RealVDeblur: One-Step Diffusion for Generalizable Real-World Video Deblurring

• URL: http://arxiv.org/abs/2607.20628v1
• Date: Wed, 22 Jul 2026 18:01:03 GMT
• Title: RealVDeblur: One-Step Diffusion for Generalizable Real-World Video Deblurring
• Abstract summary: Real-world video deblurring remains challenging due to diverse motion patterns, complex degradations, and the scarcity of realistic training data.<n>This work presents textbfRealVDeblur, an efficient generative framework designed to improve in-the-wild robustness under diverse real capture conditions.
• Score: 38.962439175751975
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Real-world video deblurring remains challenging due to diverse motion patterns, complex degradations, and the scarcity of realistic training data, yet robust restoration is critical for downstream pipelines such as mobile imaging and 3D reconstruction. This work presents \textbf{RealVDeblur}, an efficient generative framework designed to improve in-the-wild robustness under diverse real capture conditions. First, a large-scale, physically grounded blur synthesis pipeline is constructed from scene-level 3D Gaussian Splatting (3DGS) assets and high-frame-rate videos, providing realistic training data covering both camera-induced and object-motion blur. Second, a video diffusion prior is leveraged for restoration; to better accommodate frame-dependent blur variations, temporal compression in the VAE is disabled and a frame-wise encoding scheme is adopted. For practical deployment on long videos, multi-step diffusion sampling is distilled into an efficient one-step generator, and a training-free Temporal Window Mask stabilizes inference beyond the training horizon with constant memory usage. Extensive experiments on diverse real-world benchmarks demonstrate strong perceptual quality, semantic fidelity, and temporal consistency on unseen videos, as well as improved robustness in downstream 3D reconstruction under severe motion blur. Project page: https://rbjin.github.io/RealVDeblur

Related papers

• RealityBridge: Bridging Editable 3D Gaussian Splatting Driving Simulations and Real-World Videos [40.2251078105003]
  We propose a structure-preserving and asset-aware Sim-to-Real framework for edited 3DGS driving videos.<n>RealityBridge uses multimodal controls, including rendered videos, foreground masks, edge maps, and semantic masks, together with a lightweight GateNet.<n>Experiments show that RealityBridge outperforms existing methods in artifact removal, illumination, and long-sequence temporal consistency.
  arXiv  Detail & Related papers  (2026-06-15T06:33:13Z)
• ViSA: 3D-Aware Video Shading for Real-Time Upper-Body Avatar Creation [62.86900540547787]
  Current 3D avatar generation methods often suffer from artifacts such as blurry textures and stiff, unnatural motion.<n>We propose a novel approach that combines the strengths of both paradigms.<n>By uniting the geometric stability of 3D reconstruction with the generative capabilities of video models, our method produces high-fidelity digital avatars.
  arXiv  Detail & Related papers  (2025-12-08T17:10:29Z)
• EvDiff: High Quality Video with an Event Camera [77.07279880903009]
  Reconstructing intensity images from events is a highly ill-posed task due to the inherent ambiguity of absolute brightness.<n>We propose EvDiff, an event-based diffusion model that follows a surrogate training framework to produce high-quality videos.
  arXiv  Detail & Related papers  (2025-11-21T18:49:18Z)
• Enhanced Velocity Field Modeling for Gaussian Video Reconstruction [21.54297055995746]
  High-fidelity 3D video reconstruction is essential for enabling real-time rendering of dynamic scenes with realistic motion in virtual and augmented reality (VR/AR)<n>We propose a flow-empowered velocity field modeling scheme tailored for Gaussian video reconstruction, dubbed FlowGaussian-VR.<n>It consists of two core components: a velocity field rendering (VFR) pipeline which enables optical flow-based optimization, and a flow-assisted adaptive densification (FAD) strategy that adjusts the number and size of Gaussians in dynamic regions.
  arXiv  Detail & Related papers  (2025-07-31T16:26:22Z)
• Temporal-Consistent Video Restoration with Pre-trained Diffusion Models [51.47188802535954]
  Video restoration (VR) aims to recover high-quality videos from degraded ones.<n>Recent zero-shot VR methods using pre-trained diffusion models (DMs) suffer from approximation errors during reverse diffusion and insufficient temporal consistency.<n>We present a novel a Posterior Maximum (MAP) framework that directly parameterizes video frames in the seed space of DMs, eliminating approximation errors.
  arXiv  Detail & Related papers  (2025-03-19T03:41:56Z)
• Rethinking Video Tokenization: A Conditioned Diffusion-based Approach [58.164354605550194]
  New tokenizer, Diffusion Conditioned-based Gene Tokenizer, replaces GAN-based decoder with conditional diffusion model.<n>We trained using only a basic MSE diffusion loss for reconstruction, along with KL term and LPIPS perceptual loss from scratch.<n>Even a scaled-down version of CDT (3$times inference speedup) still performs comparably with top baselines.
  arXiv  Detail & Related papers  (2025-03-05T17:59:19Z)
• GaussianVideo: Efficient Video Representation via Hierarchical Gaussian Splatting [28.981174430968643]
  We introduce a novel neural representation that combines 3D Gaussian splatting with continuous camera motion modeling.<n> Experimental results show that our hierarchical learning, combined with robust camera motion modeling, captures complex dynamic scenes with strong temporal consistency.<n>This memory-efficient approach achieves high-quality rendering at impressive speeds.
  arXiv  Detail & Related papers  (2025-01-08T19:01:12Z)
• VideoLifter: Lifting Videos to 3D with Fast Hierarchical Stereo Alignment [54.66217340264935]
  VideoLifter is a novel video-to-3D pipeline that leverages a local-to-global strategy on a fragment basis.<n>It significantly accelerates the reconstruction process, reducing training time by over 82% while holding better visual quality than current SOTA methods.
  arXiv  Detail & Related papers  (2025-01-03T18:52:36Z)
• Event3DGS: Event-Based 3D Gaussian Splatting for High-Speed Robot Egomotion [54.197343533492486]
  Event3DGS can reconstruct high-fidelity 3D structure and appearance under high-speed egomotion. Experiments on multiple synthetic and real-world datasets demonstrate the superiority of Event3DGS compared with existing event-based dense 3D scene reconstruction frameworks. Our framework also allows one to incorporate a few motion-blurred frame-based measurements into the reconstruction process to further improve appearance fidelity without loss of structural accuracy.
  arXiv  Detail & Related papers  (2024-06-05T06:06:03Z)
• Gaussian Splatting on the Move: Blur and Rolling Shutter Compensation for Natural Camera Motion [25.54868552979793]
  We present a method that adapts to camera motion and allows high-quality scene reconstruction with handheld video data. Our results with both synthetic and real data demonstrate superior performance in mitigating camera motion over existing methods.
  arXiv  Detail & Related papers  (2024-03-20T06:19:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.