CVPR 2025 Papers

We address the challenge of generating dynamic 4D scenes from monocular multi-object videos with heavy occlusions and introduce Robust4DGen, a novel approach that integrates rendering-based deformable 3D Gaussian optimization with generative priors for view synthesis. While existing view-synthesis models excel at novel view generation for isolated objects, they struggle with full scenes due to their complexity and data demands. To overcome this, Robust4DGen decomposes scenes into individual objects, optimizing a differentiable set of deformable Gaussians per object while capturing 2D occlusions from a 3D perspective through joint Gaussian splatting. Joint splatting ensures occlusion-aware rendering losses in observed frames while explicit object decomposition allows the usage of object-centric diffusion models for object completion in unobserved viewpoints. To reconcile the differences between object-centric priors and the global frame-centric coordinate system of the video, Robust4DGen employs differentiable transformations to unify the rendering and generative constraints within a single framework. The result is a model capable of generating 4D objects across space and time while producing 2D and 3D point tracks from monocular videos. To rigorously evaluate the quality of scene generation and the accuracy of the motion under multi-object occlusions, we introduce MOSE-PTS, a subset of the challenging MOSE benchmark, which we annotated with high-quality 2D point tracks. Quantitative evaluations and perceptual human studies confirm that Robust4DGen generates more realistic novel views of scenes and produces more accurate point tracks compared to existing approaches.

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

Recent research has shown that fine-tuning diffusion models (DMs) with arbitrary rewards, including non-differentiable ones, is feasible with reinforcement learning (RL) techniques, enabling flexible model alignment. However, applying existing RL methods to step-distilled DMs is challenging for ultra-fast (<=2-step) image generation. Our analysis suggests several limitations of policy-based RL methods such as PPO or DPO toward this goal. Based on the insights, we propose fine-tuning DMs with learned differentiable surrogate rewards. Our method, named LaSRO, learns surrogate reward models in the latent space of SDXL to convert arbitrary rewards into differentiable ones for effective reward gradient guidance. LaSRO leverages pre-trained latent DMs for reward modeling and tailors reward optimization for <=2-step image generation with efficient off-policy exploration. LaSRO is effective and stable for improving ultra-fast image generation with different reward objectives, outperforming popular RL methods including DDPO and Diffusion-DPO. We further show LaSRO's connection to value-based RL, providing theoretical insights. See our webpage at https://sites.google.com/view/lasro.

Generative replay has gained significant attention in class-incremental learning; however, its application to Class Incremental Object Detection (CIOD) remains limited due to the challenges in generating complex images with precise spatial arrangements. In this study, motivated by the observation that the forgetting of prior knowledge is predominantly present in the classification sub-task as opposed to the localization sub-task, we revisit the generative replay method for class incremental object detection. Our method utilize a standard Stable Diffusion model to generate image-level replay data for all old and new tasks. Accordingly, the old detector and a stage-wise detector are conducted on the synthetic images respectively to determine the bounding box positions through pseudo-labeling. Furthermore, we propose to use a Similarity-based Cross Sampling mechanism to select more valuable confusing data between old and new tasks to more effectively mitigate catastrophic forgetting and reduce the false alarm rate for the new task. Finally, all synthetic and real data are integrated for current-stage detector training, where the images generated for previous tasks are highly beneficial in minimizing the forgetting of existing knowledge, while those synthesized for the new task can help bridge the domain gap between real and synthetic images. We conducted extensive experiments on PASCAL VOC 2007 and MS COCO benchmark datasets in multiple settings to showcase the efficacy of our proposed approach, which achieves state-of-the-art results. The code are available at https://github.com/qiangzai-lv/RGR-IOD.

Image restoration aims to recover high-quality (HQ) images from degraded low-quality (LQ) ones by reversing the effects of degradation. Existing generative models for image restoration, including diffusion and score-based models, often treat the degradation process as a stochastic transformation, which introduces inefficiency and complexity. In this work, we propose ResFlow, a novel image restoration framework that models the degradation process as a deterministic path using continuous normalizing flows. ResFlow augments the degradation process with an auxiliary process that disambiguates the uncertainty in HQ prediction to enable reversible modeling of the degradation process. ResFlow adopts entropy-preserving flow paths and learns the augmented degradation flow by matching the velocity field. ResFlow significantly improves the performance and speed of image restoration, completing the task in fewer than four sampling steps. Extensive experiments demonstrate that ResFlow achieves state-of-the-art results across various image restoration benchmarks, offering a practical and efficient solution for real-world applications.

Since 2023, Vector Quantization (VQ)-based discrete generation methods have rapidly dominated human motion generation, primarily surpassing diffusion-based continuous generation methods in standard performance metrics. However, VQ-based methods have inherent limitations. Representing continuous motion data as limited discrete tokens leads to inevitable information loss, reduces the diversity of generated motions, and restricts their ability to function effectively as motion priors or generation guidance. In contrast, the continuous space generation nature of diffusion-based methods makes them well-suited to address these limitations and with even potential for model scalability. In this work, we systematically investigate why current VQ-based methods perform well and explore the limitations of existing diffusion-based methods from the perspective of motion data representation and distribution. Drawing on these insights, we preserve the inherent strengths of a diffusion-based human motion generation model and gradually optimize it with inspiration from VQ-based approaches. Our approach introduces a human motion diffusion model enabled to perform masked autoregression, optimized with a reformed data representation and distribution. Additionally, we propose a more robust evaluation method to assess different approaches. Extensive experiments on various datasets demonstrate our method outperforms previous methods and achieves state-of-the-art performances.

Video Frame Interpolation aims to recover realistic missing frames between observed frames, generating a high-frame-rate video from a low-frame-rate video. However, without additional guidance, large motion between frames makes this problem ill-posed. Event-based Video Frame Interpolation (EVFI) addresses this challenge by using sparse, high-temporal-resolution event measurements as motion guidance. This guidance allows EVFI methods to significantly outperform frame-only methods. However, to date, EVFI methods have relied upon a limited set of paired event-frame training data, severely limiting their performance and generalization capabilities. In this work, we overcome the limited data challenge by adapting pre-trained video diffusion models trained on internet-scale datasets to EVFI. We experimentally validate our approach on real-world EVFI datasets, including a new one we introduce. Our method outperforms existing methods and generalizes across cameras far better than existing approaches.

Creative remains an inherently abstract concept for both humans and diffusion models. While text-to-image (T2I) diffusion models can easily generate out-of-distribution concepts like "a blue banana", they struggle with generating combinatorial objects such as "a creative mixture that resembles a lettuce and a mantis", due to difficulties in understanding the semantic depth of "creative". Current methods rely heavily on synthesizing reference prompts or images to achieve a creative effect, typically requiring retraining for each unique creative output-a process that is computationally intensive and limits practical applications. To address this, we introduce CreTok, which brings meta-creativity to diffusion models by redefining "creative" as a new token, <CreTok>, thus enhancing models' semantic understanding for combinatorial creativity. CreTok achieves such redefinition by iteratively sampling diverse text pairs from our proposed CangJie dataset to form adaptive prompts and restrictive prompts, and then optimizing the similarity between their respective text embeddings. Extensive experiments demonstrate that <CreTok> enables the universal and direct generation of combinatorial creativity across diverse concepts without additional training, achieving state-of-the-art performance with improved text-image alignment and higher human preference ratings. Code will be made available at https://github.com/fu-feng/CreTok.

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 ReCFG with 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.

Latent diffusion models with Transformer architectures excel at generating high-fidelity images. However, recent studies reveal an optimization dilemma in this two-stage design: while increasing the per-token feature dimension in visual tokenizers improves reconstruction quality, it requires substantially larger diffusion models and more training iterations to achieve comparable generation performance. Consequently, existing systems often settle for sub-optimal solutions, either producing visual artifacts due to information loss within tokenizers or failing to converge fully due to expensive computation costs. We argue that this dilemma stems from the inherent difficulty in learning unconstrained high-dimensional latent spaces. To address this, we propose aligning the latent space with pre-trained vision foundation models when training the visual tokenizers. Our proposed VA-VAE (Vision foundation model Aligned Variational AutoEncoder) significantly expands the reconstruction-generation frontier of latent diffusion models, enabling faster convergence of Diffusion Transformers (DiT) in high-dimensional latent spaces. To exploit the full potential of VA-VAE, we build an enhanced DiT baseline with improved training strategies and architecture designs, termed LightningDiT. The integrated system achieves state-of-the-art (SOTA) performance on ImageNet 256 generation with an FID score of 1.35 while demonstrating remarkable training efficiency by reaching an FID score of 2.11 in just 64 epochs -- representing an over 21 times convergence speedup compared to the original DiT. Models and codes are available at https://github.com/hustvl/LightningDiT.

Due to visual ambiguities and inter-person occlusions, existing human pose estimation methods cannot recover plausible close interactions from in-the-wild videos. Even state-of-the-art large foundation models (e.g., SAM) cannot accurately distinguish human semantics in such challenging scenarios. In this work, we find that human appearance can provide a straightforward cue to address these obstacles. Based on this observation, we propose a dual-branch optimization framework to reconstruct accurate interactive motions with plausible body contacts constrained by human appearances, social proxemics, and physical laws. Specifically, we first train a diffusion model to learn the human proxemic behavior and pose prior knowledge. The trained network and two optimizable tensors are then incorporated into a dual-branch optimization framework to reconstruct human motions and appearances. Several constraints based on 3D Gaussians, 2D keypoints, and mesh penetrations are also designed to assist the optimization. With the proxemics prior and diverse constraints, our method is capable of estimating accurate interactions from in-the-wild videos captured in complex environments. We further build a dataset with pseudo ground-truth interaction annotations, which may promote future research on pose estimation and human behavior understanding. Experimental results on several benchmarks demonstrate that our method outperforms existing approaches. The code and data are available at https://www.buzhenhuang.com/works/CloseApp.html.

Plug-and-play (PnP) methods offer an iterative strategy for solving image restoration (IR) problems in a zero-shot manner, using a learned discriminative denoiser as the implicit prior. More recently, a sampling-based variant of this approach, which utilizes a pre-trained generative diffusion model, has gained great popularity for solving IR problems through stochastic sampling. The IR results using PnP with a pre-trained diffusion model demonstrate distinct advantages compared to those using discriminative denoisers, i.e., improved perceptual quality while sacrificing the data fidelity. The unsatisfactory results are due to the lack of integration of these strategies in the IR tasks. In this work, we propose a novel zero-shot IR scheme, dubbed Reconciling Diffusion Model in Dual (RDMD), which leverages only a single pre-trained diffusion model to construct two complementary regularizers. Specifically, the diffusion model in RDMD will iteratively perform deterministic denoising and stochastic sampling, aiming to achieve high-fidelity image restoration with appealing perceptual quality.RDMD also allows users to customize the distortion-perception tradeoff with a single hyperparameter, enhancing the adaptability of the restoration process in different practical scenarios. Extensive experiments on several IR tasks demonstrate that our proposed method could achieve superior results compared to existing approaches on both the FFHQ and ImageNet datasets.

While computer vision models have made incredible strides in static image recognition, they still do not match human performance in tasks that require the understanding of complex, dynamic motion. This is notably true for real-world scenarios where embodied agents face complex and motion-rich environments. Our approach, BrainNRDS (Brain-Neural Representations of Dynamic Stimuli), leverages state-of-the-art video diffusion models to decouple static image representation from motion generation, enabling us to utilize fMRI brain activity for a deeper understanding of human responses to dynamic visual stimuli. Conversely, we also demonstrate that information about the brain's representation of motion can enhance the prediction of optical flow in artificial systems. Our novel approach leads to four main findings: (1) Visual motion, represented as fine-grained, object-level resolution optical flow, can be decoded from brain activity generated by participants viewing video stimuli; (2) Video encoders outperform image-based models in predicting video-driven brain activity; (3) Brain-decoded motion signals enable realistic video reanimation based only on the initial frame of the video; and (4) We extend prior work to achieve full video decoding from video-driven brain activity. BrainNRDS advances our understanding of how the brain represents spatial and temporal information in dynamic visual scenes. Our findings demonstrate the potential of combining brain imaging with video diffusion models for developing more robust and biologically-inspired computer vision systems. We show additional decoding and encoding examples on this site: https://brain-nrds.github.io/.

The diffusion model has been successfully applied to various detection tasks. However, it still faces several challenges when used for oriented object detection: objects that are arbitrarily rotated require the diffusion model to encode their orientation information; uncontrollable random boxes inaccurately locate objects with dense arrangements and extreme aspect ratios; oriented boxes result in the misalignment between them and image features. To overcome these limitations, we propose ReDiffDet, a framework that formulates oriented object detection as a rotation-equivariant denoising diffusion process. First, we represent an oriented box as a 2D Gaussian distribution, forming the basis of the denoising paradigm. The reverse process can be proven to be rotation-equivariant within this representation and model framework. Second, we design a conditional encoder with conditional boxes to prevent boxes from being randomly placed across the entire image. Third, we propose an aligned decoder for alignment between oriented boxes and image features. The extensive experiments demonstrate ReDiffDet achieves promising performance and significantly outperforms the diffusion-based baseline detector.

Recently, breakthroughs in video modeling have allowed for controllable camera trajectories in generated videos. However, these methods cannot be directly applied to user-provided videos that are not generated by a video model. In this paper, we present ReCapture, a method for generating new videos with novel camera trajectories from a single user-provided video. Our method allows us to re-generate the reference video, with all its existing scene motion, from vastly different angles and with cinematic camera motion. Notably, using our method we can also plausibly hallucinate parts of the scene that were not observable in the reference video. Our method works by (1) generating a noisy anchor video with a new camera trajectory using multiview diffusion models or depth-based point cloud rendering and then (2) regenerating the anchor video into a clean and temporally consistent reangled video using our proposed masked video fine-tuning technique.

Current digital human studies focusing on lip-syncing and body movement are no longer sufficient to meet the growing industrial demand, while human video generation techniques that support interacting with real-world environments (e.g., objects) have not been well investigated. Despite human hand synthesis already being an intricate problem, generating objects in contact with hands and their interactions presents an even more challenging task, especially when the objects exhibit obvious variations in size and shape. To tackle these issues, we present a novel video Reenactment framework focusing on Human-Object Interaction (HOI) via an adaptive Layout-instructed Diffusion model (Re-HOLD). Our key insight is to employ specialized layout representation for hands and objects, respectively. Such representations enable effective disentanglement of hand modeling and object adaptation to diverse motion sequences. To further improve the generation quality of HOI, we design an interactive textural enhancement module for both hands and objects by introducing two independent memory banks. We also propose a layout adjustment strategy for the cross-object reenactment scenario to adaptively adjust unreasonable layouts caused by diverse object sizes during inference. Comprehensive qualitative and quantitative evaluations demonstrate that our proposed framework significantly outperforms existing methods. Project page: https://fyycs.github.io/Re-HOLD.

Diffusion models have achieved remarkable success across various domains. However, their slow generation speed remains a critical challenge. Existing acceleration methods, while aiming to reduce steps, often compromise sample quality, controllability, or introduce training complexities. Therefore, we propose \underline RayFlow , a novel diffusion framework that addresses these limitations. Unlike previous methods, RayFlow guides each sample along a unique path towards an instance-specific target distribution. This method minimizes sampling steps while preserving generation diversity and stability. Furthermore, we introduce Time Sampler, an importance sampling technique to enhance training efficiency by focusing on crucial timesteps. Extensive experiments demonstrate RayFlow's superiority in generating high-quality images with improved speed, control, and training efficiency compared to existing acceleration techniques.

Diffusion models generate high-quality images through progressive denoising but are computationally intensive due to large model sizes and repeated sampling. Knowledge distillation--transferring knowledge from a complex teacher to a simpler student model--has been widely studied in recognition tasks, particularly for transferring concepts unseen during student training. However, its application to diffusion models remains underexplored, especially in enabling student models to generate concepts not covered by the training images. In this work, we propose Random Conditioning, a novel approach that pairs noised images with randomly selected text conditions to enable efficient, image-free knowledge distillation. By leveraging this technique, we show that the student can generate concepts unseen in the training images. When applied to conditional diffusion model distillation, our method allows the student to explore the condition space without generating condition-specific images, resulting in notable improvements in both generation quality and efficiency. This promotes resource-efficient deployment of generative diffusion models, broadening their accessibility for both research and real-world applications. Code, models, and datasets are available at: https://dohyun-as.github.io/Random-Conditioning