CVPR 2025 Papers

Video inpainting, which aims to fill missing regions with visually coherent content, has emerged as a crucial technique for creative applications such as editing. While existing approaches achieve visual consistency or text-guided generation, they often struggle to balance coherence and creative diversity. In this work, we introduce VideoRepainter, a two-stage framework that allows users to inpaint a keyframe using established image-level techniques, then propagate the changes to other frames. Our approach can leverage state-of-the-art image models for keyframe manipulation, thereby easing the burden of the video-inpainting process. To this end, we integrate an image-to-video model with a symmetric condition mechanism to address ambiguity caused by direct mask downsampling. We further explore efficient strategies for mask synthesis and parameter tuning to reduce costs in data processing and model training. Evaluations demonstrate our method achieves superior results in both visual fidelity and content diversity compared to existing approaches, providing a practical solution for creative video manipulation.

Current audio-driven facial animation methods achieve impressive results for short videos but suffer from error accumulation and identity drift when extended to longer durations. Existing methods attempt to mitigate this through external spatial control, increasing long-term consistency but compromising the naturalness of motion. We propose KeyFace, a novel two-stage diffusion-based framework, to address these issues. In the first stage, keyframes are generated at a low frame rate, conditioned on audio input and an identity frame, to capture essential facial expressions and movements over extended periods of time. In the second stage, an interpolation model fills in the gaps between keyframes, ensuring smooth transitions and temporal coherence. To further enhance realism, we incorporate continuous emotion representations and handle a wide range of non-speech vocalizations (NSVs), such as laughter and sighs. We also introduce two new evaluation metrics for assessing lip synchronization and NSV generation. Experimental results show that KeyFace outperforms state-of-the-art methods in generating natural, coherent facial animations over extended durations, successfully encompassing NSVs and continuous emotions.

Multimodal semantic segmentation is a critical challenge in computer vision, with early methods suffering from high computational costs and limited transferability due to full fine-tuning of RGB-based pre-trained parameters. Recent studies, while leveraging additional modalities as supplementary prompts to RGB, still predominantly rely on RGB, which restricts the full potential of other modalities. To address these issues, we propose a novel symmetric parameter-efficient fine-tuning framework for multimodal segmentation, featuring with a modality-aware prompting and adaptation scheme, to simultaneously adapt the capabilities of a powerful pre-trained model to both RGB and X modalities. Furthermore, prevalent approaches use the global cross-modality correlations of attention mechanism for modality fusion, which inadvertently introduces noise across modalities. To mitigate this noise, we propose a dynamic sparse cross-modality fusion module to facilitate effective and efficient cross-modality fusion. To further strengthen the above two modules, we propose a training strategy that leverages accurately predicted dual-modality results to self-teach the single-modality outcomes. In comprehensive experiments, we demonstrate that our method outperforms previous state-of-the-art approaches across six multimodal segmentation scenarios with minimal computation cost.

Video Quality Assessment (VQA), which intends to predict the perceptual quality of videos, has attracted increasing attention. Due to factors like motion blur or specific distortions, the quality of different regions in a video varies. Recognizing the region-wise local quality within a video is beneficial for assessing global quality and can guide us in adopting fine-grained enhancement or transcoding strategies. Due to the heavy cost of annotating region-wise quality, the lack of ground truth constraints from relevant datasets further complicates the utilization of local perception. Inspired by the Human Visual System (HVS) that links global quality to the local texture of different regions and their visual saliency, we propose a Kaleidoscope Video Quality Assessment (KVQ) framework, which aims to effectively assess both saliency and local texture, thereby facilitating the assessment of global quality. Our framework extracts visual saliency and allocates attention using Fusion-Window Attention (FWA) while incorporating a Local Perception Constraint (LPC) to mitigate the reliance of regional texture perception on neighboring areas. KVQ obtains significant improvements across multiple scenarios on five VQA benchmarks compared to SOTA methods. Furthermore, to assess local perception, we establish a new Local Perception Visual Quality (LPVQ) dataset with region-wise annotations. Experimental results demonstrate the capability of KVQ in perceiving local distortions. KVQ models and the LPVQ dataset will be available at https://github.com/qyp2000/KVQ.

Magnetic resonance imaging (MRI), with modalities including T1, T2, T1ce, and Flair, providing complementary information critical for sub-region analysis, is widely used for brain tumor diagnosis. However, clinical practice often suffers from varying degrees of incompleteness of necessary modalities due to reasons such as susceptibility to artifacts. It significantly impairs segmentation model performance. Given the limited available modalities at hand, existing approaches attempt to project them into a shared latent space. However, they ignore decomposing the modality-shared and modality-specific information and failed to construct the relationship among different modalities. Such deficiency limits the effectiveness of the segmentation performance, particularly at the time when the amount of data in each modality is different. In this paper, we propose the plug-and-play Koopman Multi-modality Decomposition (KMD) module, leveraging the Koopman Invariant Subspace to disentangle modality-common and modality-specific information. It is capable of constructing modality relationships that minimize bias toward modalities across various modality-incomplete scenarios. More importantly, it can be integrated into several existing backbones feasibility. Through theoretical deductions and extensive empirical experiences on the BraTS2018 and BraTS2020 datasets, we have sufficiently demonstrated the effectiveness of the proposed KMD to promote generalization performance.

The rapid advancement of visual generative models necessitates efficient and reliable evaluation methods. Arena platform, which gathers user votes on model comparisons, can rank models with human preferences. However, traditional Arena methods, while established, require an excessive number of comparisons for ranking to converge and are vulnerable to preference noise in voting, suggesting the need for better approaches tailored to contemporary evaluation challenges. In this paper, we introduce K-Sort Arena, an efficient and reliable platform based on a key insight: images and videos possess higher perceptual intuitiveness than texts, enabling rapid evaluation of multiple samples simultaneously. Consequently, K-Sort Arena employs K-wise comparisons, allowing K models to engage in free-for-all competitions, which yield much richer information than pairwise comparisons. To enhance the robustness of the system, we leverage probabilistic modeling and Bayesian updating techniques. We propose an exploration-exploitation-based matchmaking strategy to facilitate more informative comparisons. In our experiments, K-Sort Arena exhibits 16.3xfaster convergence compared to the widely used ELO algorithm. To further validate the superiority and obtain a comprehensive leaderboard, we collect human feedback via crowdsourced evaluations of numerous cutting-edge text-to-image and text-to-video models. Thanks to its high efficiency, K-Sort Arena can continuously incorporate emerging models and update the leaderboard with minimal votes. Our project has undergone several months of internal testing and is now available online.

Recent studies have explored combining different LoRAs to jointly generate learned style and content. However, existing methods either fail to effectively preserve both the original subject and style simultaneously or require additional training. In this paper, we argue that the intrinsic properties of LoRA can effectively guide diffusion models in merging learned subject and style. Building on this insight, we propose K-LoRA, a simple yet effective training-free LoRA fusion approach. In each attention layer, K-LoRA compares the Top-K elements in each LoRA to be fused, determining which LoRA to select for optimal fusion. This selection mechanism ensures that the most representative features of both subject and style are retained during the fusion process, effectively balancing their contributions. Experimental results demonstrate that the proposed method effectively integrates the subject and style information learned by the original LoRAs, outperforming state-of-the-art training-based approaches in both qualitative and quantitative results.

Vision-Language (V-L) pre-trained models such as CLIP show prominent capabilities in various downstream tasks. Despite this promise, V-L models are notoriously limited by their inherent social biases. A typical demonstration is that V-L models often produce biased predictions against specific groups of people, significantly undermining their real-world applicability. Existing approaches endeavor to mitigate the social bias problem in V-L models by removing biased attribute information from model embeddings. However, after our revisiting of these methods, we find that their bias removal is frequently accompanied by greatly compromised V-L alignment capabilities. We then reveal that this performance degradation stems from the unbalanced debiasing in image and text embeddings. To address this issue, we propose a novel V-L debiasing framework to align image and text biases followed by removing them from both modalities. By doing so, our method achieves multi-modal bias mitigation while maintaining the V-L alignment in the debiased embeddings. Additionally, we advocate a new evaluation protocol that can 1) holistically quantify the model debiasing and V-L alignment ability, and 2) evaluate the generalization of social bias removal models. We believe this work will offer new insights and guidance for future studies addressing the social bias problem in CLIP.

Multi-task prompt learning has emerged as a promising technique for fine-tuning pre-trained Vision-Language Models (VLMs) to various downstream tasks. However, existing methods ignore challenges caused by spurious correlations and dynamic task relationships, which may reduce the model performance. To tackle these challenges, we propose JSCPT, a novel approach for Joint Scheduling of Causal Prompts and Tasks to enhance multi-task prompt learning. Specifically, we first design a Multi-Task Vison-Language Prompt (MTVLP) model, which learns task-shared and task-specific vison-language prompts and selects useful prompt features via causal intervention, alleviating spurious correlations. Then, we propose the task-prompt scheduler that models inter-task affinities and assesses the causal effect of prompt features to optimize the multi-task prompt learning process. Finally, we formulate the scheduler and the multi-task prompt learning process as a bi-level optimization problem to optimize prompts and tasks adaptively. In the lower optimization, MTVLP is updated with the scheduled gradient, while in the upper optimization, the scheduler is updated with the implicit gradient. Extensive experiments show the superiority of our proposed JSCPT approach over several baselines in terms of multi-task prompt learning for pre-trained VLMs.

As the data demand for deep learning models increases, active learning (AL) becomes essential to strategically select samples for labeling, which maximizes data efficiency and reduces training costs. Real-world scenarios necessitate the consideration of incomplete data knowledge within AL. Prior works address handling out-of-distribution (OOD) data, while another research direction has focused on category discovery. However, a combined analysis of real-world considerations combining AL with out-of-distribution data and category discovery remains unexplored. To address this gap, we propose Joint Out-of-distribution filtering and data Discovery Active learning (Joda), to uniquely address both challenges simultaneously by filtering out OOD data before selecting candidates for labeling. In contrast to previous methods, we deeply entangle the training procedure with filter and selection to construct a common feature space that aligns known and novel categories while separating OOD samples. Unlike previous works, Joda is highly efficient and completely omits auxiliary models and training access to the unlabeled pool for filtering or selection. In extensive experiments on 18 configurations and 3 metrics, Joda consistently achieves the highest accuracy with the best class discovery to OOD filtering balance compared to state-of-the-art competitor approaches.

Neural Radiance Fields (NeRF) has demonstrated its superior capability to represent 3D geometry but require accurately precomputed camera poses during training. To mitigate this requirement, existing methods jointly optimize camera poses and NeRF often relying on good pose initialisation or depth priors. However, these approaches struggle in challenging scenarios, such as large rotations, as they map each camera to a world coordinate system. We propose a novel method that eliminates prior dependencies by modeling continuous camera motions as time-dependent angular velocity and velocity. Relative motions between cameras are learned first via velocity integration, while camera poses can be obtained by aggregating such relative motions up to a world coordinate system defined at a single time step within the video. Specifically, accurate continuous camera movements are learned through a time-dependent NeRF, which captures local scene geometry and motion by training from neighboring frames for each time step. The learned motions enable fine-tuning the NeRF to represent the full scene geometry. Experiments on Co3D and Scannet show our approach achieves superior camera pose and depth estimation and comparable novel-view synthesis performance compared to state-of-the-art methods.

Deep-learning-based autonomous driving (AD) perception introduces a promising picture for safe and environment-friendly transportation. However, the over-reliance on real labeled data in LiDAR perception limits the scale of on-road attempts. 3D real world data is notoriously time-and-energy-consuming to annotate and lacks corner cases like rare traffic participants. On the contrary, in simulators like CARLA, generating labeled LiDAR point clouds with corner cases is a piece of cake. However, introducing synthetic point clouds to improve real perception is non-trivial. This stems from two challenges: 1) sample efficiency of simulation datasets 2) simulation-to-real gaps. To overcome both challenges, we propose a plug-and-play method called JiSAM, shorthand for Jittering augmentation, domain-aware backbone and memory-based Sectorized AlignMent. In extensive experiments conducted on the famous AD dataset NuScenes, we demonstrate that, with SOTA 3D object detector, JiSAM is able to utilize the simulation data and only labels on 2.5% available real data to achieve comparable performance to models trained on all real data. Additionally, JiSAM achieves more than 15 mAPs on the objects not labeled in the real training set. We will release models and codes.

Vision-centric perception systems often struggle with unpredictable and coupled weather degradations in the wild. Current solutions are often limited, as they either depend on specific degradation priors or suffer from significant domain gaps. To enable robust and autonomous operation in real-world conditions, we propose JarvisIR, a VLM-powered agent that leverages the VLM (e.g., Llava-Llama3) as a controller to manage multiple expert restoration models. To further enhance system robustness, reduce hallucinations, and improve generalizability in real-world adverse weather, JarvisIR employs a novel two-stage framework consisting of supervised fine-tuning and human feedback alignment. Specifically, to address the lack of paired data in real-world scenarios, the human feedback alignment enables the VLM to be fine-tuned effectively on large-scale real-world data in an unsupervised manner. To support the training and evaluation of JarvisIR, we introduce CleanBench, a comprehensive dataset consisting of high-quality and large-scale instruction-responses pairs, including 150K synthetic entries and 80K real entries. Extensive experiments demonstrate that JarvisIR exhibits superior decision-making and restoration capabilities. Compared with existing methods, it achieves a 50% improvement in the average of all perception metrics on CleanBench-Real.

We present JanusFlow, a powerful framework that unifies image understanding and generation in a single model.JanusFlow introduces a minimalist architecture that integrates autoregressive language models with rectified flow, a state-of-the-art method in generative modeling.Our key finding demonstrates that rectified flow can be straightforwardly trained within the large language model framework, eliminating the need for complex architectural modifications.To further improve the performance of our unified model, we adopt two key strategies: (i) decoupling the understanding and generation encoders, and (ii) aligning their representations during unified training.Extensive experiments show that JaunsFlow achieves comparable or superior performance to specialized models in their respective domains, while significantly outperforming existing unified approaches.This work represents a step toward more efficient and versatile vision-language models.

We introduce Janus, an autoregressive framework that unifies multimodal understanding and generation. Prior research often relies on a single visual encoder for both tasks, such as Chameleon. However, due to the differing levels of information granularity required by multimodal understanding and generation, this approach can lead to suboptimal performance, particularly in multimodal understanding. To address this issue, we decouple visual encoding into separate pathways, while still leveraging a single, unified transformer architecture for processing. The decoupling not only alleviates the conflict between the visual encoder's roles in understanding and generation, but also enhances the framework's flexibility. For instance, both the multimodal understanding and generation components can independently select their most suitable encoding methods. Experiments show that Janus surpasses previous unified model and matches or exceeds the performance of task-specific models. The simplicity, high flexibility, and effectiveness of Janus make it a strong candidate for next-generation unified multimodal models.

Existing state-of-the-art feature matchers capture long-range dependencies with Transformers but are hindered by high spatial complexity,leading to demanding training and high-latency inference.Striking a better balance between performance and efficiency remains a critical challenge in feature matching.Inspired by the linear complexity \mathcal O (N) of Mamba, we propose an ultra-lightweight Mamba-based matcher, named JamMa, which converges on a single GPU and achieves an impressive performance-efficiency balance in inference.To unlock the potential of Mamba for feature matching,we propose Joint Mamba with a scan-merge strategy named JEGO, which enables:(1) Joint scan of two images to achieve high-frequency mutual interaction, (2) Efficient scan with skip steps to reduce sequence length, (3) Global receptive field, and (4) Omnidirectional feature representation.With the above properties, the JEGO strategy significantly outperforms the scan-merge strategies proposed in VMamba and EVMamba in the feature matching task.Compared to attention-based sparse and semi-dense matchers, JamMa demonstrates a notably superior balance between performance and efficiency,delivering better performance with less than 50% of the parameters and FLOPs.

Non-transferable learning (NTL) has been proposed to protect model intellectual property (IP) by creating a "non-transferable barrier" to restrict generalization from authorized to unauthorized domains. Recently, well-designed attack, which restores the unauthorized-domain performance by fine-tuning NTL models on few authorized samples, highlights the security risks of NTL-based applications. However, such attack requires modifying model weights, thus being invalid in the black-box scenario. This raises a critical question: can we trust the security of NTL models deployed as black-box systems? In this work, we reveal the first loophole of black-box NTL models by proposing a novel attack method (dubbed as JailNTL) to jailbreak the non-transferable barrier through test-time data disguising, The main idea of JailNTL is to disguise unauthorized data so it can be identified as authorized by the NTL model, thereby bypassing the non-transferable barrier without modifying the NTL model weights. Specifically, JailNTL encourages unauthorized-domain disguising in two levels, including: (i) data-intrinsic disguising (DID) for eliminating domain discrepancy and preserving class-related content at the input-level, and (ii) model-guided disguising (MGD) for mitigating output-level statistics difference of the NTL model. Empirically, when attacking state-of-the-art (SOTA) NTL models in the black-box scenario, JailNTL achieves an accuracy increase of up to 55.7% in the unauthorized domain by using only 1% authorized samples, largely exceeding existing SOTA white-box attacks. Code is released at https://github.com/tmllab/2025_CVPR_JailNTL.

Unmanned Aerial Vehicles (UAVs) are widely adopted across various fields, yet they raise significant privacy and safety concerns, demanding robust monitoring solutions. Existing anti-UAV methods primarily focus on position tracking but fail to capture UAV behavior and intent. To address this, we introduce a novel task--UAV Tracking and Intent Understanding (UTIU)--which aims to track UAVs while inferring and describing their motion states and intent for a more comprehensive monitoring approach. To tackle the task, we propose JTD-UAV, the first joint tracking, and intent description framework based on large language models. Our dual-branch architecture integrates UAV tracking with Visual Question Answering (VQA), allowing simultaneous localization and behavior description. To benchmark this task, we introduce the TDUAV dataset, the largest dataset for joint UAV tracking and intent understanding, featuring 1,328 challenging video sequences, over 163K annotated thermal frames, and 3K VQA pairs. Our benchmark demonstrates the effectiveness of JTD-UAV, and both the dataset and code will be publicly available.

We propose a novel Iterative Predictor-Critic Code Decoding framework for real-world image dehazing, abbreviated as IPC-Dehaze, which leverages the high-quality codebook prior encapsulated in a pre-trained VQGAN. Apart from previous codebook-based methods that rely on one-shot decoding, our method utilizes high-quality codes obtained in the previous iteration to guide the prediction of the Code-Predictor in the subsequent iteration, improving code prediction accuracy and ensuring stable dehazing performance. Our idea stems from the observations that 1) the degradation of hazy images varies with haze density and scene depth, and 2) clear regions play crucial cues in restoring dense haze regions. However, it is nontrivial to progressively refine the obtained codes in subsequent iterations, owing to the difficulty in determining which codes should be retained or replaced at each iteration. Another key insight of our study is to propose Code-Critic to capture interrelations among codes. The Code-Critic is used to evaluate code correlations and then resample a set of codes with the highest mask scores, i.e., a higher score indicates that the code is more likely to be rejected, which helps retain more accurate codes and predict difficult ones. Extensive experiments demonstrate the superiority of our method over state-of-the-art methods in real-world dehazing. Our code will be made publicly available.