Dynamic Gaussian Splatting from Defocused and Motion-blurred Monocular Videos

• URL: http://arxiv.org/abs/2510.10691v3
• Date: Fri, 31 Oct 2025 15:40:49 GMT
• Title: Dynamic Gaussian Splatting from Defocused and Motion-blurred Monocular Videos
• Authors: Xuankai Zhang, Junjin Xiao, Qing Zhang,
• Abstract summary: This paper presents a unified framework that allows high-quality dynamic Gaussian Splatting from both defocused and motion-red monocular videos.<n>We use a blur prediction network that exploits blur-related scene and camera information and is subject to a blur-aware sparsity constraint.<n>Our method outperforms the state-of-the-art methods in generating photorealistic novel view synthesis from defocused and motion-red monocular videos.
• Score: 9.965683509488203
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This paper presents a unified framework that allows high-quality dynamic Gaussian Splatting from both defocused and motion-blurred monocular videos. Due to the significant difference between the formation processes of defocus blur and motion blur, existing methods are tailored for either one of them, lacking the ability to simultaneously deal with both of them. Although the two can be jointly modeled as blur kernel-based convolution, the inherent difficulty in estimating accurate blur kernels greatly limits the progress in this direction. In this work, we go a step further towards this direction. Particularly, we propose to estimate per-pixel reliable blur kernels using a blur prediction network that exploits blur-related scene and camera information and is subject to a blur-aware sparsity constraint. Besides, we introduce a dynamic Gaussian densification strategy to mitigate the lack of Gaussians for incomplete regions, and boost the performance of novel view synthesis by incorporating unseen view information to constrain scene optimization. Extensive experiments show that our method outperforms the state-of-the-art methods in generating photorealistic novel view synthesis from defocused and motion-blurred monocular videos. Our code is available at https://github.com/hhhddddddd/dydeblur.

Related papers

• Breaking the Vicious Cycle: Coherent 3D Gaussian Splatting from Sparse and Motion-Blurred Views [40.70901994944635]
  We introduce CoherentGS, a framework for high-fidelity 3D reconstruction from sparse and blurry images.<n>Our key insight is to address these compound degradations using a dual-prior strategy.<n>CoherentGS significantly outperforms existing methods, setting a new state-of-the-art for this challenging task.
  arXiv  Detail & Related papers  (2025-12-11T07:36:35Z)
• Blur2seq: Blind Deblurring and Camera Trajectory Estimation from a Single Camera Motion-blurred Image [2.842028685390758]
  Motion blur caused by camera shake, particularly under large or rotational movements, is a major challenge in image restoration.<n>We propose a deep learning framework that jointly estimates the latent sharp image and the underlying camera motion trajectory from a single blurry image.<n>Our method achieves state-of-the-art performance on both synthetic and real datasets.
  arXiv  Detail & Related papers  (2025-10-23T13:26:07Z)
• Fine-grained Defocus Blur Control for Generative Image Models [66.30016220484394]
  Current text-to-image diffusion models excel at generating diverse, high-quality images.<n>We introduce a novel text-to-image diffusion framework that leverages camera metadata.<n>Our model enables superior fine-grained control without altering the depicted scene.
  arXiv  Detail & Related papers  (2025-10-07T17:59:15Z)
• BokehDiff: Neural Lens Blur with One-Step Diffusion [53.11429878683807]
  We introduce BokehDiff, a lens blur rendering method that achieves physically accurate and visually appealing outcomes.<n>Our method employs a physics-inspired self-attention module that aligns with the image formation process.<n>We adapt the diffusion model to the one-step inference scheme without introducing additional noise, and achieve results of high quality and fidelity.
  arXiv  Detail & Related papers  (2025-07-24T03:23:19Z)
• Bokeh Diffusion: Defocus Blur Control in Text-to-Image Diffusion Models [26.79219274697864]
  Bokeh Diffusion is a scene-consistent bokeh control framework.<n>We introduce a hybrid training pipeline that aligns in-the-wild images with synthetic blur augmentations.<n>Our approach enables flexible, lens-like blur control, supports downstream applications such as real image editing via inversion.
  arXiv  Detail & Related papers  (2025-03-11T13:49:12Z)
• Oscillation Inversion: Understand the structure of Large Flow Model through the Lens of Inversion Method [60.88467353578118]
  We show that a fixed-point-inspired iterative approach to invert real-world images does not achieve convergence, instead oscillating between distinct clusters. We introduce a simple and fast distribution transfer technique that facilitates image enhancement, stroke-based recoloring, as well as visual prompt-guided image editing.
  arXiv  Detail & Related papers  (2024-11-17T17:45:37Z)
• BAGS: Blur Agnostic Gaussian Splatting through Multi-Scale Kernel Modeling [32.493592776662005]
  We analyze the robustness of Gaussian-Splatting-based methods against various image blur. We propose Blur Agnostic Gaussian Splatting (BAGS) to address this issue. BAGS introduces additional 2D modeling capacities such that a 3D-consistent and high quality scene can be reconstructed despite image-wise blur.
  arXiv  Detail & Related papers  (2024-03-07T22:21:08Z)
• Diffusion Priors for Dynamic View Synthesis from Monocular Videos [59.42406064983643]
  Dynamic novel view synthesis aims to capture the temporal evolution of visual content within videos. We first finetune a pretrained RGB-D diffusion model on the video frames using a customization technique. We distill the knowledge from the finetuned model to a 4D representations encompassing both dynamic and static Neural Radiance Fields.
  arXiv  Detail & Related papers  (2024-01-10T23:26:41Z)
• Lightweight High-Speed Photography Built on Coded Exposure and Implicit Neural Representation of Videos [34.152901518593396]
  The demand for compact cameras capable of recording high-speed scenes with high resolution is steadily increasing. However, achieving such capabilities often entails high bandwidth requirements, resulting in bulky, heavy systems unsuitable for low-capacity platforms. We propose a novel approach to address these challenges by combining the classical coded exposure imaging technique with the emerging implicit neural representation for videos.
  arXiv  Detail & Related papers  (2023-11-22T03:41:13Z)
• Blind Motion Deblurring with Pixel-Wise Kernel Estimation via Kernel Prediction Networks [0.0]
  We propose a learning-based motion deblurring method based on dense non-uniform motion blur estimation. We train the networks on sharp/blurry pairs synthesized according to a convolution-based, non-uniform motion blur degradation model.
  arXiv  Detail & Related papers  (2023-08-05T20:23:13Z)
• Joint Video Multi-Frame Interpolation and Deblurring under Unknown Exposure Time [101.91824315554682]
  In this work, we aim ambitiously for a more realistic and challenging task - joint video multi-frame and deblurring under unknown exposure time. We first adopt a variant of supervised contrastive learning to construct an exposure-aware representation from input blurred frames. We then build our video reconstruction network upon the exposure and motion representation by progressive exposure-adaptive convolution and motion refinement.
  arXiv  Detail & Related papers  (2023-03-27T09:43:42Z)
• Animation from Blur: Multi-modal Blur Decomposition with Motion Guidance [83.25826307000717]
  We study the challenging problem of recovering detailed motion from a single motion-red image. Existing solutions to this problem estimate a single image sequence without considering the motion ambiguity for each region. In this paper, we explicitly account for such motion ambiguity, allowing us to generate multiple plausible solutions all in sharp detail.
  arXiv  Detail & Related papers  (2022-07-20T18:05:53Z)
• ParticleSfM: Exploiting Dense Point Trajectories for Localizing Moving Cameras in the Wild [57.37891682117178]
  We present a robust dense indirect structure-from-motion method for videos that is based on dense correspondence from pairwise optical flow. A novel neural network architecture is proposed for processing irregular point trajectory data. Experiments on MPI Sintel dataset show that our system produces significantly more accurate camera trajectories.
  arXiv  Detail & Related papers  (2022-07-19T09:19:45Z)
• TimeLens: Event-based Video Frame Interpolation [54.28139783383213]
  We introduce Time Lens, a novel indicates equal contribution method that leverages the advantages of both synthesis-based and flow-based approaches. We show an up to 5.21 dB improvement in terms of PSNR over state-of-the-art frame-based and event-based methods.
  arXiv  Detail & Related papers  (2021-06-14T10:33:47Z)

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.