Visual question answering (VQA) has experienced tremendous progress in recent years. However, most efforts have only focused on 2D image question-answering tasks. In this article, we extend VQA to its 3D counterpart, 3D question answering (3DQA), which can facilitate a machine's perception of 3D real-world scenarios. Unlike 2D image VQA, 3DQA takes the color point cloud as input and requires both appearance and 3D geometrical comprehension to answer the 3D-related questions. To this end, we propose a novel transformer-based 3DQA framework "3DQA-TR", which consists of two encoders to exploit the appearance and geometry information, respectively. Finally, the multi-modal information about the appearance, geometry, and linguistic question can attend to each other via a 3D-linguistic Bert to predict the target answers. To verify the effectiveness of our proposed 3DQA framework, we further develop the first 3DQA dataset "ScanQA", which builds on the ScanNet dataset and contains over 10 K question-answer pairs for 806 scenes. To the best of our knowledge, ScanQA is the first large-scale dataset with natural-language questions and free-form answers in 3D environments that is fully human-annotated. We also use several visualizations and experiments to investigate the astonishing diversity of the collected questions and the significant differences between this task from 2D VQA and 3D captioning. Extensive experiments on this dataset demonstrate the obvious superiority of our proposed 3DQA framework over state-of-the-art VQA frameworks and the effectiveness of our major designs. Our code and dataset will be made publicly available to facilitate research in this direction. The code and data are available at http://shuquanye.com/3DQA_website/.

Text-driven 3D scene generation is widely applicable to video gaming, film industry, and metaverse applications that have a large demand for 3D scenes. However, existing text-to-3D generation methods are limited to producing 3D objects with simple geometries and dreamlike styles that lack realism. In this work, we present Text2NeRF, which is able to generate a wide range of 3D scenes with complicated geometric structures and high-fidelity textures purely from a text prompt. To this end, we adopt NeRF as the 3D representation and leverage a pre-trained text-to-image diffusion model to constrain the 3D reconstruction of the NeRF to reflect the scene description. Specifically, we employ the diffusion model to infer the text-related image as the content prior and use a monocular depth estimation method to offer the geometric prior. Both content and geometric priors are utilized to update the NeRF model. To guarantee textured and geometric consistency between different views, we introduce a progressive scene inpainting and updating strategy for novel view synthesis of the scene. Our method requires no additional training data but only a natural language description of the scene as the input. Extensive experiments demonstrate that our Text2NeRF outperforms existing methods in producing photo-realistic, multi-view consistent, and diverse 3D scenes from a variety of natural language prompts. Our code and model are available at https://github.com/eckertzhang/Text2NeRF.

We propose VQ-NeRF, a two-branch neural network model that incorporates Vector Quantization (VQ) to decompose and edit reflectance fields in 3D scenes. Conventional neural reflectance fields use only continuous representations to model 3D scenes, despite the fact that objects are typically composed of discrete materials in reality. This lack of discretization can result in noisy material decomposition and complicated material editing. To address these limitations, our model consists of a continuous branch and a discrete branch. The continuous branch follows the conventional pipeline to predict decomposed materials, while the discrete branch uses the VQ mechanism to quantize continuous materials into individual ones. By discretizing the materials, our model can reduce noise in the decomposition process and generate a segmentation map of discrete materials. Specific materials can be easily selected for further editing by clicking on the corresponding area of the segmentation outcomes. Additionally, we propose a dropout-based VQ codeword ranking strategy to predict the number of materials in a scene, which reduces redundancy in the material segmentation process. To improve usability, we also develop an interactive interface to further assist material editing. We evaluate our model on both computer-generated and real-world scenes, demonstrating its superior performance. To the best of our knowledge, our model is the first to enable discrete material editing in 3D scenes.

Looping videos are short video clips that can be looped endlessly without visible seams or artifacts. They provide a very attractive way to capture the dynamism of natural scenes. Existing methods have been mostly limited to 2D representations. In this paper, we take a step forward and propose a practical solution that enables an immersive experience on dynamic 3D looping scenes. The key challenge is to consider the per-view looping conditions from asynchronous input while maintaining view consistency for the 3D representation. We propose a novel sparse 3D video representation, namely Multi-Tile Video (MTV), which not only provides a view-consistent prior, but also greatly reduces memory usage, making the optimization of a 4D volume tractable. Then, we introduce a two-stage pipeline to construct the 3D looping MTV from completely asynchronous multi-view videos with no time overlap. A novel looping loss based on video temporal retargeting algorithms is adopted during the optimization to loop the 3D scene. Experiments of our framework have shown promise in successfully generating and rendering photorealistic 3D looping videos in real time even on mobile devices. The code, dataset, and live demos are available in https://limacv.github.io/VideoLoop3D_web/.

Neural radiance fields (NeRFs) enable novel-view synthesis with unprecedented visual quality. However, to render photorealistic images, NeRFs require hundreds of deep multilayer perceptron (MLP) evaluations - for each pixel. This is prohibitively expensive and makes realtime rendering infeasible, even on powerful modern GPUs. In this paper, we propose a novel approach to distill and bake NeRFs into highly efficient mesh-based neural representations that are fully compatible with the massively parallel graphics rendering pipeline. We represent scenes as neural radiance features encoded on a two-layer duplex mesh, which effectively over-comes the inherent inaccuracies in 3D surface reconstruction by learning the aggregated radiance information from a reliable interval of ray-surface intersections. To exploit local geometric relationships of nearby pixels, we leverage screen-space convolutions instead of the MLPs used in NeRFs to achieve high-quality appearance. Finally, the performance of the whole framework is further boosted by a novel multi-view distillation optimization strategy. We demonstrate the effectiveness and superiority of our approach via extensive experiments on a range of standard datasets.

This paper focuses on analyzing and improving the commonsense ability of recent popular vision-language (VL) models. Despite the great success, we observe that existing VL-models still lack commonsense knowledge/reasoning ability (e.g., “Lemons are sour”), which is a vital component towards artificial general intelligence. Through our analysis, we find one important reason is that existing large-scale VL datasets do not contain much commonsense knowledge, which motivates us to improve the commonsense of VL-models from the data perspective. Rather than collecting a new VL training dataset, we propose a more scalable strategy, i.e., “Data Augmentation with kNowledge graph linearization for CommonsensE capability” (DANCE). It can be viewed as one type of data augmentation technique, which can inject commonsense knowledge into existing VL datasets on the fly during training. More specifically, we leverage the commonsense knowledge graph (e.g., ConceptNet) and create variants of text description in VL datasets via bidirectional sub-graph sequentialization. For better commonsense evaluation, we further propose the first retrieval-based commonsense diagnostic benchmark. By conducting extensive experiments on some representative VL-models, we demonstrate that our DANCE technique is able to significantly improve the commonsense ability while maintaining the performance on vanilla retrieval tasks. The code and data are available at https://github.com/pleaseconnectwifi/DANCE.

Medical image registration is a critical task that estimates the spatial correspondence between pairs of images. However, current traditional and deep-learning-based methods rely on similarity measures to generate a deforming field, which often results in disproportionate volume changes in dissimilar regions, especially in tumor regions. These changes can significantly alter the tumor size and underlying anatomy, which limits the practical use of image registration in clinical diagnosis. To address this issue, we have formulated image registration with tumors as a constraint problem that preserves tumor volumes while maximizing image similarity in other normal regions. Our proposed strategy involves a two-stage process. In the first stage, we use similarity-based registration to identify potential tumor regions by their volume change, generating a soft tumor mask accordingly. In the second stage, we propose a volume-preserving registration with a novel adaptive volume-preserving loss that penalizes the change in size adaptively based on the masks calculated from the previous stage. Our approach balances image similarity and volume preservation in different regions, i.e., normal and tumor regions, by using soft tumor masks to adjust the imposition of volume-preserving loss on each one. This ensures that the tumor volume is preserved during the registration process. We have evaluated our strategy on various datasets and network architectures, demonstrating that our method successfully preserves the tumor volume while achieving comparable registration results with state-of-the-art methods. Our codes is available at: https://dddraxxx.github.io/Volume-Preserving-Registration/.

Neural implicit fields are powerful for representing 3D scenes and generating high-quality novel views, but it remains challenging to use such implicit representations for creating a 3D human avatar with a specific identity and artistic style that can be easily animated. Our proposed method, AvatarCraft, addresses this challenge by using diffusion models to guide the learning of geometry and texture for a neural avatar based on a single text prompt. We carefully design the optimization framework of neural implicit fields, including a coarse-to-fine multi-bounding box training strategy, shape regularization, and diffusion-based constraints, to produce high-quality geometry and texture. Additionally, we make the human avatar animatable by deforming the neural implicit field with an explicit warping field that maps the target human mesh to a template human mesh, both represented using parametric human models. This simplifies animation and reshaping of the generated avatar by controlling pose and shape parameters. Extensive experiments on various text descriptions show that AvatarCraft is effective and robust in creating human avatars and rendering novel views, poses, and shapes. Our project page is: https://avatar-craft.github.io/.

Hair editing has made tremendous progress in recent years. Early hair editing methods use well-drawn sketches or masks to specify the editing conditions. Even though they can enable very fine-grained local control, such interaction modes are inefficient for the editing conditions that can be easily specified by language descriptions or reference images. Thanks to the recent breakthrough of cross-modal models (e.g., CLIP), HairCLIP is the first work that enables hair editing based on text descriptions or reference images. However, such text-driven and reference-driven interaction modes make HairCLIP unable to support fine-grained controls specified by sketch or mask. In this paper, we propose HairCLIPv2, aiming to support all the aforementioned interactions with one unified framework. Simultaneously, it improves upon HairCLIP with better irrelevant attributes (e.g., identity, background) preservation and unseen text descriptions support. The key idea is to convert all the hair editing tasks into hair transfer tasks, with editing conditions converted into different proxies accordingly. The editing effects are added upon the input image by blending the corresponding proxy features within the hairstyle or hair color feature spaces. Besides the unprecedented user interaction mode support, quantitative and qualitative experiments demonstrate the superiority of HairCLIPv2 in terms of editing effects, irrelevant attribute preservation and visual naturalness. Our code is available at https://github.com/wty-ustc/HairCLIPv2.

Recently, text-to-image denoising diffusion probabilistic models (DDPMs) have demonstrated impressive image generation capabilities and have also been successfully applied to image inpainting. However, in practice, users often require more control over the inpainting process beyond textual guidance, especially when they want to composite objects with customized appearance, color, shape, and layout. Unfortunately, existing diffusion-based inpainting methods are limited to single-modal guidance and require task-specific training, hindering their cross-modal scalability. To address these limitations, we propose Uni-paint, a unified framework for multimodal inpainting that offers various modes of guidance, including unconditional, text-driven, stroke-driven, exemplar-driven inpainting, as well as a combination of these modes. Furthermore, our Uni-paint is based on pretrained Stable Diffusion and does not require task-specific training on specific datasets, enabling few-shot generalizability to customized images. We have conducted extensive qualitative and quantitative evaluations that show our approach achieves comparable results to existing single-modal methods while offering multimodal inpainting capabilities not available in other methods. Code is available at https://github.com/ysy31415/unipaint.

Vector graphics are widely used in digital art and valued by designers for their scalability and layer-wise topological properties. However, the creation and editing of vector graphics necessitate creativity and design expertise, leading to a time-consuming process. In this paper, we propose a novel pipeline that generates high-quality customized vector graphics based on textual prompts while preserving the properties and layer-wise information of a given exemplar SVG. Our method harnesses the capabilities of large pre-trained text-to-image models. By fine-tuning the cross-attention layers of the model, we generate customized raster images guided by textual prompts. To initialize the SVG, we introduce a semantic-based path alignment method that preserves and transforms crucial paths from the exemplar SVG. Additionally, we optimize path parameters using both image-level and vector-level losses, ensuring smooth shape deformation while aligning with the customized raster image. We extensively evaluate our method using multiple metrics from vector-level, image-level, and text-level perspectives. The evaluation results demonstrate the effectiveness of our pipeline in generating diverse customizations of vector graphics with exceptional quality. The project page is https://intchous.github.io/SVGCustomization.

Abstract Recent advancements in large‐scale text‐to‐image diffusion models have enabled many applications in image editing. However, none of these methods have been able to edit the layout of single existing images. To address this gap, we propose the first framework for layout editing of a single image while preserving its visual properties, thus allowing for continuous editing on a single image. Our approach is achieved through two key modules. First, to preserve the characteristics of multiple objects within an image, we disentangle the concepts of different objects and embed them into separate textual tokens using a novel method called masked textual inversion. Next, we propose a training‐free optimization method to perform layout control for a pre‐trained diffusion model, which allows us to regenerate images with learned concepts and align them with user‐specified layouts. As the first framework to edit the layout of existing images, we demonstrate that our method is effective and outperforms other baselines that were modified to support this task. Code is available at our project page.

Semantic image synthesis, translating semantic layouts to photo-realistic images, is a one-to-many mapping problem. Though impressive progress has been recently made, diverse semantic synthesis that can efficiently produce semantic-level or even instance-level multimodal results, still remains a challenge. In this article, we propose a novel diverse semantic image synthesis framework from the perspective of semantic class distributions, which naturally supports diverse generation at both semantics and instance level. We achieve this by modeling class-level conditional modulation parameters as continuous probability distributions instead of discrete values, and sampling per-instance modulation parameters through instance-adaptive stochastic sampling that is consistent across the network. Moreover, we propose prior noise remapping, through linear perturbation parameters encoded from paired references, to facilitate supervised training and exemplar-based instance style control at test time. To further extend the user interaction function of the proposed method, we also introduce sketches into the network. In addition, specially designed generator modules, Progressive Growing Module and Multi-Scale Refinement Module, can be used as a general module to improve the performance of complex scene generation. Extensive experiments on multiple datasets show that our method can achieve superior diversity and comparable quality compared to state-of-the-art methods. Codes are available at https://github.com/tzt101/INADE.git.

We propose to restore old photos that suffer from severe degradation through a deep learning approach. Unlike conventional restoration tasks that can be solved through supervised learning, the degradation in real photos is complex and the domain gap between synthetic images and real old photos makes the network fail to generalize. Therefore, we propose a novel triplet domain translation network by leveraging real photos along with massive synthetic image pairs. Specifically, we train two variational autoencoders (VAEs) to respectively transform old photos and clean photos into two latent spaces. And the translation between these two latent spaces is learned with synthetic paired data. This translation generalizes well to real photos because the domain gap is closed in the compact latent space. Besides, to address multiple degradations mixed in one old photo, we design a global branch with a partial nonlocal block targeting the structured defects, such as scratches and dust spots, and a local branch targeting the unstructured defects, such as noises and blurriness. We also extend the global branch with a more memory-efficient scheme, named multi-scale patch-based attention to processing high-resolution photos. Two branches are fused in the latent space, leading to improved capability to restore old photos from multiple defects. Furthermore, we apply another face refinement network to recover fine details of faces in the old photos, thus ultimately generating photos with enhanced perceptual quality. With comprehensive experiments, the proposed pipeline demonstrates superior performance over state-of-the-art methods as well as existing commercial tools in terms of visual quality for old photos restoration. Both code and models could be found at https://github.com/microsoft/Bringing-Old-Photos-Back-to-Life.

Point cloud segmentation is a fundamental task in 3D. Despite recent progress on point cloud segmentation with the power of deep networks, current learning methods based on the clean label assumptions may fail with noisy labels. Yet, class labels are often mislabeled at both instance-level and boundary-level in real-world datasets. In this work, we take the lead in solving the instance-level label noise by proposing a Point Noise-Adaptive Learning (PNAL) framework. Compared to noise-robust methods on image tasks, our framework is noise-rate blind, to cope with the spatially variant noise rate specific to point clouds. Specifically, we propose a point-wise confidence selection to obtain reliable labels from the historical predictions of each point. A cluster-wise label correction is proposed with a voting strategy to generate the best possible label by considering the neighbor correlations. To handle boundary-level label noise, we also propose a variant "PNAL-boundary " with a progressive boundary label cleaning strategy. Extensive experiments demonstrate its effectiveness on both synthetic and real-world noisy datasets. Even with 60% symmetric noise and high-level boundary noise, our framework significantly outperforms its baselines, and is comparable to the upper bound trained on completely clean data. Moreover, we cleaned the popular real-world dataset ScanNetV2 for rigorous experiment. Our code and data is available at https://github.com/pleaseconnectwifi/PNAL.

Medical image segmentation is almost the most important pre-processing procedure in computer-aided diagnosis but is also a very challenging task due to the complex shapes of segments and various artifacts caused by medical imaging, (i.e., low-contrast tissues, and non-homogenous textures). In this paper, we propose a simple yet effective segmentation framework that incorporates the geometric prior and contrastive similarity into the weakly-supervised segmentation framework in a loss-based fashion. The proposed geometric prior built on point cloud provides meticulous geometry to the weakly-supervised segmentation proposal, which serves as better supervision than the inherent property of the bounding-box annotation (i.e., height and width). Furthermore, we propose the contrastive similarity to encourage organ pixels to gather around in the contrastive embedding space, which helps better distinguish low-contrast tissues. The proposed contrastive embedding space can make up for the poor representation of the conventionally-used gray space. Extensive experiments are conducted to verify the effectiveness and the robustness of the proposed weakly-supervised segmentation framework. The proposed framework are superior to state-of-the-art weakly-supervised methods on the following publicly accessible datasets: LiTS 2017 Challenge, KiTS 2021 Challenge and LPBA40. We also dissect our method and evaluate the performance of each component.

Scalable Vector Graphics (SVG) is a popular vector image format that offers good support for interactivity and animation. Despite its appealing characteristics, creating custom SVG content can be challenging for users due to the steep learning curve required to understand SVG grammars or get familiar with professional editing software. Recent advancements in text-to-image generation have inspired researchers to explore vector graphics synthesis using either image-based methods (i.e., text → raster image → vector graphics) combining text-to-image generation models with image vectorization, or language-based methods (i.e., text → vector graphics script) through pretrained large language models. Nevertheless, these methods suffer from limitations in terms of generation quality, diversity, and flexibility. In this paper, we introduce IconShop, a text-guided vector icon synthesis method using autoregressive transformers. The key to success of our approach is to sequentialize and tokenize SVG paths (and textual descriptions as guidance) into a uniquely decodable token sequence. With that, we are able to exploit the sequence learning power of autoregressive transformers, while enabling both unconditional and text-conditioned icon synthesis. Through standard training to predict the next token on a large-scale vector icon dataset accompanied by textural descriptions, the proposed IconShop consistently exhibits better icon synthesis capability than existing image-based and language-based methods both quantitatively (using the FID and CLIP scores) and qualitatively (through formal subjective user studies). Meanwhile, we observe a dramatic improvement in generation diversity, which is validated by the objective Uniqueness and Novelty measures. More importantly, we demonstrate the flexibility of IconShop with multiple novel icon synthesis tasks, including icon editing, icon interpolation, icon semantic combination, and icon design auto-suggestion.

Exemplar-based portrait stylization is widely attractive and highly desired. Despite recent successes, it remains challenging, especially when considering both texture and geometric styles. In this article, we present the first framework for one-shot 3D portrait style transfer, which can generate 3D face models with both the geometry exaggerated and the texture stylized while preserving the identity from the original content. It requires only one arbitrary style image instead of a large set of training examples for a particular style, provides geometry and texture outputs that are fully parameterized and disentangled, and enables further graphics applications with the 3D representations. The framework consists of two stages. In the first geometric style transfer stage, we use facial landmark translation to capture the coarse geometry style and guide the deformation of the dense 3D face geometry. In the second texture style transfer stage, we focus on performing style transfer on the canonical texture by adopting a differentiable renderer to optimize the texture in a multi-view framework. Experiments show that our method achieves robustly good results on different artistic styles and outperforms existing methods. We also demonstrate the advantages of our method via various 2D and 3D graphics applications.

Face image manipulation via three-dimensional guidance has been widely applied in various interactive scenarios due to its semantically-meaningful understanding and user-friendly controllability. However, existing 3D-morphable-model-based manipulation methods are not directly applicable to out-of-domain faces, such as non-photorealistic paintings, cartoon portraits, or even animals, mainly due to the formidable difficulties in building the model for each specific face domain. To overcome this challenge, we propose, as far as we know, the first method to manipulate faces in arbitrary domains using human 3DMM. This is achieved through two major steps: 1) disentangled mapping from 3DMM parameters to the latent space embedding of a pre-trained StyleGAN2 [1] that guarantees disentangled and precise controls for each semantic attribute; and 2) cross-domain adaptation that bridges domain discrepancies and makes human 3DMM applicable to out-of-domain faces by enforcing a consistent latent space embedding. Experiments and comparisons demonstrate the superiority of our high-quality semantic manipulation method on a variety of face domains with all major 3D facial attributes controllable - pose, expression, shape, albedo, and illumination. Moreover, we develop an intuitive editing interface to support user-friendly control and instant feedback. Our project page is https://cassiepython.github.io/cddfm3d/index.html.

Due to inevitable noises introduced during scanning and quantization, 3D reconstruction via RGB-D sensors suffers from errors both in geometry and texture, leading to artifacts such as camera drifting, mesh distortion, texture ghosting, and blurriness. Given an imperfect reconstructed 3D model, most previous methods have focused on refining either geometry, texture, or camera pose. Consequently, different optimization schemes and objectives for optimizing each component have been used in previous joint optimization methods, forming a complicated system. In this paper, we propose a novel optimization approach based on differentiable rendering, which integrates the optimization of camera pose, geometry, and texture into a unified framework by enforcing consistency between the rendered results and the corresponding RGB-D inputs. Based on the unified framework, we introduce a joint optimization approach to fully exploit the inter-relationships among the three objective components, and describe an adaptive interleaving strategy to improve optimization stability and efficiency. Using differentiable rendering, an image-level adversarial loss is applied to further improve the 3D model, making it more photorealistic. Experiments on synthetic and real data using quantitative and qualitative evaluation demonstrated the superiority of our approach in recovering both fine-scale geometry and high-fidelity texture.

Neural Radiance Field (NeRF) has gained considerable attention recently for 3D scene reconstruction and novel view synthesis due to its remarkable synthesis quality. However, image blurriness caused by defocus or motion, which often occurs when capturing scenes in the wild, significantly degrades its reconstruction quality. To address this problem, We propose Deblur-NeRF, the first method that can recover a sharp NeRF from blurry input. We adopt an analysis-by-synthesis approach that reconstructs blurry views by simulating the blurring process, thus making NeRF robust to blurry inputs. The core of this simulation is a novel Deformable Sparse Kernel (DSK) module that models spatially-varying blur kernels by deforming a canonical sparse kernel at each spatial location. The ray origin of each kernel point is Jointly optimized, inspired by the physical blurring process. This module is parameterized as an MLP that has the ability to be generalized to various blur types. Jointly optimizing the NeRF and the DSK module allows us to restore a sharp NeRF. We demonstrate that our method can be used on both camera motion blur and defocus blur: the two most common types of blur in real scenes. Evaluation results on both synthetic and real-world data show that our method outperforms several baselines. The synthetic and real datasets along with the source code is publicly available at https://limacv.github.io/deblurNeRF/.

We present a learning-based framework, recurrent transformer network (RTN), to restore heavily degraded old films. Instead of performing frame-wise restoration, our method is based on the hidden knowledge learned from adjacent frames that contain abundant information about the occlusion, which is beneficial to restore challenging artifacts of each frame while ensuring temporal coherency. Moreover, contrasting the representation of the current frame and the hidden knowledge makes it possible to infer the scratch position in an unsupervised manner, and such defect localization generalizes well to real-world degradations. To better resolve mixed degradation and compensate for the flow estimation error during frame alignment, we propose to leverage more expressive transformer blocks for spatial restoration. Experiments on both synthetic dataset and real-world old films demonstrate the significant superiority of the proposed RTN over existing solutions. In addition, the same framework can effectively propagate the color from keyframes to the whole video, ultimately yielding compelling restored films. The implementation and model will be released at https://github.com/raywzy/Bringing-Old-Films-Back-to-Life.

We present CLIP-NeRF, a multi-modal 3D object manipulation method for neural radiance fields (NeRF). By leveraging the joint language-image embedding space of the recent Contrastive Language-Image Pre-Training (CLIP) model, we propose a unified framework that allows manip-ulating NeRF in a user-friendly way, using either a short text prompt or an exemplar image. Specifically, to combine the novel view synthesis capability of NeRF and the controllable manipulation ability of latent representations from generative models, we introduce a disentangled conditional NeRF architecture that allows individual control over both shape and appearance. This is achieved by performing the shape conditioning via applying a learned deformation field to the positional encoding and deferring color conditioning to the volumetric rendering stage. To bridge this disentangled latent representation to the CLIP embedding, we design two code mappers that take a CLIP embedding as input and update the latent codes to reflect the targeted editing. The mappers are trained with a CLIP-based matching loss to ensure the manipulation accuracy. Furthermore, we propose an inverse optimization method that accurately projects an input image to the latent codes for manipulation to enable editing on real images. We evaluate our approach by extensive experiments on a variety of text prompts and exemplar images and also provide an intuitive interface for interactive editing.

Hair editing is an interesting and challenging problem in computer vision and graphics. Many existing methods require well-drawn sketches or masks as conditional inputs for editing, however these interactions are neither straight-forward nor efficient. In order to free users from the tedious interaction process, this paper proposes a new hair editing interaction mode, which enables manipulating hair attributes individually or jointly based on the texts or reference images provided by users. For this purpose, we encode the image and text conditions in a shared embedding space and propose a unified hair editing framework by leveraging the powerful image text representation capability of the Contrastive Language-Image Pre-Training (CLIP) model. With the carefully designed network structures and loss functions, our framework can perform high-quality hair editing in a disentangled manner. Extensive experiments demonstrate the superiority of our approach in terms of manipulation accuracy, visual realism of editing results, and irrelevant attribute preservation.

We propose an approach to simulate and render realistic water animation from a single still input photograph. We first segment the water surface, estimate rendering parameters, and compute water reflection textures with a combination of neural networks and traditional optimization techniques. Then we propose an image-based screen space local reflection model to render the water surface overlaid on the input image and generate real-time water animation. Our approach creates realistic results with no user intervention for a wide variety of natural scenes containing large bodies of water with different lighting and water surface conditions. Since our method provides a 3D representation of the water surface, it naturally enables direct editing of water parameters and also supports interactive applications like adding synthetic objects to the scene.

We propose a Few-shot Dynamic Neural Radiance Field (FDNeRF), the first NeRF-based method capable of reconstruction and expression editing of 3D faces based on a small number of dynamic images. Unlike existing dynamic NeRFs that require dense images as input and can only be modeled for a single identity, our method enables face reconstruction across different persons with few-shot inputs. Compared to state-of-the-art few-shot NeRFs designed for modeling static scenes, the proposed FDNeRF accepts view-inconsistent dynamic inputs and supports arbitrary facial expression editing, i.e., producing faces with novel expressions beyond the input ones. To handle the inconsistencies between dynamic inputs, we introduce a well-designed conditional feature warping (CFW) module to perform expression conditioned warping in 2D feature space, which is also identity adaptive and 3D constrained. As a result, features of different expressions are transformed into the target ones. We then construct a radiance field based on these view-consistent features and use volumetric rendering to synthesize novel views of the modeled faces. Extensive experiments with quantitative and qualitative evaluation demonstrate that our method outperforms existing dynamic and few-shot NeRFs on both 3D face reconstruction and expression editing tasks. Code is available at https://fdnerf.github.io .

Spatially-adaptive normalization (SPADE) is remarkably successful recently in conditional semantic image synthesis in T. Park et al. 2019 which modulates the normalized activation with spatially-varying transformations learned from semantic layouts, to prevent the semantic information from being washed away. Despite its impressive performance, a more thorough understanding of the advantages inside the box is still highly demanded to help reduce the significant computation and parameter overhead introduced by this novel structure. In this paper, from a return-on-investment point of view, we conduct an in-depth analysis of the effectiveness of this spatially-adaptive normalization and observe that its modulation parameters benefit more from semantic-awareness rather than spatial-adaptiveness, especially for high-resolution input masks. Inspired by this observation, we propose class-adaptive normalization (CLADE), a lightweight but equally-effective variant that is only adaptive to semantic class. In order to further improve spatial-adaptiveness, we introduce intra-class positional map encoding calculated from semantic layouts to modulate the normalization parameters of CLADE and propose a truly spatially-adaptive variant of CLADE, namely CLADE-ICPE. Through extensive experiments on multiple challenging datasets, we demonstrate that the proposed CLADE can be generalized to different SPADE-based methods while achieving comparable generation quality compared to SPADE, but it is much more efficient with fewer extra parameters and lower computational cost. The code and pretrained models are available at https://github.com/tzt101/CLADE.git.

Despite the tremendous success, deep neural networks are exposed to serious IP infringement risks. Given a target deep model, if the attacker knows its full information, it can be easily stolen by fine-tuning. Even if only its output is accessible, a surrogate model can be trained through student-teacher learning by generating many input-output training pairs. Therefore, deep model IP protection is important and necessary. However, it is still seriously under-researched. In this work, we propose a new model watermarking framework for protecting deep networks trained for low-level computer vision or image processing tasks. Specifically, a special task-agnostic barrier is added after the target model, which embeds a unified and invisible watermark into its outputs. When the attacker trains one surrogate model by using the input-output pairs of the barrier target model, the hidden watermark will be learned and extracted afterwards. To enable watermarks from binary bits to high-resolution images, a deep invisible watermarking mechanism is designed. By jointly training the target model and watermark embedding, the extra barrier can even be absorbed into the target model. Through extensive experiments, we demonstrate the robustness of the proposed framework, which can resist attacks with different network structures and objective functions.

This paper studies the problem of StyleGAN inversion, which plays an essential role in enabling the pretrained StyleGAN to be used for real image editing tasks. The goal of StyleGAN inversion is to find the exact latent code of the given image in the latent space of StyleGAN. This problem has a high demand for quality and efficiency. Existing optimization-based methods can produce high-quality results, but the optimization often takes a long time. On the contrary, forward-based methods are usually faster but the quality of their results is inferior. In this paper, we present a new feed-forward network "E2Style" for StyleGAN inversion, with significant improvement in terms of efficiency and effectiveness. In our inversion network, we introduce: 1) a shallower backbone with multiple efficient heads across scales; 2) multi-layer identity loss and multi-layer face parsing loss to the loss function; and 3) multi-stage refinement. Combining these designs together forms an effective and efficient method that exploits all benefits of optimization-based and forward-based methods. Quantitative and qualitative results show that our E2Style performs better than existing forward-based methods and comparably to state-of-the-art optimization-based methods while maintaining the high efficiency as well as forward-based methods. Moreover, a number of real image editing applications demonstrate the efficacy of our E2Style. Our code is available at https://github.com/wty-ustc/e2style.

Recent research shows deep neural networks are vulnerable to different types of attacks, such as adversarial attacks, data poisoning attacks, and backdoor attacks. Among them, backdoor attacks are the most cunning and can occur in almost every stage of the deep learning pipeline. Backdoor attacks have attracted lots of interest from both academia and industry. However, most existing backdoor attack methods are visible or fragile to some effortless pre-processing such as common data transformations. To address these limitations, we propose a robust and invisible backdoor attack called "Poison Ink". Concretely, we first leverage the image structures as target poisoning areas and fill them with poison ink (information) to generate the trigger pattern. As the image structure can keep its semantic meaning during the data transformation, such a trigger pattern is inherently robust to data transformations. Then we leverage a deep injection network to embed such input-aware trigger pattern into the cover image to achieve stealthiness. Compared to existing popular backdoor attack methods, Poison Ink outperforms both in stealthiness and robustness. Through extensive experiments, we demonstrate that Poison Ink is not only general to different datasets and network architectures but also flexible for different attack scenarios. Besides, it also has very strong resistance against many state-of-the-art defense techniques.

Image-to-Image (I2I) translation is an emerging topic in academia, and it also has been applied in real-world industry for tasks like image synthesis, super-resolution, and colorization. Traditional I2I translation methods usually train data in two or more domains together. This requires lots of computation resources. The results are of lower quality, and contain more artifacts. The training process could be unstable when the data in different domains are not balanced, and modal collapse is more likely to happen. In this paper, we propose a new I2I translation method that generates a new model in the target domain via a series of model transformations on a pre-trained StyleGAN2 model in the source domain. After that, we develop an inversion method to achieve the conversion between an image and its latent vector. By feeding the latent vector into the generated model, we can perform I2I translation between the source domain and target domain. Both qualitative and quantitative evaluations were conducted to verify that the proposed method can achieve better performance in terms of image quality, diversity and semantic similarity to the input and reference images compared to state-of-the-art works.

Sketch-to-image (S2I) translation plays an important role in image synthesis and manipulation tasks, such as photo editing and colorization. Some specific S2I translations, including sketch-to-photo and sketch-to-painting, can be used as powerful tools in the art design industry. However, previous methods only support S2I translation with a single level of density, which gives less flexibility to users for controlling the input sketches. In this work, we propose the first multi-level density sketch-to-image translation framework, which allows the input sketch to cover a wide range from rough object outlines to microstructures. Moreover, to tackle the problem of noncontinuous representation of multi-level density input sketches, we project the density level into a continuous latent space, which can then be linearly controlled by a parameter. This allows users to conveniently control the densities of input sketches and the generation of images. Moreover, our method has been successfully verified on various datasets for different applications, including face editing, multi-modal sketch-to-photo translation, and anime colorization, providing coarse-to-fine levels of controls to these applications.

The facial caricature shows the distinct characteristics of a person via exaggerations of both shape and appearance. This paper presents a novel framework that automatically generates vivid facial caricatures by encoding personalized semantic information. To this end, we first design a part-based scheme for geometry warping, which composes local semantic deformation into a global warping field, equipped with sufficient warping freedom of different facial components. Second, under the scheme of Part-based Warping, we design a photo-to-caricature translation network called PbWarpGAN, and adopt several novel losses to capture the personalized characteristics of each input face and preserve its identity better. Third, based on PbWarpGAN, we develop a user-friendly interface by introducing an attention scheme on each facial component, allowing ordinary users to adjust the automatically generated caricature by PbWarpGAN according to their preference conveniently. Experimental results show that our PbWarpGAN is more effective in capturing personalized characteristics than counterparts, and provides an efficient tool for caricature designing application.

We propose the first unified framework UniColor to support colorization in multiple modalities, including both unconditional and conditional ones, such as stroke, exemplar, text, and even a mix of them. Rather than learning a separate model for each type of condition, we introduce a two-stage colorization framework for incorporating various conditions into a single model. In the first stage, multi-modal conditions are converted into a common representation of hint points. Particularly, we propose a novel CLIP-based method to convert the text to hint points. In the second stage, we propose a Transformer-based network composed of Chroma-VQGAN and Hybrid-Transformer to generate diverse and high-quality colorization results conditioned on hint points. Both qualitative and quantitative comparisons demonstrate that our method outperforms state-of-the-art methods in every control modality and further enables multi-modal colorization that was not feasible before. Moreover, we design an interactive interface showing the effectiveness of our unified framework in practical usage, including automatic colorization, hybrid-control colorization, local recolorization, and iterative color editing. Our code and models are available at https://luckyhzt.github.io/unicolor .

Implicit radiance functions emerged as a powerful scene representation for reconstructing and rendering photo-realistic views of a 3D scene. These representations, however, suffer from poor editability. On the other hand, explicit representations such as polygonal meshes allow easy editing but are not as suitable for reconstructing accurate details in dynamic human heads, such as fine facial features, hair, teeth, and eyes. In this work, we present Neural Parameterization (NeP), a hybrid representation that provides the advantages of both implicit and explicit methods. NeP is capable of photo-realistic rendering while allowing fine-grained editing of the scene geometry and appearance. We first disentangle the geometry and appearance by parameterizing the 3D geometry into 2D texture space. We enable geometric editability by introducing an explicit linear deformation blending layer. The deformation is controlled by a set of sparse key points, which can be explicitly and intuitively displaced to edit the geometry. For appearance, we develop a hybrid 2D texture consisting of an explicit texture map for easy editing and implicit view and time-dependent residuals to model temporal and view variations. We compare our method to several reconstruction and editing baselines. The results show that the NeP achieves almost the same level of rendering accuracy while maintaining high editability.

Multiple sketch datasets have been proposed to understand how people draw 3D objects. However, such datasets are often of small scale and cover a small set of objects or categories. In addition, these datasets contain freehand sketches mostly from expert users, making it difficult to compare the drawings by expert and novice users, while such comparisons are critical in informing more effective sketch-based interfaces for either user groups. These observations motivate us to analyze how differently people with and without adequate drawing skills sketch 3D objects. We invited 70 novice users and 38 expert users to sketch 136 3D objects, which were presented as 362 images rendered from multiple views. This leads to a new dataset of 3,620 freehand multi-view sketches, which are registered with their corresponding 3D objects under certain views. Our dataset is an order of magnitude larger than the existing datasets. We analyze the collected data at three levels, i.e., sketch-level, stroke-level, and pixel-level, under both spatial and temporal characteristics, and within and across groups of creators. We found that the drawings by professionals and novices show significant differences at stroke-level, both intrinsically and extrinsically. We demonstrate the usefulness of our dataset in two applications: (i) freehand-style sketch synthesis, and (ii) posing it as a potential benchmark for sketch-based 3D reconstruction. Our dataset and code are available at https://chufengxiao.github.io/DifferSketching/.

We propose a novel framework to produce cartoon videos by fetching the color information from two input keyframes while following the animated motion guided by a user sketch. The key idea of the proposed approach is to estimate the dense cross-domain correspondence between the sketch and cartoon video frames, and employ a blending module with occlusion estimation to synthesize the middle frame guided by the sketch. After that, the input frames and the synthetic frame equipped with established correspondence are fed into an arbitrary-time frame interpolation pipeline to generate and refine additional inbetween frames. Finally, a module to preserve temporal consistency is employed. Compared to common frame interpolation methods, our approach can address frames with relatively large motion and also has the flexibility to enable users to control the generated video sequences by editing the sketch guidance. By explicitly considering the correspondence between frames and the sketch, we can achieve higher quality results than other image synthesis methods. Our results show that our system generalizes well to different movie frames, achieving better results than existing solutions.

Invertible grayscale is a special kind of grayscale from which the original color can be recovered. Given an input color image, this seminal work tries to hide the color information into its grayscale counterpart while making it hard to recognize any anomalies. This powerful functionality is enabled by training a hiding sub-network and restoring sub-network in an end-to-end way. Despite its expressive results, two key limitations exist: 1) The restored color image often suffers from some noticeable visual artifacts in the smooth regions. 2) It is very sensitive to JPEG compression, i.e., the original color information cannot be well recovered once the intermediate grayscale image is compressed by JPEG. To overcome these two limitations, this article introduces adversarial training and JPEG simulator respectively. Specifically, two auxiliary adversarial networks are incorporated to make the intermediate grayscale images and final restored color images indistinguishable from normal grayscale and color images. And the JPEG simulator is utilized to simulate real JPEG compression during the online training so that the hiding and restoring sub-networks can automatically learn to be JPEG robust. Extensive experiments demonstrate that the proposed method is superior to the original invertible grayscale work both qualitatively and quantitatively while ensuring the JPEG robustness. We further show that the proposed framework can be applied under different types of grayscale constraints and achieve excellent results.

Point cloud upsampling is vital for the quality of the mesh in three-dimensional reconstruction. Recent research on point cloud upsampling has achieved great success due to the development of deep learning. However, the existing methods regard point cloud upsampling of different scale factors as independent tasks. Thus, the methods need to train a specific model for each scale factor, which is both inefficient and impractical for storage and computation in real applications. To address this limitation, in this article, we propose a novel method called "Meta-PU" to first support point cloud upsampling of arbitrary scale factors with a single model. In the Meta-PU method, besides the backbone network consisting of residual graph convolution (RGC) blocks, a meta-subnetwork is learned to adjust the weights of the RGC blocks dynamically, and a farthest sampling block is adopted to sample different numbers of points. Together, these two blocks enable our Meta-PU to continuously upsample the point cloud with arbitrary scale factors by using only a single model. In addition, the experiments reveal that training on multiple scales simultaneously is beneficial to each other. Thus, Meta-PU even outperforms the existing methods trained for a specific scale factor only.

Recoloring 3D models is a challenging task that often requires professional knowledge and tedious manual efforts. In this article, we present the first deep-learning framework for exemplar-based 3D model recolor, which can automatically transfer the colors from a reference image to the 3D model texture. Our framework consists of two modules to solve two major challenges in the 3D color transfer. First, we propose a new feed-forward Color Transfer Network to achieve high-quality semantic-level color transfer by finding dense semantic correspondences between images. Second, considering 3D model constraints such as UV mapping, we design a novel 3D Texture Optimization Module which can generate a seamless and coherent texture by combining color transferred results rendered in multiple views. Experiments show that our method performs robustly and generalizes well to various kinds of models.

User-intended visual content fills the hole regions of an input image in the image editing scenario. The coarse low- level inputs, which typically consist of sparse sketch lines and color dots, convey user intentions for content creation (i.e., free-form editing). While existing methods combine an input image and these low-level controls for CNN inputs, the corresponding feature representations are not sufficient to convey user intentions, leading to unfaithfully generated content. In this paper, we propose DeFLOCNet which relies on a deep encoder-decoder CNN to retain the guidance of these controls in the deep feature representations. In each skip-connection layer, we design a structure generation block. Instead of attaching low-level controls to an input image, we inject these controls directly into each structure generation block for sketch line refinement and color propagation in the CNN feature space. We then concatenate the modulated features with the original decoder features for structure generation. Meanwhile, DeFLOCNet involves another decoder branch for texture generation and detail enhancement. Both structures and textures are rendered in the decoder, leading to user-intended editing results. Experiments on benchmarks demonstrate that DeFLOCNet effectively transforms different user intentions to create visually pleasing content.

We propose PD-GAN, a probabilistic diverse GAN for image inpainting. Given an input image with arbitrary hole regions, PD-GAN produces multiple inpainting results with diverse and visually realistic content. Our PD-GAN is built upon a vanilla GAN which generates images based on random noise. During image generation, we modulate deep features of input random noise from coarse-to-fine by injecting an initially restored image and the hole regions in multiple scales. We argue that during hole filling, the pixels near the hole boundary should be more deterministic (i.e., with higher probability trusting the context and initially restored image to create natural inpainting boundary), while those pixels lie in the center of the hole should enjoy more degrees of freedom (i.e., more likely to depend on the random noise for enhancing diversity). To this end, we propose spatially probabilistic diversity normalization (SPDNorm) inside the modulation to model the probability of generating a pixel conditioned on the context information. SPDNorm dynamically balances the realism and diversity inside the hole region, making the generated content more diverse towards the hole center and resemble neighboring image content more towards the hole boundary. Meanwhile, we propose a perceptual diversity loss to further empower PD-GAN for diverse content generation. Experiments on benchmark datasets including CelebA-HQ, Places2 and Paris Street View indicate that PD-GAN is effective for diverse and visually realistic image restoration.

Semantic image synthesis, translating semantic layouts to photo-realistic images, is a one-to-many mapping problem. Though impressive progress has been recently made, diverse semantic synthesis that can efficiently produce semantic-level multimodal results, still remains a challenge. In this paper, we propose a novel diverse semantic image synthesis framework from the perspective of semantic class distributions, which naturally supports diverse generation at semantic or even instance level. We achieve this by modeling class-level conditional modulation parameters as continuous probability distributions instead of discrete values, and sampling per-instance modulation parameters through instance-adaptive stochastic sampling that is consistent across the network. Moreover, we propose prior noise remapping, through linear perturbation parameters encoded from paired references, to facilitate supervised training and exemplar-based instance style control at test time. Extensive experiments on multiple datasets show that our method can achieve superior diversity and comparable quality compared to state-of-the-art methods. Code will be available at https://github.com/tzt101/INADE.git

Image matting is a fundamental and challenging problem in computer vision and graphics. Most existing matting methods leverage a user-supplied trimap as an auxiliary input to produce good alpha matte. However, obtaining high-quality trimap itself is arduous, thus restricting the application of these methods. Recently, some trimap-free methods have emerged, however, the matting quality is still far behind the trimap-based methods. The main reason is that, without the trimap guidance in some cases, the target network is ambiguous about which is the foreground target. In fact, choosing the foreground is a subjective procedure and depends on the user’s intention. To this end, this paper proposes an improved deep image matting framework which is trimap-free and only needs several user click interactions to eliminate the ambiguity. Moreover, we introduce a new uncertainty estimation module that can predict which parts need polishing and a following local refinement module. Based on the computation budget, users can choose how many local parts to improve with the uncertainty guidance. Quantitative and qualitative results show that our method performs better than existing trimap-free methods and comparably to state-of-the-art trimap-based methods with minimal user effort.

Contaminants such as dust, dirt and moisture adhering to the camera lens can greatly affect the quality and clarity of the resulting image or video. In this paper, we propose a video restoration method to automatically remove these contaminants and produce a clean video. Our approach first seeks to detect attention maps that indicate the regions that need to be restored. In order to leverage the corresponding clean pixels from adjacent frames, we propose a flow completion module to hallucinate the flow of the background scene to the attention regions degraded by the contaminants. Guided by the attention maps and completed flows, we propose a recurrent technique to restore the input frame by fetching clean pixels from adjacent frames. Finally, a multi-frame processing stage is used to further process the entire video sequence in order to enforce temporal consistency. The entire network is trained on a synthetic dataset that approximates the physical lighting properties of contaminant artifacts. This new dataset and our novel framework lead to our method that is able to address different contaminants and outperforms competitive restoration approaches both qualitatively and quantitatively.

Image completion has made tremendous progress with convolutional neural networks (CNNs), because of their powerful texture modeling capacity. However, due to some inherent properties (e.g., local inductive prior, spatial-invariant kernels), CNNs do not perform well in understanding global structures or naturally support pluralistic completion. Recently, transformers demonstrate their power in modeling the long-term relationship and generating diverse results, but their computation complexity is quadratic to input length, thus hampering the application in processing high-resolution images. This paper brings the best of both worlds to pluralistic image completion: appearance prior reconstruction with transformer and texture replenishment with CNN. The former transformer recovers pluralistic coherent structures together with some coarse textures, while the latter CNN enhances the local texture details of coarse priors guided by the high-resolution masked images. The proposed method vastly outperforms state-of-the-art methods in terms of three aspects: 1) large performance boost on image fidelity even compared to deterministic completion methods; 2) better diversity and higher fidelity for pluralistic completion; 3) exceptional generalization ability on large masks and generic dataset, like ImageNet. Code and pre-trained models have been publicly released at https://github.com/raywzy/ICT.

Point cloud segmentation is a fundamental task in 3D. Despite recent progress on point cloud segmentation with the power of deep networks, current deep learning methods based on the clean label assumptions may fail with noisy labels. Yet, object class labels are often mislabeled in real-world point cloud datasets. In this work, we take the lead in solving this issue by proposing a novel Point Noise-Adaptive Learning (PNAL) framework. Compared to existing noise-robust methods on image tasks, our PNAL is noise-rate blind, to cope with the spatially variant noise rate problem specific to point clouds . Specifically, we propose a novel point-wise confidence selection to obtain reliable labels based on the historical predictions of each point. A novel cluster-wise label correction is proposed with a voting strategy to generate the best possible label taking the neighbor point correlations into consideration. We conduct extensive experiments to demonstrate the effectiveness of PNAL on both synthetic and real-world noisy datasets. In particular, even with 60% symmetric noisy labels, our proposed method produces much better results than its baseline counterpart without PNAL and is comparable to the ideal upper bound trained on a completely clean dataset. Moreover, we fully re-labeled the validation set of a popular but noisy real-world scene dataset ScanNetV2 to make it clean, for rigorous experiment and future research. Our code and data will be released.

Abstract Despite recent breakthroughs in deep learning methods for image lighting enhancement, they are inferior when applied to portraits because 3D facial information is ignored in their models. To address this, we present a novel deep learning framework for portrait lighting enhancement based on 3D facial guidance. Our framework consists of two stages. In the first stage, corrected lighting parameters are predicted by a network from the input bad lighting image, with the assistance of a 3D morphable model and a differentiable renderer. Given the predicted lighting parameter, the differentiable renderer renders a face image with corrected shading and texture, which serves as the 3D guidance for learning image lighting enhancement in the second stage. To better exploit the long‐range correlations between the input and the guidance, in the second stage, we design an image‐to‐image translation network with a novel transformer architecture, which automatically produces a lighting‐enhanced result. Experimental results on the FFHQ dataset and in‐the‐wild images show that the proposed method outperforms state‐of‐the‐art methods in terms of both quantitative metrics and visual quality.

Image style transfer is to re-render the content of one image with the style of another. Most existing methods couple content and style information in their network structures and hyper-parameters, and learn it as a black-box. For better understanding, this paper aims to provide a new explicit decoupled perspective. Specifically, we propose StyleBank, which is composed of multiple convolution filter banks and each filter bank explicitly represents one style. To transfer an image to a specific style, the corresponding filter bank is operated on the intermediate feature produced by a single auto-encoder. The StyleBank and the auto-encoder are jointly learnt in such a way that the auto-encoder does not encode any style information. This explicit representation also enables us to conduct incremental learning to add a new style and fuse styles at not only the image level, but also the region level. Our method is the first style transfer network that links back to traditional texton mapping methods, and provides new understanding on neural style transfer. We further apply this general filterbank learning idea to two different multi-parameter image processing tasks: edge-aware image smoothing and denoising. Experiments demonstrate that it can achieve comparable results to its single parameter setting counterparts.

Many image-to-image (I2I) translation problems are in nature of high diversity that a single input may have various counterparts. The multi-modal network that can build a many-to-many mapping between two visual domains has been proposed in prior works. However, most of them are guided by sampled noises. Some others encode the reference image into a latent vector, which would eliminate the semantic information of the reference image. In this work, we aim to provide a solution to control the output based on references semantically. Given a reference image and an input in another domain, we first perform semantic matching between the two visual content and generate an auxiliary image, which explicitly encourages the semantic characteristic to be preserved. A deep network then is used for I2I translation and the final outputs are expected to be semantically similar to both the input and the reference. However, few paired data can satisfy that dual-similarity in a supervised fashion, and so we build up a self-supervised framework in the training stage. We improve the quality and diversity of the outputs by employing non-local blocks and a multi-task architecture. We assess the proposed method through extensive qualitative and quantitative evaluations and also present comparisons with several state-of-the-art models.

When adding a photo onto a graphic design, professional graphic designers often adjust its colors based on some target colors obtained from the brand or product to make the entire design more memorable to audiences and establish a consistent brand identity. However, adjusting the colors of a photo in the context of a graphic design is a difficult task, with two major challenges: (1) Locality: The color is often adjusted locally to preserve the semantics and atmosphere of the original image; and (2) Naturalness: The modified region needs to be carefully chosen and recolored to obtain a semantically valid and visually natural result. To address these challenges, we propose a learning-based approach to photo color adjustment for graphic designs, which maps an input photo along with the target colors to a recolored result. Our method decomposes the color adjustment process into two successive stages: modifiable region selection and target color propagation. The first stage aims to solve the core, challenging problem of which local image region(s) should be adjusted, which requires not only a common sense of colors appearing in our visual world but also understanding of subtle visual design heuristics. To this end, we capitalize on both natural photos and graphic designs to train a region selection network, which detects the most likely regions to be adjusted to the target colors. The second stage trains a recoloring network to naturally propagate the target colors in the detected regions. Through extensive experiments and a user study, we demonstrate the effectiveness of our selective region-based photo recoloring framework.

Deep learning has achieved tremendous success in numerous industrial applications. As training a good model often needs massive high-quality data and computation resources, the learned models often have significant business values. However, these valuable deep models are exposed to a huge risk of infringements. For example, if the attacker has the full information of one target model including the network structure and weights, the model can be easily finetuned on new datasets. Even if the attacker can only access the output of the target model, he/she can still train another similar surrogate model by generating a large scale of input-output training pairs. How to protect the intellectual property of deep models is a very important but seriously under-researched problem. There are a few recent attempts at classification network protection only.In this paper, we propose the first model watermarking framework for protecting image processing models. To achieve this goal, we leverage the spatial invisible watermarking mechanism. Specifically, given a black-box target model, a unified and invisible watermark is hidden into its outputs, which can be regarded as a special task-agnostic barrier. In this way, when the attacker trains one surrogate model by using the input-output pairs of the target model, the hidden watermark will be learned and extracted afterward. To enable watermarks from binary bits to high-resolution images, both traditional and deep spatial invisible watermarking mechanism are considered. Experiments demonstrate the robustness of the proposed watermarking mechanism, which can resist surrogate models learned with different network structures and objective functions. Besides deep models, the proposed method is also easy to be extended to protect data and traditional image processing algorithms.

We propose to restore old photos that suffer from severe degradation through a deep learning approach. Unlike conventional restoration tasks that can be solved through supervised learning, the degradation in real photos is complex and the domain gap between synthetic images and real old photos makes the network fail to generalize. Therefore, we propose a novel triplet domain translation network by leveraging real photos along with massive synthetic image pairs. Specifically, we train two variational autoencoders (VAEs) to respectively transform old photos and clean photos into two latent spaces. And the translation between these two latent spaces is learned with synthetic paired data. This translation generalizes well to real photos because the domain gap is closed in the compact latent space. Besides, to address multiple degradations mixed in one old photo, we design a global branch with a partial nonlocal block targeting to the structured defects, such as scratches and dust spots, and a local branch targeting to the unstructured defects, such as noises and blurriness. Two branches are fused in the latent space, leading to improved capability to restore old photos from multiple defects. The proposed method outperforms state-of-the-art methods in terms of visual quality for old photos restoration.

Deep neural networks have made tremendous progress in 3D point-cloud recognition. Recent works have shown that these 3D recognition networks are also vulnerable to adversarial samples produced from various attack methods, including optimization-based 3D Carlini-Wagner attack, gradient-based iterative fast gradient method, and skeleton-detach based point-dropping. However, after a careful analysis, these methods are either extremely slow because of the optimization/iterative scheme, or not flexible to support targeted attack of a specific category. To overcome these shortcomings, this paper proposes a novel label guided adversarial network (LG-GAN) for real-time flexible targeted point cloud attack. To the best of our knowledge, this is the first generation based 3D point cloud attack method. By feeding the original point clouds and target attack label into LG-GAN, it can learn how to deform the point clouds to mislead the recognition network into the specific label only with a single forward pass. In detail, LG-GAN first leverages one multi-branch adversarial network to extract hierarchical features of the input point clouds, then incorporates the specified label information into multiple intermediate features using the label encoder. Finally, the encoded features will be fed into the coordinate reconstruction decoder to generate the target adversarial sample. By evaluating different point-cloud recognition models (e.g., PointNet, PointNet++ and DGCNN), we demonstrate that the proposed LG-GAN can support flexible targeted attack on the fly while guaranteeing good attack performance and higher efficiency simultaneously.

Recently, generative adversarial networks (GAN) have been widely used to solve image-to-image translation problems such as edges to photos, labels to scenes, and colorizing grayscale images. However, how to recover details of smoothed images is still unexplored. Naively training a GAN like pix2pix causes insufficiently perfect results due to the fact that we ignore two main characteristics including spatial variability and spatial correlation as for this problem. In this work, we propose DeSmoothGAN to utilize both characteristics specifically. The spatial variability indicates that the details of different areas of smoothed images are distinct and they are supposed to be recovered differently. Therefore, we propose to perform spatial feature-wise transformation to recover individual areas differently. The spatial correlation represents that the details of different areas are related to each other. Thus, we propose to apply full attention to consider the relations between them. The proposed method generates satisfying results on several real-world datasets. We have conducted quantitative experiments including smooth consistency and image similarity to demonstrate the effectiveness of DeSmoothGAN. Furthermore, ablation studies are performed to illustrate the usefulness of our proposed feature-wise transformation and full attention.

One-shot weight sharing methods have recently drawn great attention in neural architecture search due to high efficiency and competitive performance. However, weight sharing across models has an inherent deficiency, i.e., insufficient training of subnetworks in the hypernetwork. To alleviate this problem, we present a simple yet effective architecture distillation method. The central idea is that subnetworks can learn collaboratively and teach each other throughout the training process, aiming to boost the convergence of individual models. We introduce the concept of prioritized path, which refers to the architecture candidates exhibiting superior performance during training. Distilling knowledge from the prioritized paths is able to boost the training of subnetworks. Since the prioritized paths are changed on the fly depending on their performance and complexity, the final obtained paths are the cream of the crop. We directly select the most promising one from the prioritized paths as the final architecture, without using other complex search methods, such as reinforcement learning or evolution algorithms. The experiments on ImageNet verify such path distillation method can improve the convergence ratio and performance of the hypernetwork, as well as boosting the training of subnetworks. The discovered architectures achieve superior performance compared to the recent MobileNetV3 and EfficientNet families under aligned settings. Moreover, the experiments on object detection and more challenging search space show the generality and robustness of the proposed method. Code and models are available at \url{https://github.com/neurips-20/cream.git}.

Despite tremendous success in many application scenarios, deep learning faces serious intellectual property (IP) infringement threats. Considering the cost of designing and training a good model, infringements will significantly infringe the interests of the original model owner. Recently, many impressive works have emerged for deep model IP protection. However, they either are vulnerable to ambiguity attacks, or require changes in the target network structure by replacing its original normalization layers and hence cause significant performance drops. To this end, we propose a new passport-aware normalization formulation, which is generally applicable to most existing normalization layers and only needs to add another passport-aware branch for IP protection. This new branch is jointly trained with the target model but discarded in the inference stage. Therefore it causes no structure change in the target model. Only when the model IP is suspected to be stolen by someone, the private passport-aware branch is added back for ownership verification. Through extensive experiments, we verify its effectiveness in both image and 3D point recognition models. It is demonstrated to be robust not only to common attack techniques like fine-tuning and model compression, but also to ambiguity attacks. By further combining it with trigger-set based methods, both black-box and white-box verification can be achieved for enhanced security of deep learning models deployed in real systems.

Traditional image processing operators often provide some control parameters to tweak the final results. Recently, different convolutional neural networks have been used to approximate or improve these operators. However, in those methods, one single model can only handle one operator of a specific parameter value and does not support parameter tuning. In this paper, we propose a new plugin module, “Adaptive Filterbank Pyramid”, which can be inserted into a backbone network to support multiple operators and continuous parameter tuning. Our module explicitly represents one operator with one filterbank pyramid. To generate the results of a specific operator, the corresponding filterbank pyramid is convolved with the intermediate feature pyramid produced by the backbone network. The weights of the filterbank pyramid are directly regressed by another sub-network, which is jointly trained with the backbone network and adapted to the input parameter, thus enabling continuous parameter tuning. We applied the proposed module for a large variety of image processing tasks, including image smoothing, image denoising, image deblocking, image enhancement and neural style transfer. Experiments show that our method is generalized to different types of image processing tasks and different backbone network structures. Compared to the single-operator-single-parameter baseline, our method can produce comparable results but is significantly more efficient in both training and testing.

Despite the recent success of face image generation with GANs, conditional hair editing remains challenging due to the under-explored complexity of its geometry and appearance. In this paper, we present MichiGAN (Multi-Input-Conditioned Hair Image GAN), a novel conditional image generation method for interactive portrait hair manipulation. To provide user control over every major hair visual factor, we explicitly disentangle hair into four orthogonal attributes, including shape, structure, appearance, and background. For each of them, we design a corresponding condition module to represent, process, and convert user inputs, and modulate the image generation pipeline in ways that respect the natures of different visual attributes. All these condition modules are integrated with the backbone generator to form the final end-to-end network, which allows fully-conditioned hair generation from multiple user inputs. Upon it, we also build an interactive portrait hair editing system that enables straightforward manipulation of hair by projecting intuitive and high-level user inputs such as painted masks, guiding strokes, or reference photos to well-defined condition representations. Through extensive experiments and evaluations, we demonstrate the superiority of our method regarding both result quality and user controllability.

We propose the first general framework to automatically correct different types of geometric distortion in a single input image. Our proposed method employs convolutional neural networks (CNNs) trained by using a large synthetic distortion dataset to predict the displacement field between distorted images and corrected images. A model fitting method uses the CNN output to estimate the distortion parameters, achieving a more accurate prediction. The final corrected image is generated based on the predicted flow using an efficient, high-quality resampling method. Experimental results demonstrate that our algorithm outperforms traditional correction methods, and allows for interesting applications such as distortion transfer, distortion exaggeration, and co-occurring distortion correction.

This paper presents the first end-to-end network for exemplar-based video colorization. The main challenge is to achieve temporal consistency while remaining faithful to the reference style. To address this issue, we introduce a recurrent framework that unifies the semantic correspondence and color propagation steps. Both steps allow a provided reference image to guide the colorization of every frame, thus reducing accumulated propagation errors. Video frames are colorized in sequence based on the colorization history, and its coherency is further enforced by the temporal consistency loss. All of these components, learned end-to-end, help produce realistic videos with good temporal stability. Experiments show our result is superior to the state-of-the-art methods both quantitatively and qualitatively.

To recognize objects of the unseen classes, most existing Zero-Shot Learning (ZSL) methods first learn a compatible projection function between the common semantic space and the visual space based on the data of source seen classes, then directly apply it to the target unseen classes. However, in real scenarios, the data distribution between the source and target domain might not match well, thus causing the well-known domain shift problem. Based on the observation that visual features of test instances can be separated into different clusters, we propose a new visual structure constraint on class centers for transductive ZSL, to improve the generality of the projection function (\ie alleviate the above domain shift problem). Specifically, three different strategies (symmetric Chamfer-distance,Bipartite matching distance, and Wasserstein distance) are adopted to align the projected unseen semantic centers and visual cluster centers of test instances. We also propose a new training strategy to handle the real cases where many unrelated images exist in the test dataset, which is not considered in previous methods. Experiments on many widely used datasets demonstrate that the proposed visual structure constraint can bring substantial performance gain consistently and achieve state-of-the-art results.

Image dehazing aims to recover the uncorrupted content from a hazy image. Instead of leveraging traditional low-level or handcrafted image priors as the restoration constraints, e.g., dark channels and increased contrast, we propose an end-to-end gated context aggregation network to directly restore the final haze-free image. In this network, we adopt the latest smoothed dilation technique to help remove the gridding artifacts caused by the widely-used dilated convolution with negligible extra parameters, and leverage a gated sub-network to fuse the features from different levels. Extensive experiments demonstrate that our method can surpass previous state-of-the-art methods by a large margin both quantitatively and qualitatively. In addition, to demonstrate the generality of the proposed method, we further apply it to the image deraining task, which also achieves the state-of-the-art performance.

Abstract We present a new video‐based performance cloning technique. After training a deep generative network using a reference video capturing the appearance and dynamics of a target actor, we are able to generate videos where this actor reenacts other performances. All of the training data and the driving performances are provided as ordinary video segments, without motion capture or depth information. Our generative model is realized as a deep neural network with two branches, both of which train the same space‐time conditional generator, using shared weights. One branch, responsible for learning to generate the appearance of the target actor in various poses, uses paired training data, self‐generated from the reference video. The second branch uses unpaired data to improve generation of temporally coherent video renditions of unseen pose sequences. Through data augmentation, our network is able to synthesize images of the target actor in poses never captured by the reference video. We demonstrate a variety of promising results, where our method is able to generate temporally coherent videos, for challenging scenarios where the reference and driving videos consist of very different dance performances.

Abstract Recent neural style transfer frameworks have obtained astonishing visual quality and flexibility in Single‐style Transfer (SST), but little attention has been paid to Multi‐style Transfer (MST) which refers to simultaneously transferring multiple styles to the same image. Compared to SST, MST has the potential to create more diverse and visually pleasing stylization results. In this paper, we propose the first MST framework to automatically incorporate multiple styles into one result based on regional semantics. We first improve the existing SST backbone network by introducing a novel multi‐level feature fusion module and a patch attention module to achieve better semantic correspondences and preserve richer style details. For MST, we designed a conceptually simple yet effective region‐based style fusion module to insert into the backbone. It assigns corresponding styles to content regions based on semantic matching, and then seamlessly combines multiple styles together. Comprehensive evaluations demonstrate that our framework outperforms existing works of SST and MST.

With the continued proliferation of smart mobile devices, the Quick Response (QR) code has become one of the most-used types of two-dimensional code in the world. Aiming at beautifying the visual-unpleasant appearance of QR codes, existing works have developed a series of techniques. However, these works still leave much to be desired, such as personalization, artistry, and robustness. To address these issues, in this paper, we propose a novel type of aesthetic QR codes, Stylized aEsthEtic (SEE) QR code , and a three-stage approach to automatically produce such robust style-oriented codes. Specifically, in the first stage, we propose a method to generate an optimized baseline aesthetic QR code, which reduces the visual contrast between the noise-like black/white modules and the blended image. In the second stage, to obtain an art style QR code, we tailor an appropriate neural style transformation network to endow the baseline aesthetic QR code with artistic elements. In the third stage, we design a module-based robustness-optimization mechanism to ensure the performance robust by balancing two competing terms: visual quality and readability. Extensive experiments demonstrate that the SEE QR code has high quality in terms of both visual appearance and robustness and also offers a greater variety of personalized choices to users.

We propose a new algorithm for color transfer between images that have perceptually similar semantic structures. We aim to achieve a more accurate color transfer that leverages semantically meaningful dense correspondence between images. To accomplish this, our algorithm uses neural representations for matching. Additionally, the color transfer should be spatially variant and globally coherent. Therefore, our algorithm optimizes a local linear model for color transfer satisfying both local and global constraints. Our proposed approach jointly optimizes matching and color transfer, adopting a coarse-to-fine strategy. The proposed method can be successfully extended from one-to-one to one-to-many color transfer. The latter further addresses the problem of mismatching elements of the input image. We validate our proposed method by testing it on a large variety of image content.

We propose a novel learning method to rectify document images with various distortion types from a single input image. As opposed to previous learning-based methods, our approach seeks to first learn the distortion flow on input image patches rather than the entire image. We then present a robust technique to stitch the patch results into the rectified document by processing in the gradient domain. Furthermore, we propose a second network to correct the uneven illumination, further improving the readability and OCR accuracy. Due to the less complex distortion present on the smaller image patches, our patch-based approach followed by stitching and illumination correction can significantly improve the overall accuracy in both the synthetic and real datasets.

This paper presents the first attempt at stereoscopic neural style transfer, which responds to the emerging demand for 3D movies or AR/VR. We start with a careful examination of applying existing monocular style transfer methods to left and right views of stereoscopic images separately. This reveals that the original disparity consistency cannot be well preserved in the final stylization results, which causes 3D fatigue to the viewers. To address this issue, we incorporate a new disparity loss into the widely adopted style loss function by enforcing the bidirectional disparity constraint in non-occluded regions. For a practical realtime solution, we propose the first feed-forward network by jointly training a stylization sub-network and a disparity sub-network, and integrate them in a feature level middle domain. Our disparity sub-network is also the first end-to-end network for simultaneous bidirectional disparity and occlusion mask estimation. Finally, our network is effectively extended to stereoscopic videos, by considering both temporal coherence and disparity consistency. We will show that the proposed method clearly outperforms the baseline algorithms both quantitatively and qualitatively.

This paper introduces a novel method by reshuffling deep features (i.e., permuting the spacial locations of a feature map) of the style image for arbitrary style transfer. We theoretically prove that our new style loss based on reshuffle connects both global and local style losses respectively used by most parametric and non-parametric neural style transfer methods. This simple idea can effectively address the challenging issues in existing style transfer methods. On one hand, it can avoid distortions in local style patterns, and allow semantic-level transfer, compared with neural parametric methods. On the other hand, it can preserve globally similar appearance to the style image, and avoid wash-out artifacts, compared with neural non-parametric methods. Based on the proposed loss, we also present a progressive feature-domain optimization approach. The experiments show that our method is widely applicable to various styles, and produces better quality than existing methods.

Correspondence between images is a fundamental problem in computer vision, with a variety of graphics applications. This paper presents a novel method for sparse cross-domain correspondence. Our method is designed for pairs of images where the main objects of interest may belong to different semantic categories and differ drastically in shape and appearance, yet still contain semantically related or geometrically similar parts. Our approach operates on hierarchies of deep features, extracted from the input images by a pre-trained CNN. Specifically, starting from the coarsest layer in both hierarchies, we search for Neural Best Buddies (NBB): pairs of neurons that are mutual nearest neighbors. The key idea is then to percolate NBBs through the hierarchy, while narrowing down the search regions at each level and retaining only NBBs with significant activations. Furthermore, in order to overcome differences in appearance, each pair of search regions is transformed into a common appearance. We evaluate our method via a user study, in addition to comparisons with alternative correspondence approaches. The usefulness of our method is demonstrated using a variety of graphics applications, including cross-domain image alignment, creation of hybrid images, automatic image morphing, and more.

Facial caricature is an art form of drawing faces in an exaggerated way to convey humor or sarcasm. In this paper, we propose the first Generative Adversarial Network (GAN) for unpaired photo-to-caricature translation, which we call "CariGANs". It explicitly models geometric exaggeration and appearance stylization using two components: CariGeoGAN , which only models the geometry-to-geometry transformation from face photos to caricatures, and CariStyGAN , which transfers the style appearance from caricatures to face photos without any geometry deformation. In this way, a difficult cross-domain translation problem is decoupled into two easier tasks. The perceptual study shows that caricatures generated by our CariGANs are closer to the hand-drawn ones, and at the same time better persevere the identity, compared to state-of-the-art methods. Moreover, our CariGANs allow users to control the shape exaggeration degree and change the color/texture style by tuning the parameters or giving an example caricature.

We propose the first deep learning approach for exemplar-based local colorization. Given a reference color image, our convolutional neural network directly maps a grayscale image to an output colorized image. Rather than using hand-crafted rules as in traditional exemplar-based methods, our end-to-end colorization network learns how to select, propagate , and predict colors from the large-scale data. The approach performs robustly and generalizes well even when using reference images that are unrelated to the input grayscale image. More importantly, as opposed to other learning-based colorization methods, our network allows the user to achieve customizable results by simply feeding different references. In order to further reduce manual effort in selecting the references, the system automatically recommends references with our proposed image retrieval algorithm, which considers both semantic and luminance information. The colorization can be performed fully automatically by simply picking the top reference suggestion. Our approach is validated through a user study and favorable quantitative comparisons to the-state-of-the-art methods. Furthermore, our approach can be naturally extended to video colorization. Our code and models are freely available for public use.

We present the first technique to create wide-angle, high-resolution looping panoramic videos. Starting with a 2D grid of registered videos acquired on a robotic mount, we formulate a combinatorial optimization to determine for each output pixel the source video and looping parameters that jointly maximize spatiotemporal consistency. This optimization is accelerated by reducing the set of source labels using a graph-coloring scheme. We parallelize the computation and implement it out-of-core by partitioning the domain along low-importance paths. The merged panorama is assembled using gradient-domain blending and stored as a hierarchy of video tiles. Finally, an interactive viewer adaptively preloads these tiles for responsive browsing and allows the user to interactively edit and improve local regions. We demonstrate these techniques on gigapixel-sized looping panoramas.

We propose StyleBank, which is composed of multiple convolution filter banks and each filter bank explicitly represents one style, for neural image style transfer. To transfer an image to a specific style, the corresponding filter bank is operated on top of the intermediate feature embedding produced by a single auto-encoder. The StyleBank and the auto-encoder are jointly learnt, where the learning is conducted in such a way that the auto-encoder does not encode any style information thanks to the flexibility introduced by the explicit filter bank representation. It also enables us to conduct incremental learning to add a new image style by learning a new filter bank while holding the auto-encoder fixed. The explicit style representation along with the flexible network design enables us to fuse styles at not only the image level, but also the region level. Our method is the first style transfer network that links back to traditional texton mapping methods, and hence provides new understanding on neural style transfer. Our method is easy to train, runs in real-time, and produces results that qualitatively better or at least comparable to existing methods.

Training a feed-forward network for the fast neural style transfer of images has proven successful, but the naive extension of processing videos frame by frame is prone to producing flickering results. We propose the first end-to-end network for online video style transfer, which generates temporally coherent stylized video sequences in near realtime. Two key ideas include an efficient network by incorporating short-term coherence, and propagating short-term coherence to long-term, which ensures consistency over a longer period of time. Our network can incorporate different image stylization networks and clearly outperforms the per-frame baseline both qualitatively and quantitatively. Moreover, it can achieve visually comparable coherence to optimization-based video style transfer, but is three orders of magnitude faster.

We propose a new technique for visual attribute transfer across images that may have very different appearance but have perceptually similar semantic structure. By visual attribute transfer, we mean transfer of visual information (such as color, tone, texture, and style) from one image to another. For example, one image could be that of a painting or a sketch while the other is a photo of a real scene, and both depict the same type of scene. Our technique finds semantically-meaningful dense correspondences between two input images. To accomplish this, it adapts the notion of "image analogy" [Hertzmann et al. 2001] with features extracted from a Deep Convolutional Neutral Network for matching; we call our technique deep image analogy. A coarse-to-fine strategy is used to compute the nearest-neighbor field for generating the results. We validate the effectiveness of our proposed method in a variety of cases, including style/texture transfer, color/style swap, sketch/painting to photo, and time lapse.

When interpolating images, for instance in the context of morphing, there are myriad approaches for defining correspondence maps that align structurally similar elements. However, the actual interpolation usually involves simple functions for both geometric paths and color blending. In this paper we explore new types of controls for combining two images related by a correspondence map. Our insight is to apply recent edge-aware decomposition techniques, not just to the image content but to the map itself. Our framework establishes an intuitive low-dimensional parameter space for merging the shape and color from the two source images at both low and high frequencies. A gallery-based user interface enables interactive traversal of this rich space, to either define a morph path or synthesize new hybrid images. Extrapolation of the shape parameters achieves compelling effects. Finally we demonstrate an extension of the framework to videos.

Short looping videos concisely capture the dynamism of natural scenes. Creating seamless loops usually involves maximizing spatiotemporal consistency and applying Poisson blending. We take an end-to-end view of the problem and present new techniques that jointly improve loop quality while also significantly reducing processing time. A key idea is to relax the consistency constraints to anticipate the subsequent blending, thereby enabling looping of low-frequency content like moving clouds and changing illumination. We also analyze the input video to remove an undesired bias toward short loops. The quality gains are demonstrated visually and confirmed quantitatively using a new gradient-domain consistency metric. We improve system performance by classifying potentially loopable pixels, masking the 2D graph cut, pruning graph-cut labels based on dominant periods, and optimizing on a coarse grid while retaining finer detail. Together these techniques reduce computation times from tens of minutes to nearly real-time.

Abstract We explore creating smooth transitions between videos of different scenes. As in traditional image morphing, good spatial correspondence is crucial to prevent ghosting, especially at silhouettes. Video morphing presents added challenges. Because motions are often unsynchronized, temporal alignment is also necessary. Applying morphing to individual frames leads to discontinuities, so temporal coherence must be considered. Our approach is to optimize a full spatiotemporal mapping between the two videos. We reduce tedious interactions by letting the optimization derive the fine‐scale map given only sparse user‐specified constraints. For robustness, the optimization objective examines structural similarity of the video content. We demonstrate the approach on a variety of videos, obtaining results using few explicit correspondences.

The main challenge in achieving good image morphs is to create a map that aligns corresponding image elements. Our aim is to help automate this often tedious task. We compute the map by optimizing the compatibility of corresponding warped image neighborhoods using an adaptation of structural similarity. The optimization is regularized by a thin-plate spline and may be guided by a few user-drawn points. We parameterize the map over a halfway domain and show that this representation offers many benefits. The map is able to treat the image pair symmetrically, model simple occlusions continuously, span partially overlapping images, and define extrapolated correspondences. Moreover, it enables direct evaluation of the morph in a pixel shader without mesh rasterization. We improve the morphs by optimizing quadratic motion paths and by seamlessly extending content beyond the image boundaries. We parallelize the algorithm on a GPU to achieve a responsive interface and demonstrate challenging morphs obtained with little effort.

Abstract We present a scheme for the animation of ocean waves in a recognizable drawn animation cartoon style. This consists principally of two parts: the first part is the ocean surface generated by a procedural model which governs the dynamics of the ocean surface and rendered with stylized whitewater forms over the ocean wave crests; the second part is water effects caused by interactions between the ocean water and obstacle objects, such as waves crashing against obstacles‐like rocks or boats and forms surrounding objects, and those effects are simulated with different hierarchical models. The ocean surface can be used either alone or in conjunction with effects caused by the interactions according to the scene. With minimum user intervention, i.e., specification of a few parameters, our model is able to generate cartoon ocean wave animations using these procedural methods, as shown by examples given in the paper. Copyright © 2011 John Wiley & Sons, Ltd.

We propose a method for procedural modeling and animation of cartoon water effects such as water caustics, foamy wake, and longshore currents. In our method we emulate the visual abstraction of these cartoon effects by the use of Voronoi diagrams and the motion abstraction by designing relevant controlling mechanisms corresponding to each effect. Our system enables the creation of cartoon effects with minimal intervention from the animator. Through high-level initial specification, the effects are animated procedurally in the style of hand-drawn cartoons.

Abstract In this paper, we describe a method for modeling the interaction between objects and the cartoon water which does not involve physics simulations. Our method involves the definition of flow path lines in the presence of obstacles, modeling of different types of water forms, and combinations of them in space and time. There are several notable features with our method: easy setting with little user intervention, modeling of complex water forms that represent more energetic water behavior than has been encompassed by semi‐automatic means so far, and the adaptive change of animated water forms to the variation of obstacle object in number, size, and shape in the water path. A number of formulae for managing shape and time variance in these animations are given. We tested our method with both still and moving objects that have different shape and size in the water and relevant examples are given in the paper. Copyright © 2008 John Wiley & Sons, Ltd.