3D line mapping from multi-view RGB images provides a compact and structured visual representation of scenes. We study the problem from a physical and topological perspective: a 3D line most naturally emerges as the edge of a finite 3D planar patch. We present LiP-Map, a line-plane joint optimization framework that explicitly models learnable line and planar primitives. This coupling enables accurate and detailed 3D line mapping while maintaining strong efficiency (typically completing a reconstruction in 3 to 5 minutes per scene). LiP-Map pioneers the integration of planar topology into 3D line mapping, not by imposing pairwise coplanarity constraints but by explicitly constructing interactions between plane and line primitives, thus offering a principled route toward structured reconstruction in man-made environments. On more than 100 scenes from ScanNetV2, ScanNet++, Hypersim, 7Scenes, and Tanks&Temple, LiP-Map improves both accuracy and completeness over state-of-the-art methods. Beyond line mapping quality, LiP-Map significantly advances line-assisted visual localization, establishing strong performance on 7Scenes.

This paper studies the task of SatStreet-view synthesis, which aims to render photorealistic street-view panorama images and videos given a satellite image and specified camera positions or trajectories. Our approach involves learning a satellite image conditioned neural radiance field from paired images captured from both satellite and street viewpoints, which comes to be a challenging learning problem due to the sparse-view nature and the extremely large viewpoint changes between satellite and street-view images. We tackle the challenges based on a task-specific observation that street-view specific elements, including the sky and illumination effects, are only visible in street-view panoramas, and present a novel approach, Sat2Density++, to accomplish the goal of photo-realistic street-view panorama rendering by modeling these street-view specific elements in neural networks. In the experiments, our method is evaluated on both urban and suburban scene datasets, demonstrating that Sat2Density++ is capable of rendering photorealistic street-view panoramas that are consistent across multiple views and faithful to the satellite image.

Neural radiance fields, which represent a 3D scene as a color field and a density field, have demonstrated great progress in novel view synthesis yet are unfavorable for editing due to the implicitness. This work studies the task of efficient 3D editing, where we focus on editing speed and user interactivity. To this end, we propose to learn the color field as an explicit 2D appearance aggregation, also called canonical image, with which users can easily customize their 3D editing via 2D image processing. We complement the canonical image with a projection field that maps 3D points onto 2D pixels for texture query. This field is initialized with a pseudo canonical camera model and optimized with offset regularity to ensure the naturalness of the canonical image. Extensive experiments on different datasets suggest that our representation, dubbed AGAP, well supports various ways of 3D editing (e.g., stylization, instance segmentation, and interactive drawing). Our approach demonstrates remarkable efficiency by being at least 20× faster per edit compared to existing NeRF-based editing methods. Project page is available at h ttps: //felixcheng97.github.io/AGAP/.

Due to the difficulty in scaling up, generative adversarial networks (GANs) seem to be falling out of grace with the task of text-conditioned image synthesis. Sparsely activated mixture-of-experts (MoE) has recently been demonstrated as a valid solution to training large-scale models with limited resources. Inspired by this, we present Aurora, a GAN-based text-to-image generator that employs a collection of experts to learn feature processing, together with a sparse router to adaptively select the most suitable expert for each feature point. We adopt a two-stage training strategy, which first learns a base model at 64 × 64 resolution followed by an upsampler to produce 512 × 512 images. Trained with only public data, our approach encouragingly closes the performance gap between GANs and industry-level diffusion models, maintaining a fast inference speed. We release the code and checkpoints here to facilitate the community for further development.

This paper studies the problem of Line Segment Detection (LSD) for the characterization of line geometry in images, with the aim of learning a domain-agnostic robust LSD model that works well for any natural images. With the focus of scalable self-supervised learning of LSD, we revisit and streamline the fundamental designs of (deep and non-deep) LSD approaches to have a high-performing and efficient LSD learner, dubbed as ScaleLSD, for the curation of line geometry at scale from over 10M unlabeled real-world images. Our ScaleLSD works very well to detect much more number of line segments from any natural images even than the pioneered non-deep LSD approach, having a more complete and accurate geometric characterization of images using line segments. Experimentally, our proposed ScaleLSD is comprehensively testified under zero-shot protocols in detection performance, single-view 3D geometry estimation, two-view line segment matching, and multiview 3D line mapping, all with excellent performance obtained. Based on the thorough evaluation, our ScaleLSD is observed to be the first deep approach that outperforms the pioneered non-deep LSD in all aspects we have tested, significantly expanding and reinforcing the versatility of the line geometry of images.

This work focuses on open-domain 4D avatarization, with the purpose of creating a 4D avatar from a portrait image in an arbitrary style. We select parametric triplanes as the intermediate 4D representation, and propose a practical training paradigm that takes advantage of both generative adversarial networks (GANs) and diffusion models. Our design stems from the observation that 4D GANs excel at bridging images and triplanes without supervision yet usually face challenges in handling diverse data distributions. A robust 2D diffusion prior emerges as the solution, assisting the GAN in transferring its expertise across various domains. The synergy between these experts permits the construction of a multi-domain image-triplane dataset, which drives the development of a general 4D avatar creator. Extensive experiments suggest that our model, termed AvatarArtist, is capable of producing high-quality 4D avatars with strong robustness to various source image domains. The code, the data, and the models will be made publicly available to facilitate future studies.

Derived from diffusion models, MangaNinja specializes in the task of reference-guided line art colorization. We incorporate two thoughtful designs to ensure precise character detail transcription, including a patch shuffling module to facilitate correspondence learning between the reference color image and the target line art, and a point-driven control scheme to enable fine-grained color matching. Experiments on a self-collected benchmark demonstrate the superiority of our model over current solutions in terms of precise colorization. We further showcase the potential of the proposed interactive point control in handling challenging cases (e.g., extreme poses and shadows), cross-character colorization, multi-reference harmonization, etc., beyond the reach of existing algorithms. Our code and model could be found here.

As a highly practical application, image editing encounters a variety of user demands and thus prioritizes excellent ease of use. In this paper, we unveil MagicQuill, an integrated image editing system designed to support users in swiftly actualizing their creativity. Our system starts with a streamlined yet functionally robust interface, enabling users to articulate their ideas (e.g., inserting elements, erasing objects, altering color, etc.) with just a few strokes. These interactions are then monitored by a multimodal large language model (MLLM) to anticipate user intentions in real time, bypassing the need for prompt entry. Finally, we apply the powerful diffusion prior, enhanced by a carefully learned two-branch plug-in module, to process the editing request with precise control. Please visit the ${\text{project page}}$ to try out our system.

Generating detailed captions comprehending text-rich visual content in images has received growing attention for Large Vision-Language Models (LVLMs). However, few studies have developed benchmarks specifically tailored for detailed captions to measure their accuracy and comprehensiveness. In this paper, we introduce a detailed caption benchmark, termed as CompreCap, to evaluate the visual context from a directed scene graph view. Concretely, we first manually segment the image into semantically meaningful regions (i.e., semantic segmentation mask) according to common-object vocabulary, while also distinguishing attributes of objects within all those regions. Then directional relation labels of these objects are annotated to compose a directed scene graph that can well encode rich compositional information of the image. Based on our directed scene graph, we develop a pipeline to assess the generated detailed captions from LVLMs on multiple levels, including the object-level coverage, the accuracy of attribute descriptions, the score of key relationships, etc. Experimental results on the CompreCap dataset confirm that our evaluation method aligns closely with human evaluation scores across LVLMs. We have released the code and the dataset here to support the community.

Although text-to-image (T2I) models have recently thrived as visual generative priors, their reliance on high-quality text-image pairs makes scaling up expensive. We argue that grasping the cross-modality alignment is not a necessity for a sound visual generative prior, whose focus should be on texture modeling. Such a philosophy inspires us to study image-to-image (I2I) generation, where models can learn from in-the-wild images in a self-supervised manner. We first develop a pure vision-based training framework, Lumos, and confirm the feasibility and the scalability of learning I2I models. We then find that, as an upstream task of T2I, our I2I model serves as a more foundational visual prior and achieves on-par or better performance than existing T2I models using only 1/10 text-image pairs for fine-tuning. We further demonstrate the superiority of I2I priors over T2I priors on some text-irrelevant visual generative tasks, like image-to-3D and image-to-video.

The production of 2D animation follows an industry-standard workflow, encompassing four essential stages: character design, keyframe animation, in-betweening, and coloring. Our research focuses on reducing the labor costs in the above process by harnessing the potential of increasingly powerful generative AI. Using video diffusion models as the foundation, AniDoc1emerges as a video line art colorization tool, which automatically converts sketch sequences into colored animations following the reference character specification. Our model exploits correspondence matching as an explicit guidance, yielding strong robustness to the variations (e.g., posture) between the reference character and each line art frame. In addition, our model could even automate the in-betweening process, such that users can easily create a temporally consistent animation by simply providing a character image as well as the start and end sketches. Our code is available at: https://yihaomeng.github.io/AniDocdemo.

This work addresses the challenge of streamed video depth estimation, which expects not only per-frame accuracy but, more importantly, cross-frame consistency. We argue that sharing contextual information between frames or clips is pivotal in fostering temporal consistency. Therefore, we reformulate depth prediction into a conditional generation problem to provide contextual information within a clip and across clips. Specifically, we propose a consistent context-aware training and inference strategy for arbitrarily long videos to provide cross-clip context. We sample independent noise levels for each frame within a clip during training while using a sliding window strategy and initializing overlapping frames with previously predicted frames without adding noise. Moreover, we design an effective training strategy to provide context within a clip. Extensive experimental results validate our design choices and demonstrate the superiority of our approach, dubbed ChronoDepth. Project page: xdimlab.github.io/ChronoDepth.

Text serves as the key control signal in video generation due to its narrative nature. To render text descriptions into video clips, current video diffusion models borrow features from text encoders yet struggle with limited text comprehension. The recent success of large language models (LLMs) showcases the power of decoder-only transformers, which offers three clear benefits for text-to-video (T2V) generation, namely, precise text understanding resulting from the superior scalability, imagination beyond the input text enabled by next token prediction, and flexibility to prioritize user interests through instruction tuning. Nevertheless, the feature distribution gap emerging from the two different text modeling paradigms hinders the direct use of LLMs in established T2V models. This work addresses this challenge with Mimir, an end-to-end training framework featuring a carefully tailored token fuser to harmonize the outputs from text encoders and LLMs. Such a design allows the T2V model to fully leverage learned video priors while capitalizing on the text-related capability of LLMs. Extensive quantitative and qualitative results demonstrate the effectiveness of Mimir in generating high-quality videos with excellent text comprehension, especially when processing short captions and managing shifting motions. Project page: https://lucaria-academy.github.io/Mimir/

This paper presents PlanarSplatting, an ultra-fast and accurate surface reconstruction approach for multi-view indoor images. We take the 3D planes as the main objective due to their compactness and structural expressiveness in indoor scenes, and develop an explicit optimization framework that learns to fit the expected surface of indoor scenes by splatting the 3D planes into 2.5D depth and normal maps. As our PlanarSplatting operates directly on the 3D plane primitives, it eliminates the dependencies on 2D/3D plane detection and plane matching/tracking for planar surface reconstruction. Furthermore, with the essential merits of plane-based representation coupled with CUDA-based implementation of planar splatting functions, Planar-Splatting reconstructs an indoor scene in 3 minutes while having significantly better geometric accuracy. Thanks to our ultra-fast reconstruction speed, the largest quantitative evaluation on the ScanNet and ScanNet++ datasets over hundreds of scenes clearly demonstrated the advantages of our method. We believe that our accurate and ultrafast planar surface reconstruction method will be applied in the structured data curation for surface reconstruction in the future. The code of our CUDA implementation will be publicly available.

The intuitive nature of drag-based interaction has led to its growing adoption for controlling object trajectories in image-to-video synthesis. Still, existing methods that perform dragging in the 2D space usually face ambiguity when handling out-of-plane movements. In this work, we augment the interaction with a new dimension, i.e., the depth dimension, such that users are allowed to assign a relative depth for each point on the trajectory. That way, our new interaction paradigm not only inherits the convenience from 2D dragging, but facilitates trajectory control in the 3D space, broadening the scope of creativity. We propose a pioneering method for 3D trajectory control in image-to-video synthesis by abstracting object masks into a few cluster points. These points, accompanied by the depth information and the instance information, are finally fed into a video diffusion model as the control signal. Extensive experiments validate the effectiveness of our approach, dubbed LeviTor, in precisely manipulating the object movements when producing photo-realistic videos from static images. Our code is available at: https://github.com/ant-research/LeviTor.

The Audio Description (AD) task aims to generate descriptions of visual elements for visually impaired individuals to help them access long-form video content, like movies. With video feature, text, character bank and context information as inputs, the generated ADs are able to correspond to the characters by name and provide reasonable, contextual descriptions to help audience understand the storyline of movie. To achieve this goal, we propose to leverage pre-trained foundation models through a simple and unified framework to generate ADs with interleaved multimodal sequence as input, termed as Uni-AD. To enhance the alignment of features across various modalities with finer granularity, we introduce a simple and lightweight module that maps video features into the textual feature space. Moreover, we also propose a character-refinement module to provide more precise information by identifying the main characters who play more significant roles in the video context. With these unique designs, we further incorporate contextual information and a contrastive loss into our architecture to generate smoother and more contextually appropriate ADs. Experiments on multiple AD datasets show that Uni-AD performs well on AD generation, which demonstrates the effectiveness of our approach. Our code is available at: https://github.com/ant-research/UniAD.

Classifier-Free Guidance (CFG), which combines the conditional and unconditional score functions with two coefficients summing to one, serves as a practical technique for diffusion model sampling. Theoretically, however, denoising with CFG cannot be expressed as a reciprocal diffusion process, which may consequently leave some hidden risks during use. In this work, we revisit the theory behind CFG and rigorously confirm that the improper configuration of the combination coefficients (i.e., the widely used summing-to-one version) brings about expectation shift of the generative distribution. To rectify this issue, we propose ReCFG1with a relaxation on the guidance coefficients such that denoising with ReCFG strictly aligns with the diffusion theory. We further show that our approach enjoys a closed-form solution given the guidance strength. That way, the rectified coefficients can be readily pre-computed via traversing the observed data, leaving the sampling speed barely affected. Empirical evidence on real-world data demonstrate the compatibility of our post-hoc design with existing state-of-the-art diffusion models, including both class-conditioned ones (e.g., EDM2 on ImageNet) and text-conditioned ones (e.g., SD3 on CC12M), without any retraining. Code is available at https://github.com/thuxmf/recfg.

Reconstructing complex reflections in real-world scenes from 2D images is essential for achieving photorealistic novel view synthesis. Existing methods that utilize environment maps to model reflections from distant lighting often struggle with high-frequency reflection details and fail to account for near-field reflections. In this work, we introduce EnvGS, a novel approach that employs a set of Gaussian primitives as an explicit 3D representation for capturing reflections of environments. These environment Gaussian primitives are incorporated with base Gaussian primitives to model the appearance of the whole scene. To efficiently render these environment Gaussian primitives, we developed a ray-tracing-based renderer that leverages the GPU’s RT core for fast rendering. This allows us to jointly optimize our model for high-quality reconstruction while maintaining real-time rendering speeds. Results from multiple real-world and synthetic datasets demonstrate that our method produces significantly more detailed reflections, achieving the best rendering quality in real-time novel view synthesis. The code is available at https://zju3dv.github.io/envgs.

In this work, we introduce Prometheus, a 3D-aware latent diffusion model for text-to-3D generation at both object and scene levels in seconds. We formulate 3D scene generation as multi-view, feed-forward, pixel-aligned 3D Gaussian generation within the latent diffusion paradigm. To ensure generalizability, we build our model upon pretrained text-to-image generation model with only minimal adjustments, and further train it using a large number of images from both single-view and multi-view datasets. Furthermore, we introduce an RGB-D latent space into 3D Gaussian generation to disentangle appearance and geometry information, enabling efficient feed-forward generation of 3D Gaussians with better fidelity and geometry. Extensive experimental results demonstrate the effectiveness of our method in both feed-forward 3D Gaussian reconstruction and text-to-3D generation. Project page: Prometheus.

We present FLARE, a feed-forward model designed to infer high-quality camera poses and 3D geometry from uncalibrated sparse-view images (i.e., as few as 2-8 inputs), which is a challenging yet practical setting in real-world applications. Our solution features a cascaded learning paradigm with camera pose serving as the critical bridge, recognizing its essential role in mapping 3D structures onto 2D image planes. Concretely, FLARE starts with camera pose estimation, whose results condition the subsequent learning of geometric structure and appearance, optimized through the objectives of geometry reconstruction and novel-view synthesis. Utilizing large-scale public datasets for training, our method delivers state-of-the-art performance in the tasks of pose estimation, geometry reconstruction, and novel view synthesis, while maintaining the inference efficiency (i.e., less than 0.5 seconds). The project page and code can be found at: https://zhanghe3z.github.io/FLARE/

As a verified need, consistent editing across in-the-wild images remains a technical challenge arising from various unmanageable factors, like object poses, lighting conditions, and photography environments. Edicho steps in with a training-free solution based on diffusion models, featuring a fundamental design principle of using explicit image correspondence to direct editing. Specifically, the key components include an attention manipulation module and a carefully refined classifier-free guidance (CFG) denoising strategy, both of which take into account the pre-estimated correspondence. Such an inference-time algorithm enjoys a plug-and-play nature and is compatible to most diffusion-based editing methods, such as ControlNet and BrushNet. Extensive results demonstrate the efficacy of Edicho in consistent cross-image editing under diverse settings. We will release the code to facilitate future studies.

This paper addresses the challenge of high-fidelity view synthesis of humans with sparse-view videos as input. Previous methods solve the issue of insufficient observation by leveraging 4D diffusion models to generate videos at novel viewpoints. However, the generated videos from these models often lack spatio-temporal consistency, thus degrading view synthesis quality. In this paper, we propose a novel sliding iterative denoising process to enhance the spatio-temporal consistency of the 4D diffusion model. Specifically, we define a latent grid in which each latent encodes the image, camera pose, and human pose for a certain viewpoint and timestamp, then alternately denoising the latent grid along spatial and temporal dimensions with a sliding window, and finally decode the videos at target viewpoints from the corresponding denoised latents. Through the iterative sliding, information flows sufficiently across the latent grid, allowing the diffusion model to obtain a large receptive field and thus enhance the 4D consistency of the output, while making the GPU memory consumption affordable. The experiments on the DNA-Rendering and ActorsHQ datasets demonstrate that our method is able to synthesize high-quality and consistent novel-view videos and significantly outperforms the existing approaches. See our project page for interactive demos and video results: https://diffuman4d.github.io/ .

In spite of recent progress, image diffusion models still produce artifacts. A common solution is to leverage the feedback provided by quality assessment systems or human annotators to optimize the model, where images are generally rated in their entirety. In this work, we believe problem-solving starts with identification, yielding the request that the model should be aware of not just the presence of defects in an image, but their specific locations. Motivated by this, we propose DiffDoctor, a two-stage pipeline to assist image diffusion models in generating fewer artifacts. Concretely, the first stage targets developing a robust artifact detector, for which we collect a dataset of over 1M flawed synthesized images and set up an efficient human-in-the-loop annotation process, incorporating a carefully designed class-balance strategy. The learned artifact detector is then involved in the second stage to optimize the diffusion model by providing pixel-level feedback. Extensive experiments on text-to-image diffusion models demonstrate the effectiveness of our artifact detector as well as the soundness of our diagnose-then-treat design.

We propose Framer for interactive frame interpolation, which targets producing smoothly transitioning frames between two images as per user creativity. Concretely, besides taking the start and end frames as inputs, our approach supports customizing the transition process by tailoring the trajectory of some selected keypoints. Such a design enjoys two clear benefits. First, incorporating human interaction mitigates the issue arising from numerous possibilities of transforming one image to another, and in turn enables finer control of local motions. Second, as the most basic form of interaction, keypoints help establish the correspondence across frames, enhancing the model to handle challenging cases (e.g., objects on the start and end frames are of different shapes and styles). It is noteworthy that our system also offers an "autopilot" mode, where we introduce a module to estimate the keypoints and refine the trajectory automatically, to simplify the usage in practice. Extensive experimental results demonstrate the appealing performance of Framer on various applications, such as image morphing, time-lapse video generation, cartoon interpolation, etc. The code, model, and interface are publicly accessible at https://github.com/aim-uofa/Framer.

This paper addresses the task of generating two-character online interactions. Previously, two main settings existed for two-character interaction generation: (1) generating one's motions based on the counterpart's complete motion sequence, and (2) jointly generating two-character motions based on specific conditions. We argue that these settings fail to model the process of real-life two-character interactions, where humans will react to their counterparts in real time and act as independent individuals. In contrast, we propose an online reaction policy, called Ready-to-React, to generate the next character pose based on past observed motions. Each character has its own reaction policy as its ``brain'', enabling them to interact like real humans in a streaming manner. Our policy is implemented by incorporating a diffusion head into an auto-regressive model, which can dynamically respond to the counterpart's motions while effectively mitigating the error accumulation throughout the generation process. We conduct comprehensive experiments using the challenging boxing task. Experimental results demonstrate that our method outperforms existing baselines and can generate extended motion sequences. Additionally, we show that our approach can be controlled by sparse signals, making it well-suited for VR and other online interactive environments. Code and data will be made publicly available.

Shape restoration aims to recover intact 3D shapes from defective ones, such as those that are incomplete, noisy, and low-resolution. Previous works have achieved impressive results in shape restoration subtasks thanks to advanced generative models. While effective for specific shape defects, they are less applicable in real-world scenarios involving multiple defect types simultaneously. Additionally, training on limited subsets of defective shapes hinders knowledge transfer across restoration types and thus affects generalization. In this paper, we address the task of general shape restoration, which restores shapes with various types of defects through a unified model, thereby naturally improving the applicability and scalability. Our approach first standardizes the data representation across different restoration subtasks using high-resolution TSDF grids and constructs a large-scale dataset with diverse types of shape defects. Next, we design an efficient hierarchical shape generation model and a noise-robust defective shape encoder that enables effective impaired shape understanding and intact shape generation. Moreover, we propose a scalable training strategy for efficient model training. The capabilities of our proposed method are demonstrated across multiple shape restoration subtasks and validated on various datasets, including Objaverse, ShapeNet, GSO, and ABO.

Visual-inertial odometry (VIO) has made significant progress in various applications. However, one of the key challenges in VIO is the efficient and robust fusion of visual and inertial measurements, particularly while mitigating the impact of sensor failures. To address this challenge, we propose a new learning-based VIO system, i.e., DW-VIO, which is able to integrate multiple sensors and provide robust state estimations. To this end, we design a novel deep learning-based data-fusion approach that dynamically associates information from multiple sensors to predict sensor weights for optimization. Moreover, in order to improve the efficiency, we present several real-time optimization techniques including a fast patch graph constructor and an efficient GPU-accelerated multi-factor bundle adjustment layer. Experimental results show that DW-VIO outperforms most state-of-the-art (SOTA) methods on the EuRoC MAV, ETH3D-SLAM, and KITTI-360 benchmarks across various challenging sequences. Additionally, it maintains a minimum of 20 frames per second (FPS) on a single RTX 3060 GPU with high-resolution input, highlighting its efficiency.

Effectively utilizing multi-sensory data is important for robots to generalize across diverse tasks. However, the heterogeneous nature of these modalities makes fusion challenging. Existing methods propose strategies to obtain comprehensively fused features but often ignore the fact that each modality requires different levels of attention at different manipulation stages. To address this, we propose a force-guided attention fusion module that adaptively adjusts the weights of visual and tactile features without human labeling. We also introduce a self-supervised future force prediction auxiliary task to reinforce the tactile modality, improve data imbalance, and encourage proper adjustment. Our method achieves an average success rate of 93% across three fine-grained, contact-rich tasks in real-world experiments. Further analysis shows that our policy appropriately adjusts attention to each modality at different manipulation stages. The videos can be viewed at https://adaptac-dex.github.io/.

This paper addresses metric 3D reconstruction of indoor scenes by exploiting their inherent geometric regularities with compact representations. Using planar 3D primitives -- a well-suited representation for man-made environments -- we introduce PLANA3R, a pose-free framework for metric $\underline{Plana}$r $\underline{3}$D $\underline{R}$econstruction from unposed two-view images. Our approach employs Vision Transformers to extract a set of sparse planar primitives, estimate relative camera poses, and supervise geometry learning via planar splatting, where gradients are propagated through high-resolution rendered depth and normal maps of primitives. Unlike prior feedforward methods that require 3D plane annotations during training, PLANA3R learns planar 3D structures without explicit plane supervision, enabling scalable training on large-scale stereo datasets using only depth and normal annotations. We validate PLANA3R on multiple indoor-scene datasets with metric supervision and demonstrate strong generalization to out-of-domain indoor environments across diverse tasks under metric evaluation protocols, including 3D surface reconstruction, depth estimation, and relative pose estimation. Furthermore, by formulating with planar 3D representation, our method emerges with the ability for accurate plane segmentation. The project page is available at: \url{https://lck666666.github.io/plana3r/}.

Humans intuitively perceive object shape and orientation from a single image, guided by strong priors about canonical poses. However, existing 3D generative models often produce misaligned results due to inconsistent training data, limiting their usability in downstream tasks. To address this gap, we introduce the task of orientation-aligned 3D object generation: producing 3D objects from single images with consistent orientations across categories. To facilitate this, we construct Objaverse-OA, a dataset of 14,832 orientation-aligned 3D models spanning 1,008 categories. Leveraging Objaverse-OA, we fine-tune two representative 3D generative models based on multi-view diffusion and 3D variational autoencoder frameworks to produce aligned objects that generalize well to unseen objects across various categories. Experimental results demonstrate the superiority of our method over post-hoc alignment approaches. Furthermore, we showcase downstream applications enabled by our aligned object generation, including zero-shot object orientation estimation via analysis-by-synthesis and efficient arrow-based object rotation manipulation.

In 3D object reconstruction from photographs, estimating material properties is challenging. We propose an inverse rendering method that uses active area lighting: as this provides a wider range of lighting angles per photo than point lighting, material reconstruction can be more accurate for the same number of photos. We compare area light shading with point lighting. With either mesh or 3D Gaussian splatting pipelines, area lighting can improve BRDF reconstruction and leads to +3 dB relighting PSNR over point lights, or need only \(\nicefrac {1}{5}\) of the input photos for the same quality. We also compare area light shading with Monte Carlo ray tracing and with differential linearly transformed cosines (LTC) plus shadow visibility weighting. LTC can be faster, improving optimization times by 25%. In SOTA method-level comparisons, our approach improves material reconstruction, particularly for material roughness, leading to superior relighting quality.

Recently neural implicit rendering techniques have evolved rapidly and demonstrated significant advantages in novel view synthesis and 3D scene reconstruction. However, existing neural rendering methods for editing purposes offer limited functionalities, e.g., rigid transformation and category-specific editing. In this paper, we present a novel mesh-based representation by encoding the neural radiance field with disentangled geometry, texture, and semantic codes on mesh vertices, which empowers a set of efficient and comprehensive editing functionalities, including mesh-guided geometry editing, designated texture editing with texture swapping, filling and painting operations, and semantic-guided editing. To this end, we develop several techniques including a novel local space parameterization to enhance rendering quality and training stability, a learnable modification color on vertex to improve the fidelity of texture editing, a spatial-aware optimization strategy to realize precise texture editing, and a semantic-aided region selection to ease the laborious annotation of implicit field editing. Extensive experiments and editing examples on both real and synthetic datasets demonstrate the superiority of our method on representation quality and editing ability.

This work presents AnyDoor, a diffusion-based image generator with the power to teleport target objects to new scenes at user-specified locations with desired shapes. Instead of tuning parameters for each object, our model is trained only once and effortlessly generalizes to diverse object-scene combinations at the inference stage. Such a challenging zero-shot setting requires an adequate characterization of a certain object. To this end, we leverage the powerful self-supervised image encoder (i.e., DINOv2) to extract the discriminative dentity feature of the target object. Besides, we complement the identity feature with detail features, which are carefully designed to maintain appearance details yet allow versatile local variations (e.g., lighting, orientation, posture, etc.), supporting the object in favorably blending with different surroundings. We further propose to borrow knowledge from video datasets, where we can observe various forms (i.e., along the time axis) of a single object, leading to stronger model generalizability and robustness. Starting from the task of object insertion, we further extend the framework of AnyDoor to a general solution with region-to-region image reference. With the different definitions of the source region and target region, the tasks of object insertion, object removal, and image variation could be integrated into one model without introducing extra parameters. In addition, we investigate incorporating other conditions like the mask, pose skeleton, and depth map as additional guidance to achieve more controllable generation.

Online free-view navigation in volumetric videos requires high-quality rendering and real-time streaming in order to provide immersive user experiences. However, existing methods ( e.g. , dynamic NeRF and 3DGS) may not handle dynamic scenes with complex motions, and their models may not be streamable due to storage and bandwidth constraints. In this paper, we propose a novel 4D Gaussian Video (4DGV) approach that enables the creation and streaming of photorealistic, volumetric videos for dynamic scenes over the Internet. The core of our 4DGV is a novel streamable group of Gaussians (GOG) representation based on motion layering. Each GOG consists of static and dynamic points obtained via lifting 2D segmentation into 3D in motion layering, where the deformation of each dynamic point is represented as the temporal offset of its attributes. We also adaptively convert static points back to dynamic points to handle the appearance change, (e.g. , moving shadows and reflections), of static objects through optimization. To support real-time streaming of 4DGVs, we show that by applying quantization on Gaussian attributes and H.265 encoding on deformation offsets, our GOG representation can be significantly compressed (to around 6% of the original model size) without sacrificing the accuracy (PSNR loss less than 0.01dB). Extensive experiments on standard benchmarks demonstrate that our method outperforms state-of-the-art volumetric video approaches, with superior rendering quality and minimum storage overheads.

Generating photorealistic videos of digital humans in a controllable manner is crucial for a plethora of applications. Existing approaches either build on methods that employ template-based 3D representations or emerging video generation models but suffer from poor quality or limited consistency and identity preservation when generating individual or multiple digital humans. In this paper, we introduce a new interspatial attention (ISA) mechanism as a scalable building block for modern diffusion transformer (DiT)-based video generation models. ISA is a new type of cross attention that uses relative positional encodings tailored for the generation of human videos. Leveraging a custom-developed video variation autoencoder, we train a latent ISA-based diffusion model on a large corpus of video data. Our model achieves state-of-the-art performance for 4D human video synthesis, demonstrating remarkable motion consistency and identity preservation while providing precise control of the camera and body poses. Our code and model are publicly released at https://dsaurus.github.io/isa4d/.

This paper studies the problem of structured 3D reconstruction using wireframes that consist of line segments and junctions, focusing on the computation of structured boundary geometries of scenes. Instead of leveraging matching-based solutions from 2D wireframes (or line segments) for 3D wireframe reconstruction as done in prior arts, we present NEAT, a rendering-distilling formulation using neural fields to represent 3D line segments with 2D observations, and bipartite matching for perceiving and distilling of a sparse set of 3D global junctions. The proposed NEAT enjoys the joint optimization of the neural fields and the global junctions from scratch, using view-dependent 2D observations without precomputed cross-view feature matching. Comprehensive experiments on the DTU and BlendedMVS datasets demonstrate our NEAT's superiority over state-of-the-art alternatives for 3D wireframe reconstruction. Moreover, the distilled 3D global junctions by NEAT, are a better initialization than SfM points, for the recently-emerged 3D Gaussian Splatting for high-fidelity novel view synthesis using about 20 times fewer initial 3D points. Project page: https://xuenan.net/neat.

This paper targets high-fidelity and real-time view synthe-sis of dynamic 3D scenes at 4K resolution. Recent methods on dynamic view synthesis have shown impressive rendering quality. However, their speed is still limited when rendering high-resolution images. To overcome this problem, we propose 4K4D, a 4D point cloud representation that supports hardware rasterization and network pre-computation to enable unprecedented rendering speed with a high rendering quality. Our representation is built on a 4D feature grid so that the points are naturally regularized and can be robustly optimized. In addition, we design a novel hybrid appearance model that significantly boosts the rendering quality while preserving efficiency. Moreover, we develop a differentiable depth peeling algorithm to effectively learn the proposed model from RGB videos. Experiments show that our representation can be rendered at over 400 FPS on the DNA-Rendering dataset at 1080p resolution and 80 FPS on the ENeRF-Outdoor dataset at 4K resolution using an RTX 4090 GPU, which is 30× faster than previous methods and achieves the state-of-the-art rendering quality. Our project page is available at https://ziu3dv.github.io/4k4d.

This work presents AnyDoor, a diffusion-based image generator with the power to teleport target objects to new scenes at user-specified locations with desired shapes. Instead of tuning parameters for each object, our model is trained only once and effortlessly generalizes to diverse object-scene combinations at the inference stage. Such a challenging zero-shot setting requires an adequate characterization of a certain object. To this end, we complement the commonly used identity feature with detail features, which are carefully designed to maintain appearance details yet allow versatile local variations (e.g., lighting, orientation, posture, etc.), supporting the object in favorably blending with different surroundings. We further propose to borrow knowledge from video datasets, where we can observe various forms (i.e., along the time axis) of a single object, leading to stronger model generalizability and robustness. Extensive experiments demonstrate the superiority of our approach over existing alternatives as well as its great potential in real-world applications, such as virtual try-on, shape editing, and object swapping. Code is released at github.com/ali-vilab/AnyDoor.

Existing text-to-image (T2I) diffusion models usually struggle in interpreting complex prompts, especially those with quantity, object-attribute binding, and multi-subject descriptions. In this work, we introduce a semantic panel as the middleware in decoding texts to images, supporting the generator to better follow instructions. The panel is obtained through arranging the visual concepts parsed from the input text by the aid of large language models, and then injected into the denoising network as a detailed control signal to complement the text condition. To facilitate text-to-panel learning, we come up with a carefully designed semantic formatting protocol, accompanied by a fully-automatic data preparation pipeline. Thanks to such a design, our approach, which we call Ranni, manages to enhance a pre-trained T2I generator regarding its textual controllability. More importantly, the introduction of the generative middleware brings a more convenient form of interaction (i.e., directly adjusting the elements in the panel or using language instructions) and further allows users to finely customize their generation, based on which we develop a practical system and showcase its potential in continuous generation and chatting-based editing.

We present the content deformation field (CoDeF) as a new type of video representation, which consists of a canonical content field aggregating the static contents in the entire video and a temporal deformation field recording the transformations from the canonical image (i.e., rendered from the canonical content field) to each individual frame along the time axis. Given a target video, these two fields are jointly optimized to reconstruct it through a carefully tailored rendering pipeline. We advisedly introduce some regularizations into the optimization process, urging the canonical content field to inherit semantics (e.g., the object shape) from the video. With such a design, CoDeF naturally supports lifting image algorithms for video processing, in the sense that one can apply an image algorithm to the canonical image and effortlessly propagate the outcomes to the entire video with the aid of the temporal deformation field. We experimentally show that CoDeF is able to lift image-to-image translation to video-to-video translation and lift keypoint detection to keypoint tracking without any training. More importantly, thanks to our lifting strategy that deploys the algorithms on only one image, we achieve superior cross-frame consistency in processed videos compared to existing video-to-video translation approaches, and even manage to track non-rigid objects like water and smog. Code is made available at https: / /qiuyu96. github.io/CoDeF/

Diffusion-based text-to-video generation has witnessed impressive progress in the past year yet still falls behind text-to-image generation. One of the key reasons is the limited scale of publicly available data (e.g., 10M video-text pairs in WebVid10m vs. 5B image-text pairs in LAION), considering the high cost of video captioning. Instead, it could be far easier to collect unlabeled clips from video platforms like YouTube. Motivated by this, we come up with a novel text-to-video generation framework, termed TF-T2V, which can directly learn with text-free videos. The rationale behind is to separate the process of text decoding from that of temporal modeling. To this end, we employ a content branch and a motion branch, which are jointly optimized with weights shared. Following such a pipeline, we study the effect of doubling the scale of training set (i.e., video-only WebVid10M) with some randomly collected text-free videos and are encouraged to observe the performance improvement (FID from 9.67 to 8.19 and FVD from 484 to 441), demonstrating the scalability of our approach. We also find that our model could enjoy sustainable performance gain (FID from 8.19 to 7.64 and FVD from 441 to 366) after reintroducing some text labels for training. Finally, we validate the effectiveness and generalizability of our ideology on both native text-to-video generation and compositional video synthesis paradigms. Code and models will be publicly available at here.

A diffusion model, which is formulated to produce an image using thousands of denoising steps, usually suffers from a slow inference speed. Existing acceleration algorithms simplify the sampling by skipping most steps yet exhibit considerable performance degradation. By viewing the generation of diffusion models as a discretized integral process, we argue that the quality drop is partly caused by applying an inaccurate integral direction to a timestep interval. To rectify this issue, we propose a timestep tuner that helps find a more accurate integral direction for a particular interval at the minimum cost. Specifically, at each denoising step, we replace the original parameterization by conditioning the network on a new timestep, enforcing the sampling distribution towards the real one. Extensive experiments show that our plug-in design can be trained efficiently and boost the inference performance of various state-of-the-art acceleration methods, especially when there are few denoising steps. For example, when using 10 denoising steps on LSUN Bedroom dataset, we improve the FID of DDIM from 9.65 to 6.07, simply by adopting our method for a more appropriate set of timesteps. Code is available at https://github.com/THU-LYJ-Lab/time-tuner.

Recovering dense and long-range pixel motion in videos is a challenging problem. Part of the difficulty arises from the 3D-to-2D projection process, leading to occlusions and discontinuities in the 2D motion domain. While 2D motion can be intricate, we posit that the underlying 3D motion can often be simple and low-dimensional. In this work, we propose to estimate point trajectories in 3D space to mitigate the issues caused by image projection. Our method, named SpatialTracker, lifts 2D pixels to 3D using monocular depth estimators, represents the 3D content of each frame efficiently using a triplane representation, and performs iterative updates using a transformer to estimate 3D trajectories. Tracking in 3D allows us to leverage asrigid-as-possible (ARAP) constraints while simultaneously learning a rigidity embedding that clusters pixels into different rigid parts. Extensive evaluation shows that our approach achieves state-of-the-art tracking performance both qualitatively and quantitatively, particularly in challenging scenarios such as out-of-plane rotation. And our project page is available at https://henry123-boy.github.io/SpaTracker/.

Generating large-scale 3D scenes cannot simply apply existing 3D object synthesis technique since 3D scenes usually hold complex spatial configurations and consist of a number of objects at varying scales. We thus propose a practical and efficient 3D representation that incorporates an equivariant radiance field with the guidance of a bird's-eye view (BEV) map. Concretely, objects of synthesized 3D scenes could be easily manipulated through steering the corresponding BEV maps. Moreover, by adequately incorporating positional encoding and low-pass filters into the generator, the representation becomes equivariant to the given BEV map. Such equivariance allows us to produce large-scale, even infinite-scale, 3D scenes via synthesizing local scenes and then stitching them with smooth consistency. Extensive experiments on 3D scene datasets demonstrate the effectiveness of our approach. Our project web-site is at: https://zqh0253.github.io/BerfScene/.

Diffusion models, which employ stochastic differential equations to sample images through integrals, have emerged as a dominant class of generative models. However, the rationality of the diffusion process itself receives limited attention, leaving the question of whether the problem is well-posed and well-conditioned. In this paper, we uncover a vexing propensity of diffusion models: they frequently exhibit the infinite Lipschitz near the zero point of timesteps. We provide theoretical proofs to illustrate the presence of infinite Lipschitz constants and empirical results to confirm it. The Lipschitz singularities pose a threat to the stability and accuracy during both the training and inference processes of diffusion models. Therefore, the mitigation of Lipschitz singularities holds great potential for enhancing the performance of diffusion models. To address this challenge, we propose a novel approach, dubbed E-TSDM, which alleviates the Lipschitz singularities of the diffusion model near the zero point. Remarkably, our technique yields a substantial improvement in performance. Moreover, as a byproduct of our method, we achieve a dramatic reduction in the Fréchet Inception Distance of acceleration methods relying on network Lipschitz, including DDIM and DPM-Solver, by over 33\%. Extensive experiments on diverse datasets validate our theory and method. Our work may advance the understanding of the general diffusion process, and also provide insights for the design of diffusion models.

Consistency Models (CMs) have showed a promise in creating high-quality images with few steps. However, the way to add new conditional controls to the pre-trained CMs has not been explored. In this paper, we explore the pivotal subject of leveraging the generative capacity and efficiency of consistency models to facilitate controllable visual content creation via ControlNet. First, it is observed that ControlNet trained for diffusion models (DMs) can be directly applied to CMs for high-level semantic controls but sacrifice image low-level details and realism. To tackle with this issue, we develop a CMs-tailored training strategy for ControlNet using the consistency training. It is substantiated that ControlNet can be successfully established through the consistency training technique. Besides, a unified adapter can be trained utilizing the consistency training, which enhances the adaptation of DM’s ControlNet. We quantitatively and qualitatively evaluate all strategies across various conditional controls, including sketch, hed, canny, depth, human pose, low-resolution image and masked image, with the pre-trained text-to-image latent consistency models.

Generative adversarial networks (GANs) usually struggle in learning from highly diverse data, whose underlying manifold is complex. In this work, we revisit the mathematical foundations of GANs, and theoretically reveal that the native adversarial loss for GAN training is insufficient to fix the problem of $\textit{subsets with positive Lebesgue measure of the generated data manifold lying out of the real data manifold}$. Instead, we find that score matching serves as a promising solution to this issue thanks to its capability of persistently pushing the generated data points towards the real data manifold. We thereby propose to improve the optimization of GANs with score matching regularity (SMaRt). Regarding the empirical evidences, we first design a toy example to show that training GANs by the aid of a ground-truth score function can help reproduce the real data distribution more accurately, and then confirm that our approach can consistently boost the synthesis performance of various state-of-the-art GANs on real-world datasets with pre-trained diffusion models acting as the approximate score function. For instance, when training Aurora on the ImageNet $64\times64$ dataset, we manage to improve FID from 8.87 to 7.11, on par with the performance of one-step consistency model. Code is available at https://github.com/thuxmf/SMaRt.

Image editing serves as a practical yet challenging task considering the diverse demands from users, where one of the hardest parts is to precisely describe how the edited image should look like. In this work, we present a new form of editing, termed imitative editing, to help users exercise their creativity more conveniently. Concretely, to edit an image region of interest, users are free to directly draw inspiration from some in-the-wild references (e.g., some relative pictures come across online), without having to cope with the fit between the reference and the source. Such a design requires the system to automatically figure out what to expect from the reference to perform the editing. For this purpose, we propose a generative training framework, dubbed MimicBrush, which randomly selects two frames from a video clip, masks some regions of one frame, and learns to recover the masked regions using the information from the other frame. That way, our model, developed from a diffusion prior, is able to capture the semantic correspondence between separate images in a self-supervised manner. We experimentally show the effectiveness of our method under various test cases as well as its superiority over existing alternatives. We also construct a benchmark to facilitate further research.

This work presents a unified knowledge protocol, called UKnow, which facilitates knowledge-based studies from the perspective of data. Particularly focusing on visual and linguistic modalities, we categorize data knowledge into five unit types, namely, in-image, in-text, cross-image, cross-text, and image-text, and set up an efficient pipeline to help construct the multimodal knowledge graph from any data collection. Thanks to the logical information naturally contained in knowledge graph, organizing datasets under UKnow format opens up more possibilities of data usage compared to the commonly used image-text pairs. Following UKnow protocol, we collect, from public international news, a large-scale multimodal knowledge graph dataset that consists of 1,388,568 nodes (with 571,791 vision-related ones) and 3,673,817 triplets. The dataset is also annotated with rich event tags, including 11 coarse labels and 9,185 fine labels. Experiments on four benchmarks demonstrate the potential of UKnow in supporting common-sense reasoning and boosting vision-language pre-training with a single dataset, benefiting from its unified form of knowledge organization. Code, dataset, and models will be made publicly available. See Appendix to download the dataset.

In this work, we empirically confirm that the key reason causing such an issue is that the training images are usually paired with short captions, leaving certain tokens easily overshadowed by salient tokens. Towards this problem, our initial attempt is to relabel the data with long captions, however, directly learning with which may lead to performance degradation in understanding short text (e.g., in the image classification task). Then, after incorporating corner tokens to aggregate diverse textual information, we manage to help the model catch up to its original level of short text understanding yet greatly enhance its capability of long text understanding. We further look into whether the model can continuously benefit from longer captions and notice a clear trade-off between the performance and the efficiency. Finally, we validate the effectiveness of our approach using a self-constructed large-scale dataset, which consists of 100M long caption oriented text-image pairs. Our method achieves superior performance in long-text-image retrieval tasks. The project page is available at https://wuw2019.github.io/lot-lip.

Generative models make huge progress to the photorealistic image synthesis in recent years. To enable humans to steer the image generation process and customize the output, many works explore the interpretable dimensions of the latent space in GANs. Existing methods edit the attributes of the output image such as orientation or color scheme by varying the latent code along certain directions. However, these methods usually require additional human annotations for each pretrained model, and they mostly focus on editing global attributes. In this work, we propose a self-supervised approach to improve the spatial steerability of GANs without searching for steerable directions in the latent space or requiring extra annotations. Specifically, we design randomly sampled Gaussian heatmaps to be encoded into the intermediate layers of generative models as spatial inductive bias. Along with training the GAN model from scratch, these heatmaps are aligned with the emerging attention of the GAN's discriminator in a self-supervised learning manner. During inference, users can interact with the spatial heatmaps in an intuitive manner, enabling them to edit the output image by adjusting the scene layout, moving, or removing objects. Moreover, we incorporate DragGAN into our framework, which facilitates fine-grained manipulation within a reasonable time and supports a coarse-to-fine editing process. Extensive experiments show that the proposed method not only enables spatial editing over human faces, animal faces, outdoor scenes, and complicated multi-object indoor scenes but also brings improvement in synthesis quality.

Generative Adversarial Networks (GANs) have significantly advanced image synthesis through mapping randomly sampled latent codes to high-fidelity synthesized images. However, applying well-trained GANs to real image editing remains challenging. A common solution is to find an approximate latent code that can adequately recover the input image to edit, which is also known as GAN inversion. To invert a GAN model, prior works typically focus on reconstructing the target image at the pixel level, yet few studies are conducted on whether the inverted result can well support manipulation at the semantic level. This work fills in this gap by proposing in-domain GAN inversion, which consists of a domain-guided encoder and a domain-regularized optimizer, to regularize the inverted code in the native latent space of the pre-trained GAN model. In this way, we manage to sufficiently reuse the knowledge learned by GANs for image reconstruction, facilitating a wide range of editing applications without any retraining. We further make comprehensive analyses on the effects of the encoder structure, the starting inversion point, as well as the inversion parameter space, and observe the trade-off between the reconstruction quality and the editing property. Such a trade-off sheds light on how a GAN model represents an image with various semantics encoded in the learned latent distribution.

Generative adversarial network (GAN) is formulated as a two-player game between a generator (G) and a discriminator (D), where D is asked to differentiate whether an image comes from real data or is produced by G. Under such a formulation, D plays as the rule maker and hence tends to dominate the competition. Towards a fairer game in GANs, we propose a new paradigm for adversarial training, which makes G assign a task to D as well. Specifically, given an image, we expect D to extract representative features that can be adequately decoded by G to reconstruct the input. That way, instead of learning freely, D is urged to align with the view of G for domain classification. Experimental results on various datasets demonstrate the substantial superiority of our approach over the baselines. For instance, we improve the FID of StyleGAN2 from 4.30 to 2.55 on LSUN Bedroom and from 4.04 to 2.82 on LSUN Church. We believe that the pioneering attempt present in this work could inspire the community with better designed generator-leading tasks for GAN improvement. Project page is at https://ezioby.github.io/glead/.

This work presents two astonishing findings on neural networks learned for large-scale image classification. 1) Given a well-trained model, the logits predicted for some category can be directly obtained by linearly combining the predictions of a few other categories, which we call neural dependency. 2) Neural dependencies exist not only within a single model, but even between two independently learned models, regardless of their architectures. Towards a theoretical analysis of such phenomena, we demonstrate that identifying neural dependencies is equivalent to solving the Covariance Lasso (CovLasso) regression problem proposed in this paper. Through investigating the properties of the problem solution, we confirm that neural dependency is guaranteed by a redundant logit covariance matrix, which condition is easily met given massive categories, and that neural dependency is highly sparse, implying that one category correlates to only a few others. We further empirically show the potential of neural dependencies in understanding internal data correlations, generalizing models to unseen categories, and improving model robustness with a dependency-derived regularizer. Code to reproduce the results in this paper is available at https://github.com/RuiLiFengiNeural-Dependencies.

Existing methods for 3D-aware image synthesis largely depend on the 3D pose distribution pre-estimated on the training set. An inaccurate estimation may mislead the model into learning faulty geometry. This work proposes PoF3D that frees generative radiance fields from the requirements of 3D pose priors. We first equip the generator with an efficient pose learner, which is able to infer a pose from a latent code, to approximate the underlying true pose distribution automatically. We then assign the discriminator a task to learn pose distribution under the supervision of the generator and to differentiate real and synthesized images with the predicted pose as the condition. The pose-free generator and the pose-aware discriminator are jointly trained in an adversarial manner. Extensive results on a couple of datasets confirm that the performance of our approach, regarding both image quality and geometry quality, is on par with state of the art. To our best knowledge, PoF3D demonstrates the feasibility of learning high-quality 3D-aware image synthesis without using 3D pose priors for the first time. Project page can be found here.

Semantic segmentation usually suffers from a long-tail data distribution. Due to the imbalanced number of samples across categories, the features of those tail classes may get squeezed into a narrow area in the feature space. Towards a balanced feature distribution, we introduce category-wise variation into the network predictions in the training phase such that an instance is no longer projected to a feature point, but a small region instead. Such a perturbation is highly dependent on the category scale, which appears as assigning smaller variation to head classes and larger variation to tail classes. In this way, we manage to close the gap between the feature areas of different categories, resulting in a more balanced representation. It is note-worthy that the introduced variation is discarded at the inference stage to facilitate a confident prediction. Although with an embarrassingly simple implementation, our method manifests itself in strong generalizability to various datasets and task settings. Extensive experiments suggest that our plug-in design lends itself well to a range of state-of-the-art approaches and boosts the performance on top of them.11Code: https://github.com/grantword8/BLV.

Generating a talking face video from the input audio sequence is a practical yet challenging task. Most existing methods either fail to capture fine facial details or need to train a specific model for each identity. We argue that a codebook pre-learned on high-quality face images can serve as a useful prior that facilitates high-fidelity and generalizable talking head synthesis. Thanks to the strong capability of the codebook in representing face textures, we simplify the talking face generation task as finding proper lip-codes to characterize the variation of lips during portrait talking. To this end, we propose LipFormer, a Transformer-based framework to model the audio-visual coherence and predict the lip-codes sequence based on input audio features. We further introduce an adaptive face warping module, which helps warp the reference face to the target pose in the feature space, to alleviate the difficulty of lip-code prediction under different poses. By this means, LipFormer can make better use of prelearned priors in images and is robust to posture change. Extensive experiments show that LipFormer can produce more realistic talking face videos compared to previous methods and faithfully generalize to unseen identities.

Existing 3D-aware image synthesis approaches mainly focus on generating a single canonical object and show limited capacity in composing a complex scene containing a variety of objects. This work presents DisCoScene: a 3D-aware generative model for high-quality and controllable scene synthesis. The key ingredient of our method is a very abstract object-level representation (i.e., 3D bounding boxes without semantic annotation) as the scene layout prior, which is simple to obtain, general to describe various scene contents, and yet informative to disentangle objects and background. Moreover, it serves as an intuitive user control for scene editing. Based on such a prior, the proposed model spatially disentangles the whole scene into object-centric generative radiance fields by learning on only 2D images with the global-local discrimination. Our model obtains the generation fidelity and editing flexibility of individual objects while being able to efficiently compose objects and the background into a complete scene. We demonstrate state-of-the-art performance on many scene datasets, including the challenging Waymo outdoor dataset. Project page can be found here.

Diffusion models, which learn to reverse a signal destruction process to generate new data, typically require the signal at each step to have the same dimension. We argue that, considering the spatial redundancy in image signals, there is no need to maintain a high dimensionality in the evolution process, especially in the early generation phase. To this end, we make a theoretical generalization of the forward diffusion process via signal decomposition. Concretely, we manage to decompose an image into multiple orthogonal components and control the attenuation of each component when perturbing the image. That way, along with the noise strength increasing, we are able to diminish those inconsequential components and thus use a lower-dimensional signal to represent the source, barely losing information. Such a reformulation allows to vary dimensions in both training and inference of diffusion models. Extensive experiments on a range of datasets suggest that our approach substantially reduces the computational cost and achieves on-par or even better synthesis performance compared to baseline methods. We also show that our strategy facilitates high-resolution image synthesis and improves FID of diffusion model trained on FFHQ at$1024\times 1024$resolution from 52.40 to 10.46. Code is available at https://github.com/damo-vilab/dvdp.

Foundation models are pre-trained on massive data and transferred to downstream tasks via fine-tuning. This work presents Vision Middleware (ViM), a new learning paradigm that targets unified transferring from a single foundation model to a variety of downstream tasks. ViM consists of a zoo of lightweight plug-in modules, each of which is independently learned on a midstream dataset with a shared frozen backbone. Downstream tasks can then benefit from an adequate aggregation of the module zoo thanks to the rich knowledge inherited from midstream tasks. There are three major advantages of such a design. From the efficiency aspect, the upstream backbone can be trained only once and reused for all downstream tasks without tuning. From the scalability aspect, we can easily append additional modules to ViM with no influence on existing modules. From the performance aspect, ViM can include as many midstream tasks as possible, narrowing the task gap between upstream and downstream. Considering these benefits, we believe that ViM, which the community could maintain and develop together, would serve as a powerful tool to assist foundation models.

Video temporal grounding aims to pinpoint a video segment that matches the query description. Despite the recent advance in short-form videos (e.g., in minutes), temporal grounding in long videos (e.g., in hours) is still at its early stage. To address this challenge, a common practice is to employ a sliding window, yet can be inefficient and inflexible due to the limited number of frames within the window. In this work, we propose an end-to-end framework for fast temporal grounding, which is able to model an hours-long video with one-time network execution. Our pipeline is formulated in a coarse-to-fine manner, where we first extract context knowledge from non-overlapped video clips (i.e., anchors), and then supplement the anchors that highly response to the query with detailed content knowledge. Besides the remarkably high pipeline efficiency, another advantage of our approach is the capability of capturing long-range temporal correlation, thanks to modeling the entire video as a whole, and hence facilitates more accurate grounding. Experimental results suggest that, on the long-form video datasets MAD and Ego4d, our method significantly outperforms state-of-the-arts, and achieves 14.6× / 102.8× higher efficiency respectively. Project can be found at https://github.com/afcedf/SOONet.git.

This work aims to transfer a Generative Adversarial Network (GAN) pre-trained on one image domain to another domain referred to as few as just one reference image. The challenge is that, under limited supervision, it is extremely difficult to synthesize photo-realistic and highly diverse images while retaining the representative characters of the target domain. Different from existing approaches that adopt the vanilla fine-tuning strategy, we design two lightweight modules in the generator and the discriminator respectively. We first introduce an attribute adaptor in the generator and freeze the generator’s original parameters, which can reuse the prior knowledge to the most extent and maintain the synthesis quality and diversity. We then equip the well-learned discriminator with an attribute classifier to ensure that the generator with the attribute adaptor captures the appropriate characters of the reference image. Furthermore, considering the very limited diversity of the training data (i.e., as few as only one image), we propose to constrain the diversity of the latent space through truncation in the training process, alleviating the optimization difficulty. Our approach brings appealing results under various settings, substantially surpassing state-of-the-art alternatives, especially in terms of synthesis diversity. Noticeably, our method works well even with large domain gaps and robustly converges within a few minutes for each experiment. Code and models are available at https://genforce.github.io/genda/.

Prompt tuning and adapter tuning have shown great potential in transferring pre-trained vision-language models (VLMs) to various downstream tasks. In this work, we design a new type of tuning method, termed as regularized mask tuning, which masks the network parameters through a learnable selection. Inspired by neural pathways, we argue that the knowledge required by a downstream task already exists in the pre-trained weights but just gets concealed in the upstream pre-training stage. To bring the useful knowledge back into light, we first identify a set of parameters that are important to a given downstream task, then attach a binary mask to each parameter, and finally optimize these masks on the downstream data with the parameters frozen. When updating the mask, we introduce a novel gradient dropout strategy to regularize the parameter selection, in order to prevent the model from forgetting old knowledge and overfitting the downstream data. Experimental results on 11 datasets demonstrate the consistent superiority of our method over previous alternatives. It is noteworthy that we manage to deliver 18.73% performance improvement compared to the zero-shot CLIP via masking an average of only 2.56% parameters. Furthermore, our method is synergistic with most existing parameter-efficient tuning methods and can boost the performance on top of them. Project page can be found here.

This work presents an easy-to-use regularizer for GAN training, which helps explicitly link some axes of the latent space to a set of pixels in the synthesized image. Establishing such a connection facilitates a more convenient local control of GAN generation, where users can alter the image content only within a spatial area simply by partially resampling the latent code. Experimental results confirm four appealing properties of our regularizer, which we call LinkGAN. (1) The latent-pixel linkage is applicable to either a fixed region (i.e., same for all instances) or a particular semantic category (i.e., varying across instances), like the sky. (2) Two or multiple regions can be independently linked to different latent axes, which further supports joint control. (3) Our regularizer can improve the spatial controllability of both 2D and 3D-aware GAN models, barely sacrificing the synthesis performance. (4) The models trained with our regularizer are compatible with GAN inversion techniques and maintain editability on real images. Project page can be found here.

Recent large-scale generative models learned on big data are capable of synthesizing incredible images yet suffer from limited controllability. This work offers a new generation paradigm that allows flexible control of the output image, such as spatial layout and palette, while maintaining the synthesis quality and model creativity. With compositionality as the core idea, we first decompose an image into representative factors, and then train a diffusion model with all these factors as the conditions to recompose the input. At the inference stage, the rich intermediate representations work as composable elements, leading to a huge design space (i.e., exponentially proportional to the number of decomposed factors) for customizable content creation. It is noteworthy that our approach, which we call Composer, supports various levels of conditions, such as text description as the global information, depth map and sketch as the local guidance, color histogram for low-level details, etc. Besides improving controllability, we confirm that Composer serves as a general framework and facilitates a wide range of classical generative tasks without retraining. Code and models will be made available.

This paper addresses the challenge of representing high-fidelity volumetric videos with low storage cost. Some recent feature grid-based methods have shown superior performance of fast learning implicit neural representations from input 2D images. However, such explicit representations easily lead to large model sizes when modeling dynamic scenes. To solve this problem, our key idea is reducing the spatial and temporal redundancy of feature grids, which intrinsically exist due to the self-similarity of scenes. To this end, we propose a novel neural representation, named dynamic codebook, which first merges similar features for the model compression and then compensates for the potential decline in rendering quality by a set of dynamic codes. Experiments on the NHR and DyNeRF datasets demonstrate that the proposed approach achieves state-of-the-art rendering quality, while being able to achieve more storage efficiency. The source code is available at https://github.com/zju3dv/compact_vv.

Parameter-efficient tuning has become a trend in transferring large-scale foundation models to downstream applications. Existing methods typically embed some light-weight tuners into the backbone, where both the design and the learning of the tuners are highly dependent on the base model. This work offers a new tuning paradigm, dubbed Res-Tuning, which intentionally unbinds tuners from the backbone. With both theoretical and empirical evidence, we show that popular tuning approaches have their equivalent counterparts under our unbinding formulation, and hence can be integrated into our framework effortlessly. Thanks to the structural disentanglement, we manage to free the design of tuners from the network architecture, facilitating flexible combination of various tuning strategies. We further propose a memory-efficient variant of Res-Tuning, where the bypass i.e., formed by a sequence of tuners) is effectively detached from the main branch, such that the gradients are back-propagated only to the tuners but not to the backbone. Such a detachment also allows one-time backbone forward for multi-task inference. Extensive experiments on both discriminative and generative tasks demonstrate the superiority of our method over existing alternatives from the perspectives of efficacy and efficiency. Project page: https://res-tuning.github.io/.

Synthesizing images with user-specified subjects has received growing attention due to its practical applications. Despite the recent success in single subject customization, existing algorithms suffer from high training cost and low success rate along with increased number of subjects. Towards controllable image synthesis with multiple subjects as the constraints, this work studies how to efficiently represent a particular subject as well as how to appropriately compose different subjects. We find that the text embedding regarding the subject token already serves as a simple yet effective representation that supports arbitrary combinations without any model tuning. Through learning a residual on top of the base embedding, we manage to robustly shift the raw subject to the customized subject given various text conditions. We then propose to employ layout, a very abstract and easy-to-obtain prior, as the spatial guidance for subject arrangement. By rectifying the activations in the cross-attention map, the layout appoints and separates the location of different subjects in the image, significantly alleviating the interference across them. Using cross-attention map as the intermediary, we could strengthen the signal of target subjects and weaken the signal of irrelevant subjects within a certain region, significantly alleviating the interference across subjects. Both qualitative and quantitative experimental results demonstrate our superiority over state-of-the-art alternatives under a variety of settings for multi-subject customization.

Despite the rapid advance of 3D-aware image synthesis, existing studies usually adopt a mixture of techniques and tricks, leaving it unclear how each part contributes to the final performance in terms of generality. Following the most popular and effective paradigm in this field, which incorporates a neural radiance field (NeRF) into the generator of a generative adversarial network (GAN), we builda well-structured codebase through modularizing the generation process. Such a design allows researchers to develop and replace each module independently, and hence offers an opportunity to fairly compare various approaches and recognize their contributions from the module perspective. The reproduction of a range of cutting-edge algorithms demonstrates the availability of our modularized codebase. We also perform a variety of in-depth analyses, such as the comparison across different types of point feature, the necessity of the tailing upsampler in the generator, the reliance on the camera pose prior, etc., which deepen our understanding of existing methods and point out some further directions of the research work. Code and models will be made publicly available to facilitate the development and evaluation of this field.

The pursuit of controllability as a higher standard of visual content creation has yielded remarkable progress in customizable image synthesis. However, achieving controllable video synthesis remains challenging due to the large variation of temporal dynamics and the requirement of cross-frame temporal consistency. Based on the paradigm of compositional generation, this work presents VideoComposer that allows users to flexibly compose a video with textual conditions, spatial conditions, and more importantly temporal conditions. Specifically, considering the characteristic of video data, we introduce the motion vector from compressed videos as an explicit control signal to provide guidance regarding temporal dynamics. In addition, we develop a Spatio-Temporal Condition encoder (STC-encoder) that serves as a unified interface to effectively incorporate the spatial and temporal relations of sequential inputs, with which the model could make better use of temporal conditions and hence achieve higher inter-frame consistency. Extensive experimental results suggest that VideoComposer is able to control the spatial and temporal patterns simultaneously within a synthesized video in various forms, such as text description, sketch sequence, reference video, or even simply hand-crafted motions. The code and models are publicly available at https://videocomposer.github.io.

This work presents FaceComposer, a unified generative model that accomplishes a variety of facial content creation tasks, including text-conditioned face synthesis, text-guided face editing, face animation etc. Based on the latent diffusion framework, FaceComposer follows the paradigm of compositional generation and employs diverse face-specific conditions, e.g., Identity Feature and Projected Normalized Coordinate Code, to release the model creativity at all possible. To support text control and animation, we clean up some existing face image datasets and collect around 500 hours of talking-face videos, forming a high-quality large-scale multi-modal face database. A temporal self-attention module is incorporated into the U-Net structure, which allows learning the denoising process on the mixture of images and videos. Extensive experiments suggest that our approach not only achieves comparable or even better performance than state-of-the-arts on each single task, but also facilitates some combined tasks with one-time forward, demonstrating its potential in serving as a foundation generative model in face domain. We further develop an interface such that users can enjoy our one-step service to create, edit, and animate their own characters. Code, dataset, model, and interface will be made publicly available.

A good metric, which promises a reliable comparison between solutions, is essential for any well-defined task. Unlike most vision tasks that have per-sample ground-truth, image synthesis tasks target generating unseen data and hence are usually evaluated through a distributional distance between one set of real samples and another set of generated samples. This study presents an empirical investigation into the evaluation of synthesis performance, with generative adversarial networks (GANs) as a representative of generative models. In particular, we make in-depth analyses of various factors, including how to represent a data point in the representation space, how to calculate a fair distance using selected samples, and how many instances to use from each set. Extensive experiments conducted on multiple datasets and settings reveal several important findings. Firstly, a group of models that include both CNN-based and ViT-based architectures serve as reliable and robust feature extractors for measurement evaluation. Secondly, Centered Kernel Alignment (CKA) provides a better comparison across various extractors and hierarchical layers in one model. Finally, CKA is more sample-efficient and enjoys better agreement with human judgment in characterizing the similarity between two internal data correlations. These findings contribute to the development of a new measurement system, which enables a consistent and reliable re-evaluation of current state-of-the-art generative models.

The success of style-based generators largely benefits from style modulation, which helps take care of the cross-instance variation within data. However, the instance-wise stochasticity is typically introduced via regular convolution, where kernels interact with features at some fixed locations, limiting its capacity for modeling geometric variation. To alleviate this problem, we equip the generator in generative adversarial networks (GANs) with a plug-and-play module, termed as modulated transformation module (MTM). This module predicts spatial offsets under the control of latent codes, based on which the convolution operation can be applied at variable locations for different instances, and hence offers the model an additional degree of freedom to handle geometry deformation. Extensive experiments suggest that our approach can be faithfully generalized to various generative tasks, including image generation, 3D-aware image synthesis, and video generation, and get compatible with state-of-the-art frameworks without any hyper-parameter tuning. It is noteworthy that, towards human generation on the challenging TaiChi dataset, we improve the FID of StyleGAN3 from 21.36 to 13.60, demonstrating the efficacy of learning modulated geometry transformation. Code and models are available at https://github.com/limbo0000/mtm.

Recent years witness the tremendous success of generative adversarial networks (GANs) in synthesizing photo-realistic images. GAN generator learns to compose realistic images and reproduce the real data distribution. Through that, a hierarchical visual feature with multi-level semantics spontaneously emerges. In this work we investigate that such a generative feature learned from image synthesis exhibits great potentials in solving a wide range of computer vision tasks, including both generative ones and more importantly discriminative ones. We first train an encoder by considering the pre-trained StyleGAN generator as a learned loss function. The visual features produced by our encoder, termed as Generative Hierarchical Features (GH-Feat), highly align with the layer-wise GAN representations, and hence describe the input image adequately from the reconstruction perspective. Extensive experiments support the versatile transferability of GH-Feat across a range of applications, such as image editing, image processing, image harmonization, face verification, landmark detection, layout prediction, image retrieval, etc. We further show that, through a proper spatial expansion, our developed GH-Feat can also facilitate fine-grained semantic segmentation using only a few annotations. Both qualitative and quantitative results demonstrate the appealing performance of GH-Feat. Code and models are available at https://genforce.github.io/ghfeat/.

High-quality large-scale scene rendering requires a scalable representation and accurate camera poses. This research combines tile-based hybrid neural fields with parallel distributive optimization to improve bundle-adjusting neural radiance fields. The proposed method scales with a divide-and-conquer strategy. We partition scenes into tiles, each with a multi-resolution hash feature grid and shallow chained diffuse and specular multilayer perceptrons (MLPs). Tiles unify foreground and background via a spatial contraction function that allows both distant objects in outdoor scenes and planar reflections as virtual images outside the tile. Decomposing appearance with the specular MLP allows a specular-aware warping loss to provide a second optimization path for camera poses. We apply the alternating direction method of multipliers (ADMM) to achieve consensus among camera poses while maintaining parallel tile optimization. Experimental results show that our method outperforms state-of-the-art neural scene rendering method quality by 5%--10% in PSNR, maintaining sharp distant objects and view-dependent reflections across six indoor and outdoor scenes.

The crux of semi-supervised semantic segmentation is to assign adequate pseudo-labels to the pixels of unlabeled images. A common practice is to select the highly confident predictions as the pseudo ground-truth, but it leads to a problem that most pixels may be left unused due to their unreliability. We argue that every pixel matters to the model training, even its prediction is ambiguous. Intuitively, an unreliable prediction may get confused among the top classes (i.e., those with the highest probabilities), however, it should be confident about the pixel not belonging to the remaining classes. Hence, such a pixel can be convincingly treated as a negative sample to those most unlikely categories. Based on this insight, we develop an effective pipeline to make sufficient use of unlabeled data. Concretely, we separate reliable and unreliable pixels via the entropy of predictions, push each unreliable pixel to a category-wise queue that consists of negative samples, and manage to train the model with all candidate pixels. Considering the training evolution, where the prediction becomes more and more accurate, we adaptively adjust the threshold for the reliable-unreliable partition. Experimental results on various benchmarks and training settings demonstrate the superiority of our approach over the state-of-the-art alternatives.11Project: https://haochen-wang409.github.io/U2PL.

The success of Generative Adversarial Networks (GANs) is largely built upon the adversarial training between a generator (G) and a discriminator (D). They are expected to reach a certain equilibrium where D cannot distinguish the generated images from the real ones. However, such an equilibrium is rarely achieved in practical GAN training, instead, D almost always surpasses G. We attribute one of its sources to the information asymmetry between D and G. We observe that D learns its own visual attention when determining whether an image is real or fake, but G has no explicit clue on which regions to focus on for a particular synthesis. To alleviate the issue of D dominating the competition in GANs, we aim to raise the spatial awareness of G. Randomly sampled multi-level heatmaps are encoded into the intermediate layers of G as an inductive bias. Thus G can purposefully improve the synthesis of certain image regions. We further propose to align the spatial awareness of G with the attention map induced from D. Through this way we effectively lessen the information gap between D and G. Extensive results show that our method pushes the two-player game in GANs closer to the equilibrium, leading to a better synthesis performance. As a byproduct, the intro-duced spatial awareness facilitates interactive editing over the output synthesis. Demo video and code are available at https://genforce.github.io/eqgan-sa/

Making generative models 3D-aware bridges the 2D image space and the 3D physical world yet remains challenging. Recent attempts equip a Generative Adversarial Network (GAN) with a Neural Radiance Field (NeRF), which maps 3D coordinates to pixel values, as a 3D prior. However, the implicit function in NeRF has a very local receptive field, making the generator hard to become aware of the global structure. Meanwhile, NeRF is built on volume rendering which can be too costly to produce high-resolution results, increasing the optimization difficulty. To alleviate these two problems, we propose a novel framework, termed as VolumeGAN, for high-fidelity 3D-aware image synthesis, through explicitly learning a structural representation and a textural representation. We first learn a feature volume to represent the underlying structure, which is then converted to a feature field using a NeRF-like model. The feature field is further accumulated into a 2D feature map as the textural representation, followed by a neural renderer for appearance synthesis. Such a design enables independent control of the shape and the appearance. Project page is at https://genforce.github.io/volumegan.

Semi-supervised action recognition is a challenging but important task due to the high cost of data annotation. A common approach to this problem is to assign unlabeled data with pseudo-labels, which are then used as additional supervision in training. Typically in recent work, the pseudo-labels are obtained by training a model on the labeled data, and then using confident predictions from the model to teach itself. In this work, we propose a more effective pseudo-labeling scheme, called Cross-Model Pseudo-Labeling (CMPL). Concretely, we introduce a lightweight auxiliary network in addition to the primary backbone, and ask them to predict pseudo-labels for each other. We observe that, due to their different structural biases, these two models tend to learn complementary representations from the same video clips. Each model can thus benefit from its counterpart by utilizing cross-model predictions as supervision. Experiments on different data partition protocols demonstrate the significant improvement of our framework over existing alternatives. For example, CMPL achieves 17.6% and 25.1% Top-1 accuracy on Kinetics-400 and UCF-101 using only the RGB modality and 1% labeled data, outperforming our baseline model, FixMatch [17], by 9.0% and 10.3%, respectively.11Project page is at https://justimyhxu.github.io/projects/cmpl/.

Despite the rapid advancement of semantic discovery in the latent space of Generative Adversarial Networks (GANs), existing approaches either are limited to finding global attributes or rely on a number of segmentation masks to identify local attributes. In this work, we present a highly efficient algorithm to factorize the latent semantics learned by GANs concerning an arbitrary image region. Concretely, we revisit the task of local manipulation with pre-trained GANs and formulate region-based semantic discovery as a dual optimization problem. Through an appropriately defined generalized Rayleigh quotient, we manage to solve such a problem without any annotations or training. Experimental results on various state-of-the-art GAN models demonstrate the effectiveness of our approach, as well as its superiority over prior arts regarding precise control, region robustness, speed of implementation, and simplicity of use.

Self-training has shown great potential in semi-supervised learning. Its core idea is to use the model learned on labeled data to generate pseudo-labels for unlabeled samples, and in turn teach itself. To obtain valid supervision, active attempts typically employ a momentum teacher for pseudo-label prediction yet observe the confirmation bias issue, where the incorrect predictions may provide wrong supervision signals and get accumulated in the training process. The primary cause of such a drawback is that the prevailing self-training framework acts as guiding the current state with previous knowledge because the teacher is updated with the past student only. To alleviate this problem, we propose a novel self-training strategy, which allows the model to learn from the future. Concretely, at each training step, we first virtually optimize the student (i.e., caching the gradients without applying them to the model weights), then update the teacher with the virtual future student, and finally ask the teacher to produce pseudo-labels for the current student as the guidance. In this way, we manage to improve the quality of pseudo-labels and thus boost the performance. We also develop two variants of our future-self-training (FST) framework through peeping at the future both deeply (FST-D) and widely (FST-W). Taking the tasks of unsupervised domain adaptive semantic segmentation and semi-supervised semantic segmentation as the instances, we experimentally demonstrate the effectiveness and superiority of our approach under a wide range of settings. Code is available at https://github.com/usr922/FST.

3D-aware image synthesis aims at learning a generative model that can render photo-realistic 2D images while capturing decent underlying 3D shapes. A popular solution is to adopt the generative adversarial network (GAN) and replace the generator with a 3D renderer, where volume rendering with neural radiance field (NeRF) is commonly used. Despite the advancement of synthesis quality, existing methods fail to obtain moderate 3D shapes. We argue that, considering the two-player game in the formulation of GANs, only making the generator 3D-aware is not enough. In other words, displacing the generative mechanism only offers the capability, but not the guarantee, of producing 3D-aware images, because the supervision of the generator primarily comes from the discriminator. To address this issue, we propose GeoD through learning a geometry-aware discriminator to improve 3D-aware GANs. Concretely, besides differentiating real and fake samples from the 2D image space, the discriminator is additionally asked to derive the geometry information from the inputs, which is then applied as the guidance of the generator. Such a simple yet effective design facilitates learning substantially more accurate 3D shapes. Extensive experiments on various generator architectures and training datasets verify the superiority of GeoD over state-of-the-art alternatives. Moreover, our approach is registered as a general framework such that a more capable discriminator (i.e., with a third task of novel view synthesis beyond domain classification and geometry extraction) can further assist the generator with a better multi-view consistency. Project page can be found at https://vivianszf.github.io/geod.

Discriminator plays a vital role in training generative adversarial networks (GANs) via distinguishing real and synthesized samples. While the real data distribution remains the same, the synthesis distribution keeps varying because of the evolving generator, and thus effects a corresponding change of the bi-classification task assigned to the discriminator. We argue that a discriminator with an on-the-fly adjustment on its capacity can better accommodate such a time-varying task. A comprehensive empirical study confirms that the proposed training strategy, termed as DynamicD, improves the synthesis performance without incurring any additional computation cost or training objectives. Two capacity adjusting schemes are developed for training GANs under different data regimes: i) given a sufficient amount of training data, the discriminator benefits from a progressively increased learning capacity, and ii) when the training data is limited, gradually decreasing the layer width mitigates the over-fitting issue of the discriminator. Experiments on both 2D and 3D-aware image synthesis tasks conducted on a range of datasets substantiate the generalizability of our DynamicD as well as its substantial improvement over the baselines. Furthermore, DynamicD is synergistic to other discriminator-improving approaches (including data augmentation, regularizers, and pre-training), and brings continuous performance gain when combined with them for learning GANs. Code will be made publicly available.

Despite the rapid advance of unsupervised anomaly detection, existing methods require to train separate models for different objects. In this work, we present UniAD that accomplishes anomaly detection for multiple classes with a unified framework. Under such a challenging setting, popular reconstruction networks may fall into an "identical shortcut", where both normal and anomalous samples can be well recovered, and hence fail to spot outliers. To tackle this obstacle, we make three improvements. First, we revisit the formulations of fully-connected layer, convolutional layer, as well as attention layer, and confirm the important role of query embedding (i.e., within attention layer) in preventing the network from learning the shortcut. We therefore come up with a layer-wise query decoder to help model the multi-class distribution. Second, we employ a neighbor masked attention module to further avoid the information leak from the input feature to the reconstructed output feature. Third, we propose a feature jittering strategy that urges the model to recover the correct message even with noisy inputs. We evaluate our algorithm on MVTec-AD and CIFAR-10 datasets, where we surpass the state-of-the-art alternatives by a sufficiently large margin. For example, when learning a unified model for 15 categories in MVTec-AD, we surpass the second competitor on the tasks of both anomaly detection (from 88.1% to 96.5%) and anomaly localization (from 89.5% to 96.8%). Code is available at https://github.com/zhiyuanyou/UniAD.

Although generative adversarial networks (GANs) have made significant progress in face synthesis, there lacks enough understanding of what GANs have learned in the latent representation to map a random code to a photo-realistic image. In this work, we propose a framework called InterFaceGAN to interpret the disentangled face representation learned by the state-of-the-art GAN models and study the properties of the facial semantics encoded in the latent space. We first find that GANs learn various semantics in some linear subspaces of the latent space. After identifying these subspaces, we can realistically manipulate the corresponding facial attributes without retraining the model. We then conduct a detailed study on the correlation between different semantics and manage to better disentangle them via subspace projection, resulting in more precise control of the attribute manipulation. Besides manipulating the gender, age, expression, and presence of eyeglasses, we can even alter the face pose and fix the artifacts accidentally made by GANs. Furthermore, we perform an in-depth face identity analysis and a layer-wise analysis to evaluate the editing results quantitatively. Finally, we apply our approach to real face editing by employing GAN inversion approaches and explicitly training feed-forward models based on the synthetic data established by InterFaceGAN. Extensive experimental results suggest that learning to synthesize faces spontaneously brings a disentangled and controllable face representation.

A rich set of interpretable dimensions has been shown to emerge in the latent space of the Generative Adversarial Networks (GANs) trained for synthesizing images. In order to identify such latent dimensions for image editing, previous methods typically annotate a collection of synthesized samples and train linear classifiers in the latent space. However, they require a clear definition of the target attribute as well as the corresponding manual annotations, limiting their applications in practice. In this work, we examine the internal representation learned by GANs to reveal the underlying variation factors in an unsupervised manner. In particular, we take a closer look into the generation mechanism of GANs and further propose a closedform factorization algorithm for latent semantic discovery by directly decomposing the pre-trained weights. With a lightning-fast implementation, our approach is capable of not only finding semantically meaningful dimensions comparably to the state-of-the-art supervised methods, but also resulting in far more versatile concepts across multiple GAN models trained on a wide range of datasets.1

Anomaly localization, with the purpose to segment the anomalous regions within images, is challenging due to the large variety of anomaly types. Existing methods typically train deep models by treating the entire image as a whole yet put little effort into learning the local distribution, which is vital for this pixel-precise task. In this work, we propose an unsupervised patch-based approach that gives due consideration to both the global and local information. More concretely, we employ a Local-Net and Global-Net to extract features from any individual patch and its surrounding respectively. Global-Net is trained with the purpose to mimic the local feature such that we can easily detect an abnormal patch when its feature mismatches that from the context. We further introduce an Inconsistency Anomaly Detection (IAD) head and a Distortion Anomaly Detection (DAD) head to sufficiently spot the discrepancy between global and local features. A scoring function derived from the multi-head design facilitates high-precision anomaly localization. Extensive experiments on a couple of real-world datasets suggest that our approach outperforms state-of-the-art competitors by a sufficiently large margin.

Generative Adversarial Networks (GANs) have recently advanced image synthesis by learning the underlying distribution of the observed data. However, how the features learned from solving the task of image generation are applicable to other vision tasks remains seldom explored. In this work, we show that learning to synthesize images can bring remarkable hierarchical visual features that are generalizable across a wide range of applications. Specifically, we consider the pre-trained StyleGAN generator as a learned loss function and utilize its layer-wise representation to train a novel hierarchical encoder. The visual feature produced by our encoder, termed as Generative Hierarchical Feature (GH-Feat), has strong transferability to both generative and discriminative tasks, including image editing, image harmonization, image classification, face verification, landmark detection, and layout prediction. Extensive qualitative and quantitative experimental results demonstrate the appealing performance of GH-Feat.1

Generative Adversarial Networks (GANs) have significantly advanced image synthesis, however, the synthesis quality drops significantly given a limited amount of training data. To improve the data efficiency of GAN training, prior work typically employs data augmentation to mitigate the overfitting of the discriminator yet still learn the discriminator with a bi-classification ($\textit{i.e.}$, real $\textit{vs.}$ fake) task. In this work, we propose a data-efficient Instance Generation ($\textit{InsGen}$) method based on instance discrimination. Concretely, besides differentiating the real domain from the fake domain, the discriminator is required to distinguish every individual image, no matter it comes from the training set or from the generator. In this way, the discriminator can benefit from the infinite synthesized samples for training, alleviating the overfitting problem caused by insufficient training data. A noise perturbation strategy is further introduced to improve its discriminative power. Meanwhile, the learned instance discrimination capability from the discriminator is in turn exploited to encourage the generator for diverse generation. Extensive experiments demonstrate the effectiveness of our method on a variety of datasets and training settings. Noticeably, on the setting of $2K$ training images from the FFHQ dataset, we outperform the state-of-the-art approach with 23.5\% FID improvement.

The latent space of a Generative Adversarial Network (GAN) has been shown to encode rich semantics within some subspaces. To identify these subspaces, researchers typically analyze the statistical information from a collection of synthesized data, and the identified subspaces tend to control image attributes globally (i.e., manipulating an attribute causes the change of an entire image). By contrast, this work introduces low-rank subspaces that enable more precise control of GAN generation. Concretely, given an arbitrary image and a region of interest (e.g., eyes of face images), we manage to relate the latent space to the image region with the Jacobian matrix and then use low-rank factorization to discover steerable latent subspaces. There are three distinguishable strengths of our approach that can be aptly called LowRankGAN. First, compared to analytic algorithms in prior work, our low-rank factorization of Jacobians is able to find the low-dimensional representation of attribute manifold, making image editing more precise and controllable. Second, low-rank factorization naturally yields a null space of attributes such that moving the latent code within it only affects the outer region of interest. Therefore, local image editing can be simply achieved by projecting an attribute vector into the null space without relying on a spatial mask as existing methods do. Third, our method can robustly work with a local region from one image for analysis yet well generalize to other images, making it much easy to use in practice. Extensive experiments on state-of-the-art GAN models (including StyleGAN2 and BigGAN) trained on various datasets demonstrate the effectiveness of our LowRankGAN.

Despite the success of Generative Adversarial Networks (GANs) in image synthesis, applying trained GAN models to real image processing remains challenging. Previous methods typically invert a target image back to the latent space either by back-propagation or by learning an additional encoder. However, the reconstructions from both of the methods are far from ideal. In this work, we propose a novel approach, called mGANprior, to incorporate the well-trained GANs as effective prior to a variety of image processing tasks. In particular, we employ multiple latent codes to generate multiple feature maps at some intermediate layer of the generator, then compose them with adaptive channel importance to recover the input image. Such an over-parameterization of the latent space significantly improves the image reconstruction quality, outperforming existing competitors. The resulting high-fidelity image reconstruction enables the trained GAN models as prior to many real-world applications, such as image colorization, super-resolution, image inpainting, and semantic manipulation. We further analyze the properties of the layer-wise representation learned by GAN models and shed light on what knowledge each layer is capable of representing.

Despite the recent advance of Generative Adversarial Networks (GANs) in high-fidelity image synthesis, there lacks enough understanding of how GANs are able to map a latent code sampled from a random distribution to a photo-realistic image. Previous work assumes the latent space learned by GANs follows a distributed representation but observes the vector arithmetic phenomenon. In this work, we propose a novel framework, called InterFaceGAN, for semantic face editing by interpreting the latent semantics learned by GANs. In this framework, we conduct a detailed study on how different semantics are encoded in the latent space of GANs for face synthesis. We find that the latent code of well-trained generative models actually learns a disentangled representation after linear transformations. We explore the disentanglement between various semantics and manage to decouple some entangled semantics with subspace projection, leading to more precise control of facial attributes. Besides manipulating gender, age, expression, and the presence of eyeglasses, we can even vary the face pose as well as fix the artifacts accidentally generated by GAN models. The proposed method is further applied to achieve real image manipulation when combined with GAN inversion methods or some encoder-involved models. Extensive results suggest that learning to synthesize faces spontaneously brings a disentangled and controllable facial attribute representation.

Face synthesis has achieved advanced development by using generative adversarial networks (GANs). Existing methods typically formulate GAN as a two-player game, where a discriminator distinguishes face images from the real and synthesized domains, while a generator reduces its discriminativeness by synthesizing a face of photorealistic quality. Their competition converges when the discriminator is unable to differentiate these two domains. Unlike two-player GANs, this work generates identity-preserving faces by proposing FaceID-GAN, which treats a classifier of face identity as the third player, competing with the generator by distinguishing the identities of the real and synthesized faces (see Fig.1). A stationary point is reached when the generator produces faces that have high quality as well as preserve identity. Instead of simply modeling the identity classifier as an additional discriminator, FaceID-GAN is formulated by satisfying information symmetry, which ensures that the real and synthesized images are projected into the same feature space. In other words, the identity classifier is used to extract identity features from both input (real) and output (synthesized) face images of the generator, substantially alleviating training difficulty of GAN. Extensive experiments show that FaceID-GAN is able to generate faces of arbitrary viewpoint while preserve identity, outperforming recent advanced approaches.