CVPR 2025 Papers

Recent learning-based methods for event-based optical flow estimation utilize cost volumes for pixel matching but suffer from redundant computations and limited scalability to higher resolutions for flow refinement. In this work, we take advantage of the complementarity between temporally dense feature differences of adjacent event frames and cost volume and present a lightweight event-based optical flow network (EDCFlow) to achieve high-quality flow estimation at a higher resolution. Specifically, an attention-based multi-scale temporal feature difference layer is developed to capture diverse motion patterns at high resolution in a computation-efficient manner. An adaptive fusion of high-resolution difference motion features and low-resolution correlation motion features is performed to enhance motion representation and model generalization. Notably, EDCFlow can serve as a plug-and-play refinement module for RAFT-like event-based methods to enhance flow details. Extensive experiments demonstrate that EDCFlow achieves better performance with lower complexity compared to existing methods, offering superior generalization. Codes and models will be available at here.

In Learned Video Compression (LVC), improving inter prediction, such as enhancing temporal context mining and mitigating accumulated errors, is crucial for boosting rate-distortion performance. Existing LVCs mainly focus on mining the temporal movements while neglecting non-local correlations among frames. Additionally, current contextual video compression models use a single reference frame, which is insufficient for handling complex movements. To address these issues, we propose leveraging non-local correlations across multiple frames to enhance temporal priors, significantly boosting rate-distortion performance. To mitigate error accumulation, we introduce a partial cascaded fine-tuning strategy that supports fine-tuning on full-length sequences with constrained computational resources. This method reduces the train-test mismatch in sequence lengths and significantly decreases accumulated errors. Based on the proposed techniques, we present a video compression scheme ECVC. Experiments demonstrate that our ECVC achieves state-of-the-art performance, reducing 10.5% and 11.5% more bit-rates than previous SOTA method DCVC-FM over VTM-13.2 low delay B (LDB) under the intra period (IP) of 32 and -1, respectively. Our code is available at https://github.com/JiangWeibeta/ECVC.

The enhancement of generalization in robots by large vision-language models (LVLMs) is increasingly evident. Therefore, the embodied cognitive abilities of LVLMs based on egocentric videos are of great interest. However, current datasets for embodied video question answering lack comprehensive and systematic evaluation frameworks. Critical embodied cognitive issues, such as robotic self-cognition, dynamic scene perception, and hallucination, are rarely addressed. To tackle these challenges, we propose ECBench, a high-quality benchmark designed to systematically evaluate the embodied cognitive abilities of LVLMs. ECBench features a diverse range of scene video sources, open and varied question formats, and 30 dimensions of embodied cognition. To ensure quality, balance, and high visual dependence, ECBench uses class-independent meticulous human annotation and multi-round question screening strategies. Additionally, we introduce ECEval, a comprehensive evaluation system that ensures the fairness and rationality of the indicators. Utilizing ECBench, we conduct extensive evaluations of proprietary, open-source, and task-specific LVLMs. ECBench is pivotal in advancing the embodied cognitive capabilities of LVLMs, laying a solid foundation for developing reliable core models for embodied agents. All data and code is available at https://github.com/Rh-Dang/ECBench.

Event-based sensors (EBS) are a promising new technology for star tracking due to their low latency and power efficiency, but prior work has thus far been evaluated exclusively in simulation with simplified signal models. We propose a novel algorithm for event-based star tracking, grounded in an analysis of the EBS circuit and an extended Kalman filter (EKF). We quantitatively evaluate our method using real night sky data, comparing its results with those from a space-ready active-pixel sensor (APS) star tracker. We demonstrate that our method is an order-of-magnitude more accurate than existing methods due to improved signal modeling and state estimation, while providing more frequent updates and greater motion tolerance than conventional APS trackers. We provide all code and the first dataset of events synchronized with APS solutions.

Multi-view clustering represents one of the most established paradigms within the field of unsupervised learning and has witnessed a surge in popularity in recent years. View-pair form contrastive learning allows for consistently representing multiple views by maximizing mutual information between each two views. This approach permits multi-view clustering to discern consistent latent representations across multiple views. However, two significant issues emerge when this approach is considered. i)it is challenging to ascertain which two views are most appropriate for contrastive learning when there are more than three views, particularly without prior knowledge. ii) when all views are included in contrastive learning, multi-view clustering performance is compromised by poor quality views. To tackle these issues, we present a novel Efficient Dual Selection Mechanism for deep Multi-View Clustering framework, termed EASEMVC. Specifically, EASEMVC first constructs a view graph based on the OT distance between the bipartite graph of each view. It then designs a view selection module to realize an efficient view-level selection process through the view topology relations in the view graph structure. Additionally, a cross-view sample graph structure is constructed at the sample level, with the sample topological relations in the cross-view sample graph structure being employed to generate reliable sample learning weights. Based on the view pairs and sample weights selected by the aforementioned method, we employ contrastive learning within the theoretical framework of information theory to obtain consistent representations between views. Extensive experiments on six benchmark datasets have demonstrated that the proposed EASEMVC outperforms the state-of-the-art methods.

3D Gaussian splatting (3DGS) has shown impressive performance in 3D scene reconstruction. However, it suffers from severe degradation when the number of training views is limited, resulting in blur and floaters. Many works have been devoted to standardize the optimization process of 3DGS through regularization techniques. However, we identify that inadequate initialization is a critical issue overlooked by current studies. To address this, we propose EAP-GS, a method to enhance initialization for fast, accurate, and stable few-shot scene reconstruction. Specifically, we introduce an Attentional Pointcloud Augmentation (APA) technique, which retains two-view tracks as an option for pointcloud generation. Additionally, the scene complexity is used to determine the required density distribution, thereby constructing a better pointcloud. We implemented APA by extending Structure-From-Motion (SFM) to focus on pointcloud generation in regions with complex structure but sparse pointcloud distribution, which significantly increases the number of valuable points and effectively harmonizes the density distribution. A better pointcloud leads to more accurate scene geometry and mitigates local overfitting during reconstruction stage. Furthermore, our APA can be framed as a modular augmentation to existing methods with minimal overhead. Experimental results from various indoor and outdoor scenes demonstrate that the proposed EAP-GS achieves outstanding scene reconstruction performance and surpasses state-of-the-art methods. Project page: https://osierddr.github.io/eapgs/

The increasing demand for immersive AR/VR applications and spatial intelligence has heightened the need to generate high-quality scene-level and 360deg panoramic video. However, most video diffusion models are constrained by limited resolution and aspect ratio, which restricts their applicability to scene-level dynamic content synthesis. In this work, we propose DynamicScaler, addressing these challenges by enabling spatially scalable and panoramic dynamic scene synthesis that preserves coherence across panoramic scenes of arbitrary size. Specifically, we introduce a Offset Shifting Denoiser, facilitating efficient, synchronous, and coherent denoising panoramic dynamic scenes via a diffusion model with fixed resolution through a seamless rotating Window, which ensures seamless boundary transitions and consistency across the entire panoramic space, accommodating varying resolutions and aspect ratios. Additionally, we employ a Global Motion Guidance mechanism to ensure both local detail fidelity and global motion continuity. Extensive experiments demonstrate our method achieves superior content and motion quality in panoramic scene-level video generation, offering a training-free, efficient, and scalable solution for immersive dynamic scene creation with constant VRAM consumption regardless of the output video resolution. Project page is available at https://dynamic-scaler.pages.dev/new.

This study addresses the limitations of existing dynamic pseudo-labeling (DPL) techniques, which often utilize static or dynamic thresholds for confident sample selection. The existing methods fail to capture the non-linear relationship between task accuracy and model confidence, particularly in the context of overconfidence. This can limit the model's learning opportunities for high entropy samples that significantly influence a model's generalization ability. To solve this, we propose a novel gradient pass-based DPL technique that incorporates the high-entropy samples, which are typically overlooked. Our approach introduces two classifiers--low gradient pass (LGP) and high gradient pass (HGP)--to derive over- and under-confident dynamic thresholds that indicate the class-wise overconfidence acceleration, respectively. By combining the under- and over-confident states from the GP classifiers, we create a more adaptive and accurate PL method. Our main contributions highlight the importance of considering both low and high-confidence samples in enhancing the model's robustness and generalization for improved PL performance.

We propose a novel framework for the statistical analysis of genus-zero 4D surfaces, i.e., 3D surfaces that deform and evolve overtime. This problem is particularly challenging due to the arbitrary parameterizations of these surfaces and their varying deformation speeds, necessitating effective spatiotemporal registration. Traditionally, 4D surfaces are discretized, in space and time, before computing their spatiotemporal registrations, geodesics and statistics. However, this approach may result in suboptimal solutions and, as we demonstrate in this paper, is not necessary. In contrast, we treat 4D surfaces as continuous functions in both space and time. We introduce Dynamic Spherical Neural Surfaces (D-SNS), an efficient smooth and continuous spatiotemporal representation for genus-0 4D surfaces. We then demonstrate how to perform core 4D shape analysis tasks such as spatiotemporal registration, geodesics computation, and mean 4D shape estimation, directly on these continuous representations without upfront discretization and meshing. By integrating neural representations with classical Riemannian geometry and statistical shape analysis techniques, we provide the building blocks for enabling full functional shape analysis. We demonstrate the efficiency of the framework on 4D human and face datasets.

Text-guided motion editing enables high-level semantic control and iterative modifications beyond traditional keyframe animation. Existing methods rely on limited pre-collected training triplets (original motion, edited motion, and instruction), which severely hinders their versatility in diverse editing scenarios. We introduce MotionCutMix, an online data augmentation technique that dynamically generates training triplets by blending body part motions based on input text. While MotionCutMix effectively expands the training distribution, the compositional nature introduces increased randomness and potential body part incoordination. To model such a rich distribution, we present MotionReFit, an auto-regressive diffusion model with a motion coordinator. The auto-regressive architecture facilitates learning by decomposing long sequences, while the motion coordinator mitigates the artifacts of motion composition. Our method handles both spatial and temporal motion edits directly from high-level human instructions, without relying on additional specifications or LLM. Through extensive experiments, we show that MotionReFit achieves state-of-the-art performance in text-guided motion editing. Ablation studies further verify that MotionCutMix significantly improves the model's generalizability while maintaining training convergence.

Non-exemplar Class Incremental Learning (NECIL) enables models to continuously acquire new classes without retraining from scratch and storing old task exemplars, addressing privacy and storage issues. However, the absence of data from earlier tasks exacerbates the challenge of catastrophic forgetting in NECIL. In this paper, we propose a novel framework called Dynamic Integration of task-specific Adapters (DIA), which comprises two key components: Task-Specific Adapter Integration (TSAI) and Patch-Level Model Alignment. TSAI boosts compositionality through a patch-level adapter integration strategy, aggregating richer task-specific information while maintaining low computation costs. Patch-Level Model Alignment maintains feature consistency and accurate decision boundaries via two specialized mechanisms: Patch-Level Distillation Loss (PDL) and Patch-Level Feature Reconstruction (PFR). Specifically, on the one hand, the PDL preserves feature-level consistency between successive models by implementing a distillation loss based on the contributions of patch tokens to new class learning. On the other hand, the PFR promotes classifier alignment by reconstructing old class features from previous tasks that adapt to new task knowledge, thereby preserving well-calibrated decision boundaries. Comprehensive experiments validate the effectiveness of our DIA, revealing significant improvements on NECIL benchmark datasets while maintaining an optimal balance between computational complexity and accuracy.

Deep neural networks remain vulnerable to statistical variations in data, even with advances in normalization techniques. Existing methods use fixed-size normalization sets, restricting their adaptability to evolving and diverse data characteristics. We introduce Dynamic Group Normalization (DGN), a framework that dynamically adjusts channel grouping based on statistical awareness, ensuring a flexible and optimized formation of channel groups. By leveraging an efficient spatio-temporal mechanism, DGN continuously evaluates inter-channel relationships within layers and across training epochs, ensuring robust and responsive adaptation to the updated data statistics. Extensive evaluations of 34 architectures and 11 computer vision benchmarks show the consistent superiority of DGN over traditional normalization methods. It achieves significant accuracy gains in classification, detection, and segmentation tasks while maintaining computational efficiency. Moreover, it outperforms traditional methods in challenging scenarios, including out-of-distribution generalization, imbalanced long-tailed distributions, and corrupted data.

Sound-guided object segmentation has drawn considerable attention for its potential to enhance multimodal perception. Previous methods primarily focus on developing advanced architectures to facilitate effective audio-visual interactions, without fully addressing the inherent challenges posed by audio natures, i.e., (1) feature confusion due to the overlapping nature of audio signals, and (2) audio-visual matching difficulty from the varied sounds produced by the same object. To address these challenges, we propose Dynamic Derivation and Elimination (DDESeg): a novel audio-visual segmentation framework. Specifically, to mitigate feature confusion, DDESeg reconstructs the semantic content of the mixed audio signal by enriching the distinct semantic information of each individual source, deriving representations that preserve the unique characteristics of each sound. To reduce the matching difficulty, we introduce a discriminative feature learning module, which enhances the semantic distinctiveness of generated audio representations. Considering that not all derived audio representations directly correspond to visual features (e.g., off-screen sounds), we propose a dynamic elimination module to filter out non-matching elements. This module facilitates targeted interaction between sounding regions and relevant audio semantics. By scoring the interacted features, we identify and filter out irrelevant audio information, ensuring accurate audio-visual alignment. Comprehensive experiments demonstrate that our framework achieves superior performance in AVS datasets. Our code will be publicly available.

Blind Face Video Restoration (BFVR) focuses on reconstructing high-quality facial image sequences from degraded video inputs. The main challenge is address unknown degradations, while maintaining temporal consistency across frames. Current blind face restoration methods are primarily designed for images, and directly applying these approaches to BFVR will encounter a significant drop in restoration performance. In this work, we proposed Dynamic Content Prediction with Motion-aware Priors, referred to as DCP-MP. We develop a motion-aware semantic dictionary by encoding the semantic information of high-quality videos into discrete elements, and capturing the motion information in terms of element relationships, which are derived from the dynamic temporal changes within videos. For the purpose of utilizing dictionary to represent the degraded video, we train a temporal-aware element predictor, conditioned on degraded content, to learn the prediction of discrete elements in dictionary. The predicted elements will be refined, conditioned on motion information captured by the motion-aware semantic dictionary, to enhance temporal coherence. To alleviate deviation from the original structure information, we propose a conditional structure feature correction module that corrects the features flowing from the encoder to the generator. Through extensive experiments, we validate the effectiveness of our design components and demonstrate the superior performance of DCP-MP in synthesizing high-quality video.

Annotating camera poses on dynamic Internet videos at scale is critical for advancing fields like realistic video generation and simulation. However, collecting such a dataset is difficult, as most Internet videos are unsuitable for pose estimation. Furthermore, annotating dynamic Internet videos present significant challenges even for state-of-the-art methods. In this paper, we introduce DynPose-100K, a large-scale dataset of dynamic Internet videos annotated with camera poses. Our collection pipeline addresses filtering using a carefully combined set of task-specific and generalist models. For pose estimation, we combine the latest techniques of point tracking, dynamic masking, and structure-from-motion to achieve improvements over the state-of-the-art approaches. Our analysis and experiments demonstrate that DynPose-100K is both large-scale and diverse across several key attributes, opening up avenues for advancements in various downstream applications.

Neural Radiance Fields (NeRFs) have made significant advances in rendering novel photorealistic views for both static and dynamic scenes. However, most prior works assume ideal conditions of artifact-free visual inputs i.e., images and videos. In real scenarios, artifacts such as object motion blur, camera motion blur, or lens defocus blur are ubiquitous. Some recent studies have explored novel view synthesis using blurred input frames by examining either camera motion blur, defocus blur, or both. However, these studies are limited to static scenes. In this work, we enable NeRFs to deal with object motion blur whose local nature stems from the interplay between object velocity and camera exposure time. Often, the object motion is unknown and time varying, and this adds to the complexity of scene reconstruction. Sports videos are a prime example of how rapid object motion can significantly degrade video quality for static cameras by introducing motion blur. We present an approach for realizing motion blur-free novel views of dynamic scenes from input videos with object motion blur captured from static cameras spanning multiple poses. We propose a NeRF-based analytical framework that elegantly correlates object three-dimensional (3D) motion across views as well as time to the observed blurry videos. Our proposed method DynaMoDe-NeRF (Dynamic Motion-aware Deblurring NeRF) is self-supervised and reconstructs the dynamic 3D scene, renders sharp novel views by blind deblurring, and recovers the underlying 3D motion and blur parameters. We provide comprehensive experimental analysis on synthetic and real data to validate our approach. To the best of our knowledge, this is the first work to address localized object motion blur in the NeRF domain.

Robotic manipulation in embodied AI critically depends on large-scale, high-quality datasets that reflect realistic object interactions and physical dynamics. However, existing data collection pipelines are often slow, expensive, and heavily reliant on manual efforts. We present DynScene, a diffusion-based framework for generating dynamic robotic manipulation scenes directly from textual instructions. Unlike prior methods that focus solely on static environments or isolated robot actions, DynScene decomposes the generation into two phases static scene synthesis and action trajectory generation allowing fine-grained control and diversity. Our model enhances realism and physical feasibility through scene refinement (layout sampling, quaternion quantization) and leverages residual action representation to enable action augmentation, generating multiple diverse trajectories from a single static configuration. Experiments show DynScene achieves 26.8x faster generation, 1.84x higher accuracy, and 28% greater action diversity than human-crafted data. Furthermore, agents trained with DynScene exhibit up to 19.4% higher success rates across complex manipulation tasks. Our approach paves the way for scalable, automated dataset generation in robot learning.