CVPR 2025 论文列表

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

As 3D content creation continues to grow, transferring semantic textures between 3D meshes remains a significant challenge in computer graphics. While recent methods leverage text-to-image diffusion models for texturing, they often struggle to preserve the appearance of the source texture during texture transfer. We present TriTex, a novel approach that learns a volumetric texture field from a single textured mesh by mapping semantic features to surface colors. Using an efficient triplane-based architecture, our method enables semantic-aware texture transfer to a novel target mesh. Despite training on just one example, it generalizes effectively to diverse shapes within the same category. Extensive evaluation on our newly created benchmark dataset shows that TriTex achieves superior texture transfer quality and fast inference times compared to existing methods. Our approach advances single-example texture transfer, providing a practical solution for maintaining visual coherence across related 3D models in applications like game development and simulation.

The distortion-perception (DP) tradeoff reveals a fundamental conflict between distortion metrics (e.g., MSE and PSNR) and perceptual quality. Recent research has increasingly concentrated on evaluating denoising algorithms within the DP framework. However, existing algorithms either prioritize perceptual quality by sacrificing acceptable distortion, or focus on minimizing MSE for faithful restoration. When the goal shifts or noisy measurements vary, adapting to different points on the DP plane needs retraining or even re-designing the model. Inspired by recent advances in solving inverse problems using score-based generative models, we explore the potential of flexibly and optimally traversing DP tradeoffs using a single pre-trained score-based model. Specifically, we introduce a variance-scaled reverse diffusion process and theoretically characterize the marginal distribution. We then prove that the proposed sample process is an optimal solution to the DP tradeoff for conditional Gaussian distribution. Experimental results on two-dimensional and image datasets illustrate that a single score network can effectively and flexibly traverse the DP tradeoff for general denoising problems.

Self-driving cars relying solely on ego-centric perception face limitations in sensing, often failing to detect occluded, faraway objects. Collaborative autonomous driving (CAV) seems like a promising direction, but collecting data for development is non-trivial. It requires placing multiple sensor-equipped agents in a real-world driving scene, simultaneously! As such, existing datasets are limited in locations and agents. We introduce a novel surrogate to the rescue, which is to generate realistic perception from different viewpoints in a driving scene, conditioned on a real-world sample -- the ego-car's sensory data. This surrogate has huge potential: it could potentially turn any ego-car dataset into a collaborative driving one to scale up the development of CAV. We present the very first solution, using a combination of synthetic collaborative data and real ego-car data. Our method, Transfer Your Perspective (TYP), learns a conditioned diffusion model whose output samples are not only realistic but also consistent in both semantics and layouts with the given ego-car data. Empirical results demonstrate TYP's effectiveness in aiding in a CAV setting. In particular, TYP enables us to (pre-)train collaborative perception algorithms like early and late fusion with little or no real-world collaborative data, greatly facilitating downstream CAV applications.

Conditional image synthesis is a crucial task with broad applications, such as artistic creation and virtual reality. However, current generative methods are often task-oriented with a narrow scope, handling a restricted condition with constrained applicability. In this paper, we propose a novel approach that treats conditional image synthesis as the modular combination of diverse fundamental condition units. Specifically, we divide conditions into three primary units: text, layout, and drag. To enable effective control over these conditions, we design a dedicated alignment module for each. For the text condition, we introduce a Dense Concept Alignment (DCA) module, which achieves dense visual-text alignment by drawing on diverse textual concepts. For the layout condition, we propose a Dense Geometry Alignment (DGA) module to enforce comprehensive geometric constraints that preserve the spatial configuration. For the drag condition, we introduce a Dense Motion Alignment (DMA) module to apply multi-level motion regularization, ensuring that each pixel follows its desired trajectory without visual artifacts. By flexibly inserting and combining these alignment modules, our framework enhances the model's adaptability to diverse conditional generation tasks and greatly expands its application range. Extensive experiments demonstrate the superior performance of our framework across a variety of conditions, including textual description, segmentation mask (bounding box), drag manipulation, and their combinations. Code is available at https://github.com/ZixuanWang0525/DADG

While recent foundational video generators produce visually rich output, they still struggle with appearance drift, where objects gradually degrade or change inconsistently across frames, breaking visual coherence. We hypothesize that this is because there is no explicit supervision in terms of spatial tracking at the feature level. We propose Track4Gen, a spatially aware video generator that combines video diffusion loss with point tracking across frames, providing enhanced spatial supervision on the diffusion features. Track4Gen merges the video generation and point tracking tasks into a single network by making minimal changes to existing video generation architectures. Using Stable Video Diffusion as a backbone, Track4Gen demonstrates that it is possible to unify video generation and point tracking, which are typically handled as separate tasks. Our extensive evaluations show that Track4Gen effectively reduces appearance drift, resulting in temporally stable and visually coherent video generation. Project page: https://hyeonho99.github.io/track4gen/

Dataset distillation (DD) condenses key information from large-scale datasets into smaller synthetic datasets, reducing storage and computational costs for training networks. However, recent research has primarily focused on image classification tasks, with limited expansion to detection and segmentation. Two key challenges remain: (i) Task Optimization Heterogeneity, where existing methods focus on class-level information and fail to address the diverse needs of detection and segmentation and (ii) Inflexible Image Generation, where current generation methods rely on global updates for single-class targets and lack localized optimization for specific object regions.To address these challenges, we propose a universal dataset distillation framework, named UniDD, a task-driven diffusion model for diverse DD tasks, as illustrated in Fig.1. Our approach operates in two stages: Universal Task Knowledge Mining, which captures task-relevant information through task-specific proxy model training, and Universal Task-Driven Diffusion, where these proxies guide the diffusion process to generate task-specific synthetic images.Extensive experiments across ImageNet-1K, Pascal VOC, and MS COCO demonstrate that UniDD consistently outperforms state-of-the-art methods. In particular, on ImageNet-1K with IPC-10, UniDD surpasses previous diffusion-based methods by 6.1%, while also reducing deployment costs.

The rapid advancement of generative models has significantly improved the quality of generated images. Meanwhile, it challenges information authenticity and credibility. Current generated image detection methods based on large-scale pre-trained multimodal models have achieved impressive results. Although these models provide abundant features, the authentication task-related features are often submerged. Consequently, those authentication task-irrelated features cause models to learn superficial biases, thereby harming their generalization performance across different model genera (e.g., GANs and Diffusion Models). To this end, we proposed VIB-Net, which uses Variational Information Bottlenecks to enforce authentication task-related feature learning. We tested and analyzed the proposed method and existing methods on samples generated by 17 different generative models. Compared to SOTA methods, VIB-Net achieved a 5.55% improvement in mAP and a 9.33% increase in accuracy. Notably, in generalization tests on unseen generative models from different series, VIB-Net improved mAP by 12.48% and accuracy by 23.59% over SOTA methods. The code is available at https://github.com/oceanzhf/VIBAIGCDetect.

We introduce a novel, training-free approach for enhancing alignment in Transformer-based Text-Guided Diffusion Models (TGDMs). Existing TGDMs often struggle to generate semantically aligned images, particularly when dealing with complex text prompts or multi-concept attribute binding challenges. Previous U-Net-based methods primarily optimized the latent space, but their direct application to Transformer-based architectures has shown limited effectiveness. Our method addresses these challenges by directly optimizing cross-attention maps during the generation process. Specifically, we introduce Self-Coherence Guidance, a method that dynamically refines attention maps using masks derived from previous denoising steps, ensuring precise alignment without additional training. To validate our approach, we constructed more challenging benchmarks for evaluating coarse-grained attribute binding, fine-grained attribute binding, and style binding. Experimental results demonstrate the superior performance of our method, significantly surpassing other state-of-the-art methods across all evaluated tasks. Our code is available at https://scg-diffusion.github.io/scg-diffusion.

Achieving optimal performance of video diffusion transformers within given data and compute budget is crucial due to their high training costs. This necessitates precisely determining the optimal model size and training hyperparameters before large-scale training. While scaling laws are employed in language models to predict performance, their existence and accurate derivation in visual generation models remain underexplored. In this paper, we systematically analyze scaling laws for video diffusion transformers and confirm their presence. Moreover, we discover that, unlike language models, video diffusion models are more sensitive to learning rate and batch size--two hyperparameters often not precisely modeled. To address this, we propose a new scaling law that predicts optimal hyperparameters for any model size and compute budget. Under these optimal settings, we achieve comparable performance and reduce inference costs by 40.1% compared to conventional scaling methods, within a compute budget of 1e10 TFlops. Furthermore, we establish a more generalized and precise relationship among validation loss, any model size, and compute budget. This enables performance prediction for non-optimal model sizes, which may also be appealed under practical inference cost constraints, achieving a better trade-off.

Embodied localization based on vision and natural language dialogues presents a persistent challenge in embodied intelligence. Existing methods often approach this task as an image translation problem, leveraging encoder-decoder architectures to predict heatmaps. However, these methods frequently experience a deficiency in accuracy, largely due to their heavy reliance on resolution. To address this issue, we introduce CGD, a novel framework that utilizes causality guided diffusion model to directly model coordinate distributions. Specifically, CGD employs a denoising network to regress coordinates, while integrating causal learning modules, namely back-door adjustment (BDA) and front-door adjustment (FDA) to mitigate confounders during the diffusion process. This approach reduces the dependency on high resolution for improving accuracy, while effectively minimizing spurious correlations, thereby promoting unbiased learning. By guiding the denoising process with causal adjustments, CGD offers flexible control over intensity, ensuring seamless integration with diffusion models. Experimental results demonstrate that CGD outperforms state-of-the-art methods across all metrics. Additionally, we also evaluate CGD in a multi-shot setting, achieving consistently high accuracy.

Significant progress has been made for speech-driven 3D face animation, but most works focus on learning the motion of mesh/geometry, ignoring the impact of dynamic texture. In this work, we reveal that dynamic texture plays a key role in rendering high-fidelity talking avatars, and introduce a high-resolution 4D dataset TexTalk4D, consisting of 100 minutes of audio-synced scan-level meshes with detailed 8K dynamic textures from 100 subjects. Based on the dataset, we explore the inherent correlation between motion and texture, and propose a diffusion-based framework TexTalker to simultaneously generate facial motions and dynamic textures from speech. Furthermore, we propose a novel pivot-based style injection strategy to capture the complicity of different texture and motion styles, which allows disentangled control. TexTalker, as the first method to generate audio-synced facial motion with dynamic texture, not only outperforms the prior arts in synthesising facial motions, but also produces realistic textures that are consistent with the underlying facial movements. Project page: https://xuanchenli.github.io/TexTalk/.

Diffusion models have achieved remarkable success in text-to-image generation. However, their practical applications are hindered by the misalignment between generated images and corresponding text prompts. To tackle this issue, reinforcement learning (RL) has been considered for diffusion model fine-tuning. Yet, RL's effectiveness is limited by the challenge of sparse reward, where feedback is only available at the end of the generation process. This makes it difficult to identify which actions during the denoising process contribute positively to the final generated image, potentially leading to ineffective or unnecessary denoising policies. To this end, this paper presents a novel RL-based framework that addresses the sparse reward problem when training diffusion models. Our framework, named \text B ^2\text -DiffuRL , employs two strategies: **B**ackward progressive training and **B**ranch-based sampling. For one thing, backward progressive training focuses initially on the final timesteps of the denoising process and gradually extends the training interval to earlier timesteps, easing the learning difficulty associated with sparse rewards. For another, we perform branch-based sampling for each training interval. By comparing the samples within the same branch, we can identify how much the policies of the current training interval contribute to the final image, which helps to learn effective policies instead of unnecessary ones. \text B ^2\text -DiffuRL is compatible with existing optimization algorithms. Extensive experiments demonstrate the effectiveness of \text B ^2\text -DiffuRL in improving prompt-image alignment and maintaining diversity in generated images. The code for this work is available.

Diffusion models have made breakthroughs in 3D generation tasks. Current 3D diffusion models focus on reconstructing target shape from images or a set of partial observations. While excelling in global context understanding, they struggle to capture the local details of complex shapes and limited to the occlusion and lighting conditions. To overcome these limitations, we utilize tactile images to capture the local 3D information and propose a Touch2Shape model, which leverages a touch-conditioned diffusion model to explore and reconstruct the target shape from touch. For shape reconstruction, we have developed a touch embedding module to condition the diffusion model in creating a compact representation and a touch shape fusion module to refine the reconstructed shape. For shape exploration, we combine the diffusion model with reinforcement learning to train a policy. This involves using the generated latent vector from the diffusion model to guide the touch exploration policy training through a novel reward design. Experiments validate the reconstruction quality thorough both qualitatively and quantitative analysis, and our touch exploration policy further boosts reconstruction performance.

Recent advancements in Diffusion Transformer (DiT) have demonstrated remarkable proficiency in producing high-quality video content. Nonetheless, the potential of transformer-based diffusion models for effectively generating videos with controllable motion remains an area of limited exploration. This paper introduces Tora, the first trajectory-oriented DiT framework that concurrently integrates textual, visual, and trajectory conditions, thereby enabling scalable video generation with effective motion guidance. Specifically, Tora consists of a Trajectory Extractor (TE), a Spatial-Temporal DiT, and a Motion-guidance Fuser (MGF). The TE encodes arbitrary trajectories into hierarchical spacetime motion patches with a 3D motion compression network. The MGF integrates the motion patches into the DiT blocks to generate consistent videos that accurately follow designated trajectories. Our design aligns seamlessly with DiT's scalability, allowing precise control of video content's dynamics with diverse durations, aspect ratios, and resolutions. Extensive experiments demonstrate that Tora excels in achieving high motion fidelity compared to the foundational DiT model, while also accurately simulating the complex movements of the physical world. Code is made available at https://github.com/alibaba/Tora .

Accurately modeling multi-class cell topology is crucial in digital pathology, as it provides critical insights into tissue structure and pathology. The synthetic generation of cell topology enables realistic simulations of complex tissue environments, enhances downstream tasks by augmenting training data, aligns more closely with pathologists' domain knowledge, and offers new opportunities for controlling and generalizing the tumor microenvironment. In this paper, we propose a novel approach that integrates topological constraints into a diffusion model to improve the generation of realistic, contextually accurate cell topologies. Our method refines the simulation of cell distributions and interactions, increasing the precision and interpretability of results in downstream tasks such as cell detection and classification. To assess the topological fidelity of generated layouts, we introduce a new metric, Topological Frechet Distance (TopoFD), which overcomes the limitations of traditional metrics like FID in evaluating topological structure. Experimental results demonstrate the effectiveness of our approach in generating multi-class cell layouts that capture intricate topological relationships. Code is available at https://github.com/Melon-Xu/TopoCellGen.

Human-centric motion control in video generation remains a critical challenge, particularly when jointly controlling camera movements and human poses in scenarios like the iconic Grammy Glambot moment. While recent video diffusion models have made significant progress, existing approaches struggle with limited motion representations and inadequate integration of camera and human motion controls. In this work, we present TokenMotion, the first DiT-based video diffusion framework that enables fine-grained control over camera motion, human motion, and their joint interaction. We represent camera trajectories and human poses as spatio-temporal tokens to enable local control granularity. Our approach introduces a unified modeling framework utilizing a decouple-and-fuse strategy, bridged by a human-aware dynamic mask that effectively handles the spatially varying nature of combined motion signals. Through extensive experiments, we demonstrate TokenMotion's effectiveness across both text-to-video and image-to-video paradigms, consistently outperforming current state-of-the-art methods in human-centric motion control tasks. Our work represents a significant advancement in controllable video generation, with particular relevance for creative production applications ranging from films to short-form content.

Diffusion Transformers have demonstrated remarkable capabilities in image generation but often come with excessive parameterization, resulting in considerable inference overhead in real-world applications. In this work, we present TinyFusion, a depth pruning method designed to remove redundant layers from diffusion transformers via end-to-end learning. The core principle of our approach is to create a pruned model with high recoverability, allowing it to regain strong performance after fine-tuning. To accomplish this, we introduce a differentiable sampling technique to make pruning learnable, paired with a co-optimized parameter to simulate future fine-tuning. While prior works focus on minimizing loss or error after pruning, our method explicitly models and optimizes the post-fine-tuning performance of pruned models. Experimental results indicate that this learnable paradigm offers substantial benefits for layer pruning of diffusion transformers, surpassing existing importance-based and error-based methods. Additionally, TinyFusion exhibits strong generalization across diverse architectures, such as DiTs, MARs, and SiTs. Experiments with DiT-XL show that TinyFusion can craft a shallow diffusion transformer at less than 7% of the pre-training cost, achieving a 2xspeedup with an FID score of 2.86, outperforming competitors with comparable efficiency. Code is available at https://github.com/VainF/TinyFusion

As a fundamental backbone for video generation, diffusion models are challenged by low inference speed due to the sequential nature of denoising.Previous methods speed up the models by caching and reusing model outputs at uniformly selected timesteps.However, such a strategy neglects the fact that differences among model outputs are not uniform across timesteps, which hinders selecting the appropriate model outputs to cache, leading to a poor balance between inference efficiency and visual quality.In this study, we introduce Timestep Embedding Aware Cache (TeaCache), a training-free caching approach that estimates and leverages the fluctuating differences among model outputs across timesteps.Rather than directly using the time-consuming model outputs, TeaCache focuses on model inputs, which have a strong correlation with the modeloutputs while incurring negligible computational cost.TeaCache first modulates the noisy inputs using the timestep embeddings to ensure their differences better approximating those of model outputs. TeaCache then introduces a rescaling strategy to refine the estimated differences and utilizes them to indicate output caching.Experiments show that TeaCache achieves up to 4.41xacceleration over Open-Sora-Plan with negligible (-0.07% Vbench score) degradation of visual quality.