CVPR 2025 论文列表

We propose a diffusion-based inverse rendering framework that decomposes a single RGB image into geometry, material, and lighting. Inverse rendering is inherently ill-posed, making it difficult to predict a single accurate solution. To address this challenge, recent generative model-based methods aim to present a range of possible solutions. However, finding a single accurate solution and generating diverse solutions can be conflicting. In this paper, we propose a channel-wise noise scheduling approach that allows a single diffusion model architecture to achieve two conflicting objectives. The resulting two diffusion models, trained with different channel-wise noise schedules, can predict a single highly accurate solution and present multiple possible solutions. The experimental results demonstrate the superiority of our two models in terms of both diversity and accuracy, which translates to enhanced performance in downstream applications such as object insertion and material editing.

Recently, deep image deraining models based on paired datasets have made a series of remarkable progress. However, they cannot be well applied in real-world applications due to the difficulty of obtaining real paired datasets and the poor generalization performance. In this paper, we propose a novel Channel Consistency Prior and Self-Reconstruction Strategy Based Unsupervised Image Deraining framework, CSUD, to tackle the aforementioned challenges. During training with unpaired data, CSUD is capable of generating high-quality pseudo clean and rainy image pairs which are used to enhance the performance of deraining network. Specifically, to preserve more image background details while transferring rain streaks from rainy images to the unpaired clean images, we propose a novel Channel Consistency Loss (CCLoss) by introducing the Channel Consistency Prior (CCP) of rain streaks into training process, thereby ensuring that the generated pseudo rainy images closely resemble the real ones. Furthermore, we propose a novel Self-Reconstruction (SR) strategy to alleviate the redundant information transfer problem of the generator, further improving the deraining performance and the generalization capability of our method. Extensive experiments on multiple synthetic and real-world datasets demonstrate that the deraining performance of CSUD surpasses other state-of-the-art unsupervised methods and CSUD exhibits superior generalization capability. Code is available at https://github.com/GuangluDong0728/CSUD.

We propose ChainHOI, a novel approach for text-driven human-object interaction (HOI) generation that explicitly models interactions at both the joint and kinetic chain levels. Unlike existing methods that implicitly model interactions using full-body poses as tokens, we argue that explicitly modeling joint-level interactions is more natural and effective for generating realistic HOIs, as it directly captures the geometric and semantic relationships between joints, rather than modeling interactions in the latent pose space. To this end, ChainHOI introduces a novel joint graph to capture potential interactions with objects, and a Generative Spatiotemporal Graph Convolution Network to explicitly model interactions at the joint level. Furthermore, we propose a Kinematics-based Interaction Module that explicitly models interactions at the kinetic chain level, ensuring more realistic and biomechanically coherent motions. Evaluations on two public datasets demonstrate that ChainHOI significantly outperforms previous methods, generating more realistic, and semantically consistent HOIs.

3D Vision Grounding (3DVG) is a fundamental research area that enables agents to perceive and interact with the 3D world. The challenge of the 3DVG task lies in understanding fine-grained semantics and spatial relationships within both the utterance and 3D scene. To address this challenge, we propose a zero-shot neuro-symbolic framework that utilizes a large language model (LLM) as neuro-symbolic functions to ground the object within the 3D Gaussian Splatting (3DGS) representation. By utilizing 3DGS representation, we can dynamically render high-quality 2D images from various viewpoints to enrich the semantic information. Given the complexity of spatial relationships, we construct a relationship graph and chain of semantics that decouple spatial relationships and facilitate step-by-step reasoning within 3DGS representation. Additionally, we employ a grounded-aware self-check mechanism to enable the LLM to reflect on its responses and mitigate the effects of ambiguity in spatial reasoning. We evaluate our method using two publicly available datasets, Nr3D and Sr3D, achieving accuracies of 60.8% and 91.4%, respectively. Notably, our method surpasses current state-of-the-art zero-shot methods on the Nr3D dataset. In addition, it outperforms the recent supervised models on the Sr3D dataset.

Pre-trained vision-language models (VLMs) have showcased remarkable performance in image and natural language understanding, such as image captioning and response generation. As the practical applications of VLMs become increasingly widespread, their potential safety and robustness issues raise concerns that adversaries may evade the system and cause these models to generate toxic content through malicious attacks. Therefore, evaluating the robustness of open-source VLMs against adversarial attacks has garnered growing attention, with transfer-based attacks as a representative black-box attacking strategy. However, most existing transfer-based attacks neglect the importance of the semantic correlations between vision and text modalities, leading to sub-optimal adversarial example generation and attack performance. To address this issue, we present Chain of Attack (CoA), which iteratively enhances the generation of adversarial examples based on the multi-modal semantic update using a series of intermediate attacking steps, achieving superior adversarial transferability and efficiency. A unified attack success rate computing method is further proposed for automatic evasion evaluation. Extensive experiments conducted under the most realistic and high-stakes scenario, demonstrate that our attacking strategy is able to effectively mislead models to generate targeted responses using only black-box attacks without any knowledge of the victim models. The comprehensive robustness evaluation in our paper provides insight into the vulnerabilities of VLMs and offers a reference for the safety considerations of future model developments.

Predicting human trajectories is essential for the safe operation of autonomous vehicles, yet current data-driven models often lack robustness in case of noisy inputs such as adversarial examples or imperfect observations. Although some trajectory prediction methods have been developed to provide empirical robustness, these methods are heuristic and do not offer guaranteed robustness. In this work, we propose a certification approach tailored for trajectory prediction that provides guaranteed robustness. To this end, we address the unique challenges associated with trajectory prediction, such as unbounded outputs and multi-modality. To mitigate the inherent performance drop through certification, we propose a diffusion-based trajectory denoiser and integrate it into our method. Moreover, we introduce new certified performance metrics to reliably measure the trajectory prediction performance. Through comprehensive experiments, we demonstrate the accuracy and robustness of the certified predictors and highlight their advantages over the non-certified ones. The code is available online: https://s-attack.github.io/

Simulation is critical for safety evaluation in autonomous driving, particularly in capturing complex interactive behaviors. However, generating **realistic** and **controllable** traffic scenarios in long-tail situations remains a significant challenge. Existing generative models suffer from the conflicting objective between user-defined controllability and realism constraints, which is amplified in safety-critical contexts. In this work, we introduce the **C**ausal **C**ompositional **Diff**usion Model (***CCDiff***), a structure-guided diffusion framework to address these challenges. We first formulate the learning of controllable and realistic closed-loop simulation as a constrained optimization problem. Then, CCDiff maximizes controllability while adhering to realism by automatically identifying and injecting causal structures directly into the diffusion process, providing structured guidance to enhance both realism and controllability. Through rigorous evaluations on benchmark datasets and in a closed-loop simulator, CCDiff demonstrates substantial gains over state-of-the-art approaches in generating realistic and user-preferred trajectories. Our results show CCDiff's effectiveness in extracting and leveraging causal structures, showing improved closed-loop performance based on key metrics such as collision rate, off-road rate, FDE, and comfort. For more details, welcome to check our project website: https://sites.google.com/view/ccdiff/.

The motion of deformable 4D objects lies in a low-dimensional manifold. To better capture the low dimensionality and enable better controllability, traditional methods have devised several heuristic-based methods, i.e., rigging, for manipulating dynamic objects in an intuitive fashion. However, such representations are not scalable due to the need for expert knowledge of specific categories. Instead, we study the automatic exploration of such low-dimensional structures in a purely data-driven manner. Specifically, we design a novel representation that encodes deformable 4D objects into a sparse set of spatially grounded blobs and an instance-aware feature volume to disentangle the pose and instance information of the 3D shape. With such a representation, we can manipulate the pose of 3D objects intuitively by modifying the parameters of the blobs, while preserving rich instance-specific information. We evaluate the proposed method on a variety of object categories and demonstrate the effectiveness of the proposed framework. Project page: https://guangzhaohe.com/canor.

We present CaricatureBooth, a system that transforms caricature creation into a simple interactive experience -- as easy as using a photo booth! A key challenge in caricature generation is two-fold: the scarcity of high-quality caricature data and the difficulty in enabling precise creative control over the exaggeration process while maintaining identity. Prior approaches either require large-scale caricature and photo data or lack intuitive mechanisms for users to guide the deformation without losing identity. We address the data scarcity by synthesising training data through Thin Plate Spline (TPS) deformation of standard face images. For creative control, we design a Bezier curve interface where users can easily manipulate facial features, with these edits then driving TPS transformations at inference time. When combined with a pre-trained ID-preserving diffusion model, our system maintains both identity preservation and creative flexibility. Through extensive experiments, we demonstrate that CaricatureBooth achieves state-of-the-art quality while making the joy of caricature creation as accessible as taking a photo -- just walk in and walk out with your personalised caricature! Code is available at https://github.com/WinKawaks/CaricatureBooth.

Trajectory planning is vital for autonomous driving, ensuring safe and efficient navigation in complex environments. While recent learning-based methods, particularly reinforcement learning (RL), have shown promise in specific scenarios, RL planners struggle with training inefficiencies and managing large-scale, real-world driving scenarios.In this paper, we introduce CarPlanner, a Consistent auto-regressive Planner that uses RL to generate multi-modal trajectories. The auto-regressive structure enables efficient large-scale RL training, while the incorporation of consistency ensures stable policy learning by maintaining coherent temporal consistency across time steps. Moreover, CarPlanner employs a generation-selection framework with an expert-guided reward function and an invariant-view module, simplifying RL training and enhancing policy performance.Extensive analysis demonstrates that our proposed RL framework effectively addresses the challenges of training efficiency and performance enhancement, positioning CarPlanner as a promising solution for trajectory planning in autonomous driving.To the best of our knowledge, we are the first to demonstrate that the RL-based planner can surpass both IL- and rule-based state-of-the-arts (SOTAs) on the challenging large-scale real-world dataset nuPlan. Our proposed CarPlanner surpasses RL-, IL-, and rule-based SOTA approaches within this demanding dataset.

Object detection is a fundamental enabler for many real-time downstream applications such as autonomous driving, augmented reality and supply chain management. However, the algorithmic backbone of neural networks is brittle to imperceptible perturbations in the system inputs, which were generally known as misclassifying attacks. By targeting the real-time processing capability, a new class of latency attacks has been reported recently. They exploit new attack surfaces in object detectors by creating a computational bottleneck in the post-processing module, which leads to cascading failure and puts the real-time downstream tasks at risk. In this work, we take an initial attempt to defend against this attack via background-attentive adversarial training that is also cognizant of the underlying hardware capabilities. We first draw system-level connections between latency attacks and hardware capacity across heterogeneous GPU devices. Based on the particular adversarial behaviors, we utilize objectness loss as a proxy and build background attention into the adversarial training pipeline, and achieve a favorable balance between clean and robust accuracy. The extensive experiments demonstrate the effectiveness of the defense in restoring real-time processing capability from 13 FPS to 43 FPS on Jetson Orin NX, with a better trade-off between the clean and robust accuracy. The source code is available at: https://github.com/Hill-Wu-1998/underload.

Recent video-language alignment models are trained on sets of videos, each with an associated positive caption and a negative caption generated by large language models. A problem with this procedure is that negative captions may introduce linguistic biases, i.e., concepts are seen only as negatives and never associated with a video. While a solution would be to collect videos for the negative captions, existing databases lack the fine-grained variations needed to cover all possible negatives. In this work, we study whether synthetic videos can help to overcome this issue. Our preliminary analysis with multiple generators shows that, while promising on some tasks, synthetic videos harm the performance of the model on others. We hypothesize this issue is linked to noise (semantic and visual) in the generated videos and develop a method, SynViTA, that accounts for those. SynViTA dynamically weights the contribution of each synthetic video based on how similar its target caption is w.r.t. the real counterpart. Moreover, a semantic consistency loss makes the model focus on fine-grained differences across captions, rather than differences in video appearance. Experiments show that, on average, SynViTA improves over existing methods on VideoCon test sets and SSv2-Temporal, SSv2-Events, and ATP-Hard benchmarks, being a first promising step for using synthetic videos when learning video-language models.

Improving semantic grounding in Vision-Language Models (VLMs) often involves collecting domain-specific training data, refining the network architectures, or modifying the training recipes. In this work, we venture into an orthogonal direction and explore self-correction in VLMs focusing on semantic grounding. We find that VLMs can correct their own semantic grounding mistakes when properly prompted and framed for the task, without any fine-tuning or even access to oracle feedback. We also introduce a self-correction framework in an iterative setting which consistently improves performance across all models investigated. Overall, we show that iterative self-correction consistently improves VLM performance in semantic grounding by up to 8.4 accuracy points across all models investigated, without requiring fine-tuning, additional architectural changes, or external data. Our exploration of self-correction also reveals that, even after several rounds of feedback, strong models like GPT-4V and GPT-4o retain limited capability in leveraging oracle feedback, suggesting promising directions for further research.

In this work, we introduce Camouflage Anything, a novel and robust approach to generate camouflaged datasets. To the best of our knowledge, we are the first to apply Controlled Out-painting and Representation Engineering for generating realistic camouflaged images with an objective to hide any segmented object coming from a generic or salient database. Our proposed method uses a novel control design to out-paint a given segmented object, with a camouflaged background. We also uncover the role of representation engineering in enhancing the quality of generated camouflage datasets. We address the limitations of existing metrics FID and KID in capturing the 'camouflage quality' ,by proposing a novel metric namely, CamOT. CamOT uses Optimal Transport between foreground & background Gaussian Mixture Models (GMM) of concerned camouflaged object to assign an image quality score. Furthermore, we conduct LoRA-based fine-tuning of the robust BiRefNet baseline with our generated camouflaged datasets, leading to notable improvements in camouflaged object segmentation accuracy. The experimental results showcase the efficacy and potential of Camouflage Anything, outperforming existing methods in camouflaged generation tasks.

We present a marker-based geometric estimation framework for the absolute pose of a camera by analyzing the 1D observations in a single radially distorted pixel scanline.We leverage a pair of known co-planar pencils of lines, along with lens distortion parameters, to propose an ensemble of solvers exploring the space of estimation strategies applicable to our setup.First, we present a minimal algebraic solver requiring only six measurements and yielding eight solutions, which relies on the intersection of two conics defined by one of the pencils of lines.Then, we present a unique closed-form geometric solver from seven measurements.Finally, we present an homography-based formulation amenable to linear least-squares from eight or more measurements.Our geometric framework constitutes a theoretical analysis on the minimum geometric context necessary to solve in closed form for the absolute pose of a single camera from a single radially distorted scanline.

Local features aggregation and global information perception are the fundamental to point cloud segmentation. However, existing works often fall short in effectively identifying semantic relevant neighbors and face challenges in endowing each point with high-level information. Here, we propose CamPoint, an innovative method that employs virtual cameras to solve above problems. The core of CamPoint lies in introducing the novel camera visibility feature for points, where each dimension encodes the visibility of that point from a specific camera. Leveraging this feature, we propose the camera perspective slice distance for accurate relevant neighbor searching and design the camera parameter embedding to deliver rich feature representations for global interaction. Specifically, the camera perspective slice distance between two points is defined as a similarity metric derived from their camera visibility features, whereby an increased number of shared cameras observing both points corresponds to a reduced distance between them. To effectively facilitate global semantic perception, we assign each camera an optimizable embedding and then integrate these embeddings into the original spatial features based on visibility attributes, thereby obtaining high-level features enriched with camera priors. Additionally, the state space model characterized by linear computational complexity is employed as the operator to achieve global learning with efficiency. Comprehensive experiments on multiple datasets shows that our CamPoint surpasses the current state-of-the-art in multiple datasets, achieving low training cost and fast inference speed.

This paper introduces Camera-free Diffusion (CamFreeDiff) model for 360^\circ image outpainting from a single camera-free image and text description. This method distinguishes itself from existing strategies, such as MVDiffusion, by eliminating the requirement for predefined camera poses. CamFreeDiff seamlessly incorporates a mechanism for predicting homography within the multi-view diffusion framework. The key component of our approach is to formulate camera estimation by directly predicting the homography transformation from the input view to the predefined canonical view. In contrast to the direct two-stage approach of image transformation and outpainting, CamFreeDiff utilizes predicted homography to establish point-level correspondences between the input view and the target panoramic view. This enables consistency through correspondence-aware attention, which is learned in a fully differentiable manner. Qualitative and quantitative experimental results demonstrate the strong robustness and performance of CamFreeDiff for 360^\circ image outpainting in the challenging context of camera-free inputs.

Aligning text-to-image (T2I) diffusion models with prefer-ence optimization is valuable for human-annotated datasets, but the heavy cost of manual data collection limits scalability. Using reward models offers an alternative, however, current preference optimization methods fall short in exploiting the rich information, as they only consider pairwise preference distribution. Furthermore, they lack generalization to multi-preference scenarios and struggle to handle inconsistencies between rewards. To address this, we present Calibrated Preference Optimization (CaPO), a novel method to align T2I diffusion models by incorporating the general preference from multiple reward models without human annotated data. The core of our approach involves a reward calibration method to approximate the general preference by computing the expected win-rate against the samples generated by the pretrained models. Additionally, we propose a frontier-based pair selection method that effectively manages the multi-preference distribution by selecting pairs from Pareto frontiers. Finally, we use regression loss to fine-tune diffusion models to match the difference between calibrated rewards of a selected pair. Experimental results show that CaPO consistently outperforms prior methods, such as Direct Preference Optimization (DPO), in both single and multi-reward settings validated by evaluation on T2I benchmarks, including GenEval and T2I-Compbench.

Diffusion models have gradually gained prominence in the field of image synthesis, showcasing remarkable generative capabilities. Nevertheless, the slow inference and complex networks, resulting from redundancy at both temporal and structural levels, hinder their low-latency applications in real-world scenarios. Current acceleration methods for diffusion models focus separately on temporal and structural levels. However, independent optimization at each level to further push the acceleration limits results in significant performance degradation. On the other hand, integrating optimizations at both levels can compound the acceleration effects. Unfortunately, we find that the optimizations at these two levels are not entirely orthogonal. Performing separate optimizations and then simply integrating them results in unsatisfactory performance. To tackle this issue, we propose CacheQuant, a novel training-free paradigm that comprehensively accelerates diffusion models by jointly optimizing model caching and quantization techniques. Specifically, we employ a dynamic programming approach to determine the optimal cache schedule, in which the properties of caching and quantization are carefully considered to minimize errors. Additionally, we propose decoupled error correction to further mitigate the coupled and accumulated errors step by step. Experimental results show that CacheQuant achieves a 5.18xspeedup and 4xcompression for Stable Diffusion on MS-COCO, with only a 0.02 loss in CLIP score.