CVPR 2025 论文列表

The image-to-image translation abilities of generative learning models have recently made significant progress in the estimation of complex (steered) mappings between image distributions. While appearance based tasks like image in-painting or style transfer have been studied at length, we propose to investigate the potential of generative models in the context of physical simulations. Providing a dataset of 300k image-pairs and baseline evaluations for three different physical simulation tasks, we propose a benchmark to investigate the following research questions: i) are generative models able to learn complex physical relations from input-output image pairs? ii) what speedups can be achieved by replacing differential equation based simulations? While baseline evaluations of different current models show the potential for high speedups (ii), these results also show strong limitations toward the physical correctness (i). This underlines the need for new methods to enforce physical correctness.

Humans can predict future human trajectories even from momentary observations by using human pose-related cues. However, previous Human Trajectory Prediction (HTP) methods leverage the pose cues implicitly, resulting in implausible predictions. To address this, we propose Locomotion Embodiment, a framework that explicitly evaluates the physical plausibility of the predicted trajectory by locomotion generation under the laws of physics. While the plausibility of locomotion is learned with an indifferentiable physics simulator, it is replaced by our differentiable Locomotion Value function to train an HTP network in a data-driven manner. In particular, our proposed Embodied Locomotion loss is beneficial for efficiently training a stochastic HTP network using multiple heads. Furthermore, the Locomotion Value filter is proposed to filter out implausible trajectories at inference. Experiments demonstrate that our method enhances even the state-of-the-art HTP methods across diverse datasets and problem settings. Our code is available at: https://github.com/ImIntheMiddle/EmLoco.

Understanding the environment and a robot's physical reachability is crucial for task execution. While state-of-the-art vision-language models (VLMs) excel in environmental perception, they often generate inaccurate or impractical responses in embodied visual reasoning tasks due to a lack of understanding of robotic physical reachability. To address this issue, we propose a unified representation of physical reachability across diverse robots, i.e., Space-Physical Reachability Map (S-P Map), and PhysVLM, a vision-language model that integrates this reachability information into visual reasoning. Specifically, the S-P Map abstracts a robot's physical reachability into a generalized spatial representation, independent of specific robot configurations, allowing the model to focus on reachability features rather than robot-specific parameters. Subsequently, PhysVLM extends traditional VLM architectures by incorporating an additional feature encoder to process the S-P Map, enabling the model to reason about physical reachability without compromising its general vision-language capabilities. To train and evaluate PhysVLM, we constructed a large-scale multi-robot dataset, Phys100K, and a challenging benchmark, EQA-phys, which includes tasks for six different robots in both simulated and real-world environments. Experimental results demonstrate that PhysVLM outperforms existing models, achieving a 14% improvement over GPT-4o on EQA-phys and surpassing advanced embodied VLMs such as RoboMamba and SpatialVLM on the RoboVQA-val and OpenEQA benchmarks. Additionally, the S-P Map shows strong compatibility with various VLMs, and its integration into GPT-4o-mini yields a 7.1% performance improvement.

Envisioning physically plausible outcomes from a single image requires a deep understanding of the world's dynamics. To address this, we introduce MiniTwin, a novel framework that transforms a single image into an amodal, camera-centric, interactive 3D scene. By combining advanced image-based geometric and semantic understanding with physics-based simulation, MiniTwin creates an interactive 3D world from a static image, enabling us to "imagine" and simulate future scenarios based on user input. At its core, MiniTwin estimates 3D shapes, poses, physical and lighting properties of objects, thereby capturing essential physical attributes that drive realistic object interactions. This framework allows users to specify precise initial conditions, such as object speed or material properties, for enhanced control over generated video outcomes. We evaluate MiniTwin's performance against closed-source state-of-the-art (SOTA) image-to-video models, including Pika, Kling, and Gen-3, showing MiniTwin's capacity to generate videos with realistic physics while offering greater flexibility and fine-grained control. Our results show that MiniTwin achieves a unique balance of photorealism, physical plausibility, and user-driven interactivity, opening new possibilities for generating dynamic, physics-grounded video from an image.

Creating hand-drawn animation sequences is labor-intensive and demands professional expertise. We introduce PhysAnimator, a novel approach for generating physically plausible meanwhile anime-stylized animation from static anime illustrations. Our method seamlessly integrates physics-based simulations with data-driven generative models to produce dynamic and visually compelling animations. To capture the fluidity and exaggeration characteristic of anime, we perform image-space deformable body simulations on extracted mesh geometries. We enhance artistic control by introducing customizable energy strokes and incorporating rigging point support, enabling the creation of tailored animation effects such as wind interactions. Finally, we extract and warp sketches from the simulation sequence, generating a texture-agnostic representation, and employ a sketch-guided video diffusion model to synthesize high-quality animation frames. The resulting animations exhibit temporal consistency and visual plausibility, demonstrating the effectiveness of our method in creating dynamic anime-style animations.

Text-to-video (T2V) generation has been recently enabled by transformer-based diffusion models, but current T2V models lack capabilities in adhering to the real-world common knowledge and physical rules, due to their limited understanding of physical realism and deficiency in temporal modeling. Existing solutions are either data-driven or require extra model inputs, but cannot be generalizable to out-of-distribution domains. In this paper, we present PhyT2V, a new data-independent T2V technique that expands the current T2V model's capability of video generation to out-of-distribution domains, by enabling chain-of-thought and step-back reasoning in T2V prompting. Our experiments show that PhyT2V improves existing T2V models' adherence to real-world physical rules by 2.3x, and achieves 35% improvement compared to T2V prompt enhancers.

Achieving joint control over material properties, lighting, and high-level semantics in images is essential for applications in digital media, advertising, and interactive design. Existing methods often isolate these properties, lacking a cohesive approach to manipulating materials, lighting, and semantics simultaneously. We introduce PhyS-EdiT, a novel diffusion-based model that enables precise control over four critical material properties: roughness, metallicity, albedo, and transparency while integrating lighting and semantic adjustments within a single framework. To facilitate this disentangled control, we present PR-TIPS, a large and diverse synthetic dataset designed to improve the disentanglement of material and lighting effects. PhyS-EdiT incorporates a dual-network architecture and robust training strategies to balance low-level physical realism with high-level semantic coherence, supporting localized and continuous property adjustments. Extensive experiments demonstrate the superiority of PhyS-EdiT in editing both synthetic and real-world images, achieving state-of-the-art performance on material, lighting, and semantic editing tasks.

Building a generalizable self-correction system is crucial for robots to recover from failures. Despite advancements in Multimodal Large Language Models (MLLMs) that empower robots with semantic reflection ability for failure, translating semantic reflection into how to correct fine-grained robotic actions remains a significant challenge. To address this gap, we build the Phoenix framework, which leverages motion instruction as a bridge to connect high-level semantic reflection with low-level robotic action correction. In this motion-based self-reflection framework, we start with a dual-process motion adjustment mechanism with MLLMs to translate the semantic reflection into coarse-grained motion instruction adjustment. To leverage this motion instruction for guiding how to correct fine-grained robotic actions, a multi-task motion-conditioned diffusion policy is proposed to integrate visual observations for high-frequency robotic action correction. By combining these two models, we could shift the demand for generalization capability from the low-level manipulation policy to the MLLMs-driven motion adjustment model and facilitate precise, fine-grained robotic action correction. Utilizing this framework, we further develop a lifelong learning method to automatically improve the model's capability from interactions with dynamic environments. The experiments conducted in both the RoboMimic simulation and real-world scenarios prove the superior generalization and robustness of our framework across a variety of manipulation tasks.

Multimodal Large Language Models (MLLMs) hallucinate, resulting in an emerging topic of visual hallucination evaluation (VHE). This paper contributes a ChatGPT-Prompted visual hallucination evaluation Dataset (PhD) for objective VHE at a large scale. The essence of VHE is to ask an MLLM questions about specific images to assess its susceptibility to hallucination. Depending on what to ask (objects, attributes, sentiment, etc.) and how the questions are asked, we structure PhD along two dimensions, i.e. task and mode. Five visual recognition tasks, ranging from low-level (object / attribute recognition) to middle-level (sentiment / position recognition and counting), are considered. Besides a normal visual QA mode, which we term PhD-base, PhD also asks questions with specious context (PhD-sec) or with incorrect context (PhD-icc), or with AI-generated counter common sense images (PhD-ccs). We construct PhD by a ChatGPT-assisted semi-automated pipeline, encompassing four pivotal modules: task-specific hallucinatory item (hitem) selection, hitem-embedded question generation, specious / incorrect context generation, and counter-common-sense (CCS) image generation. With over 14k daily images, 750 CCS images and 102k VQA triplets in total, PhD reveals considerable variability in MLLMs' performance across various modes and tasks, offering valuable insights into the nature of hallucination. As such, PhD stands as a potent tool not only for VHE but may also play a significant role in the refinement of MLLMs.

Recent advancements in text-based diffusion models have accelerated progress in 3D reconstruction and text-based 3D editing. Although existing 3D editing methods excel at modifying color, texture, and style, they struggle with extensive geometric or appearance changes, thus limiting their applications. To this end, we propose Perturb-and-Revise, which makes possible a variety of NeRF editing. First, we perturb the NeRF parameters with random initializations to create a versatile initialization. The level of perturbation is determined automatically through analysis of the local loss landscape. Then, we revise the edited NeRF via generative trajectories. Combined with the generative process, we impose identity-preserving gradients to refine the edited NeRF. Extensive experiments demonstrate that Perturb-and-Revise facilitates flexible, effective, and consistent editing of color, appearance, and geometry in 3D. For 360deg results, please visit our project page: https://susunghong.github.io/Perturb-and-Revise.

RLHF techniques like DPO can significantly improve the generation quality of text-to-image diffusion models. However, these methods optimize for a single reward that aligns model generation with population-level preferences, neglecting the nuances of individual users' beliefs or values. This lack of personalization limits the efficacy of these models. To bridge this gap, we introduce PPD, a multi-reward optimization objective that aligns diffusion models with personalized preferences. With PPD, a diffusion model learns the individual preferences of a population of users in a few-shot way, enabling generalization to unseen users. Specifically, our approach (1) leverages a vision-language model (VLM) to extract personal preference embeddings from a small set of pairwise preference examples, and then (2) incorporates the embeddings into diffusion models through cross attention. Conditioning on user embeddings, the text-to-image models are fine-tuned with the DPO objective, simultaneously optimizing for alignment with the preferences of multiple users. Empirical results demonstrate that our method effectively optimizes for multiple reward functions and can interpolate between them during inference. In real-world user scenarios, with as few as four preference examples from a new user, our approach achieves an average win rate of 76% over Stable Cascade, generating images that more accurately reflect specific user preferences.

We introduce PersonaHOI, a training- and tuning-free framework that fuses a general StableDiffusion model with a personalized face diffusion (PFD) model to generate identity-consistent human-object interaction (HOI) images. While existing PFD models have advanced significantly, they often overemphasize facial features at the expense of full-body coherence, PersonaHOI introduces an additional StableDiffusion (SD) branch guided by HOI-oriented text inputs. By incorporating cross-attention constraints in the PFD branch and spatial merging at both latent and residual levels, PersonaHOI preserves personalized facial details while ensuring interactive non-facial regions. Experiments, validated by a novel interaction alignment metric, demonstrate the superior realism and scalability of PersonaHOI, establishing a new standard for practical personalized face with HOI generation. Code is available at https://github.com/JoyHuYY1412/PersonaHOI.

This paper introduces Motion Personalization, a new task that generates personalized motions aligned with text descriptions using several basic motions containing Persona. To support this novel task, we introduce a new large-scale motion dataset called PerMo (PersonaMotion), which captures the unique personas of multiple actors. We also propose a multi-modal finetuning method of a pretrained motion diffusion model called PersonaBooth. PersonaBooth addresses two main challenges: i) A significant distribution gap between the persona-focused PerMo dataset and the pretraining datasets, which lack persona-specific data, and ii) the difficulty of capturing a consistent persona from the motions vary in content (action type). To tackle the dataset distribution gap, we introduce a persona token to accept new persona features and perform multi-modal adaptation for both text and visuals during finetuning. To capture a consistent persona, we incorporate a contrastive learning technique to enhance intra-cohesion among samples with the same persona. Furthermore, we introduce a context-aware fusion mechanism to maximize the integration of persona cues from multiple input motions. PersonaBooth outperforms state-of-the-art motion style transfer methods, establishing a new benchmark for motion personalization.

Person re-identification (ReID) is to associate images of individuals from different camera views against cross-view variations. Like other surveillance technologies, Re-ID faces serious privacy challenges, particularly the potential for unauthorized tracking. Although various tasks (e.g., face recognition) have developed machine unlearning techniques to address privacy concerns, such methods have not yet been explored within the Re-ID field. In this work, we pioneer the exploration of the person de-reidentification (De-ReID) problem and present its inherent challenges. In the context of ReID, De-ReID is to unlearn the knowledge about accurately matching specific persons so that these "unlearned persons" cannot be re-identified across cameras for privacy guarantee. The primary challenge is to achieve the unlearning without degrading the identity-discriminative feature embeddings to ensure the model's utility. To address this, we formulate a De-ReID framework that utilizes a labeled dataset of unlearned persons for unlearning and an unlabeled dataset of accessible persons for knowledge preservation. Instead of unlearning based on (pseudo) identity labels, we introduce a variation-guided identity shift mechanism that unlearns the specific persons by fitting the variations in their images while preserving ReID ability on other persons by overcoming the variations in images of accessible persons. As a result, the model shifts the unlearned persons to a feature space that is vulnerable to cross-view variations. Extensive experiments on benchmarks demonstrate the superiority of our method.

Periodic or quasi-periodic phenomena reveal intrinsic characteristics in various natural processes, such as weather patterns, movement behaviors, traffic flows, and biological signals. Given that these phenomena span multiple modalities, the capabilities of Multimodal Large Language Models (MLLMs) offer promising potential to effectively capture and understand their complex nature. However, current MLLMs struggle with periodic tasks due to limitations in: 1) lack of temporal modelling and 2) conflict between short and long periods. This paper introduces Period-LLM, a multimodal large language model designed to enhance the performance of periodic tasks across various modalities, and constructs a benchmark of various difficulty for evaluating the cross-modal periodic capabilities of large models. Specially, We adopt an "Easy to Hard Generalization" paradigm, starting with relatively simple text-based tasks and progressing to more complex visual and multimodal tasks, ensuring that the model gradually builds robust periodic reasoning capabilities. Additionally, we propose a "Resisting Logical Oblivion" optimization strategy to maintain periodic reasoning abilities during semantic alignment. Extensive experiments demonstrate the superiority of the proposed Period-LLM over existing MLLMs in periodic tasks. The code is available at https://github.com/keke-nice/Period-LLM.

Recent advancements in speech-driven 3D talking head generation have made significant progress in lip synchronization. However, existing models still struggle to capture the perceptual alignment between varying speech characteristics and corresponding lip movements. In this work, we claim that three criteria--Temporal Synchronization, Lip Readability, and Expressiveness--are crucial for achieving perceptually accurate lip movements. Motivated by our hypothesis that a desirable representation space exists to meet these three criteria, we introduce a speech-mesh synchronized representation that captures intricate correspondences between speech signals and 3D face meshes. We found that our learned representation exhibits desirable characteristics, and we plug it into existing models as a perceptual loss to better align lip movements to the given speech. In addition, we utilize this representation as a perceptual metric and introduce two other physically grounded lip synchronization metrics to assess how well the generated 3D talking heads align with these three criteria. Experiments show that training 3D talking head generation models with our perceptual loss significantly improve all three aspects of perceptually accurate lip synchronization. Codes and datasets are available at https://perceptual-3d-talking-head.github.io/.

Standard video codecs are rate-distortion optimization machines, where distortion is typically quantified using PSNR versus the source. However, it is now widely accepted that increasing PSNR does not necessarily translate to better visual quality. In this paper, a better balance between perception and fidelity is targeted, in order to provide for significant rate savings over state-of-the-art standards-based video codecs. Specifically, pre- and postprocessing neural networks are proposed that enhance the coding efficiency of standard video codecs when benchmarked with an array of well-established perceptual quality scores. These "neural wrapper" elements are end-to-end trained with a neural codec module serving as a differentiable proxy for standard video codecs. The codec proxy is jointly optimized with the pre- and post components, via a novel two-phase pretraining strategy and end-to-end iterative refinement with stop-gradient. This allows the neural pre- and postprocessor to learn to embed, remove and recover information in a codec-aware manner, thus improving its rate-quality performance. A single neural-wrapper model is thereby established and used for the entire rate-quality curve without needing any downscaling or upscaling. The trained model is tested with the AV1 and VVC standard codecs via an array of well-established objective quality scores (SSIM, MS-SSIM, VMAF, AVQT), as well as mean opinion scores (MOS) derived from ITU-T P.910 subjective testing. Experimental results show that the proposed approach improves all quality scores, with -18.5% average Bjontegaard Delta-rate (BD-rate) saving over all objective scores and MOS improvement over both standard codecs. This illustrates the significant potential of neural wrapper components over standards-based video coding.

David Marr's seminal theory of human perception stipulates that visual processing is a multi-stage process, prioritizing the derivation of boundary and surface properties before forming semantic object representations. In contrast, contrastive representation learning frameworks typically bypass this explicit multi-stage approach, defining their objective as the direct learning of a semantic representation space for objects. While effective in general contexts, this approach sacrifices the inductive biases of vision, leading to slower convergence speed and learning shortcut resulting in texture bias. In this work, we demonstrate that leveraging Marr's multi-stage theory--by first constructing boundary and surface-level representations using perceptual constructs from early visual processing stages and subsequently training for object semantics--leads to 2x faster convergence on ResNet18, improved final representations on semantic segmentation, depth estimation, and object recognition, and enhanced robustness and out-of-distribution capability. Together, we propose a pretraining stage before the general contrastive representation pretraining to further enhance the final representation quality and reduce the overall convergence time via inductive bias from human vision systems.

Multimodal language models (MLMs) still face challenges in fundamental visual perception tasks where specialized models excel. Tasks requiring reasoning about 3D structures benefit from depth estimation, and reasoning about 2D object instances benefits from object detection. Yet, MLMs can not produce intermediate depth or boxes to reason over. Finetuning MLMs on relevant data doesn't generalize well and outsourcing computation to specialized vision tools is too compute-intensive and memory-inefficient. To address this, we introduce Perception Tokens, intrinsic image representations designed to assist reasoning tasks where language is insufficient. Perception tokens act as auxiliary reasoning tokens, akin to chain-of-thought prompts in language models. For example, in a depth-related task, an MLM augmented with perception tokens can reason by generating a depth map as tokens, enabling it to solve the problem effectively. We propose AURORA, a training method that augments MLMs with perception tokens for improved reasoning over visual inputs. AUROA leverages a VQVAE to transform intermediate image representations, such as depth maps into a tokenized format and bounding box tokens, which is then used in a multi-task training framework. AURORA achieves notable improvements across counting benchmarks: +10.8% on BLINK, +11.3% on CVBench, and +8.3% on SEED-Bench, outperforming finetuning approaches in generalization across datasets. It also improves on relative depth: over +6% on BLINK. With perception tokens, AURORA expands the scope of MLMs beyond language-based reasoning, paving the way for more effective visual reasoning capabilities. Code and data will be released at the https://aurora-perception.github.io.