Splat-based 3D Scene Reconstruction with Extreme Motion-blur

• URL: http://arxiv.org/abs/2607.16926v1
• Date: Sat, 18 Jul 2026 18:41:02 GMT
• Title: Splat-based 3D Scene Reconstruction with Extreme Motion-blur
• Abstract summary: Under dim illumination, RGB frames often suffer from severe motion blur due to extended exposure times.<n>We propose a splat-based 3D scene reconstruction method from RGB-D input that effectively handles extreme motion blur.<n>This approach has broad implications for 3D mapping applications in robotics, autonomous navigation, and augmented reality.
• Score: 20.81830991798879
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We propose a splat-based 3D scene reconstruction method from RGB-D input that effectively handles extreme motion blur, a frequent challenge in low-light environments. Under dim illumination, RGB frames often suffer from severe motion blur due to extended exposure times, causing traditional camera pose estimation methods, such as COLMAP, to fail. This results in inaccurate camera pose and blurry color input, compromising the quality of 3D reconstructions. Although recent 3D reconstruction techniques like Neural Radiance Fields and Gaussian Splatting have demonstrated impressive results, they rely on accurate camera trajectory estimation, which becomes challenging under fast motion or poor lighting conditions. Furthermore, rapid camera movement and the limited field of view of depth sensors reduce point cloud overlap, limiting the effectiveness of pose estimation with the ICP algorithm. To address these issues, we introduce a method that combines camera pose estimation and image deblurring using a Gaussian Splatting framework, leveraging both 3D Gaussian splats and depth inputs for enhanced scene representation. Our method first aligns consecutive RGB-D frames through optical flow and ICP, then refines camera poses and 3D geometry by adjusting Gaussian positions for optimal depth alignment. To handle motion blur, we model camera movement during exposure and deblur images by comparing the input with a series of sharp, rendered frames. Experiments on a new RGB-D dataset with extreme motion blur show that our method outperforms existing approaches, enabling high-quality reconstructions even in challenging conditions. This approach has broad implications for 3D mapping applications in robotics, autonomous navigation, and augmented reality. Both code and dataset are publicly available on https://github.com/KAIST-VCLAB/gs-extreme-motion-blur.

Related papers

• Unblur-SLAM: Dense Neural SLAM for Blurry Inputs [68.94602568657164]
  Un-SLAM is a novel pipeline for sharp 3D reconstruction from blurred image inputs.<n>We demonstrate state-of-the-art performance in the presence of both motion blur and defocus blur.<n>Experiments on several real-world datasets demonstrate consistent improvements in both pose estimation and sharp reconstruction results.
  arXiv  Detail & Related papers  (2026-03-26T14:29:47Z)
• BSGS: Bi-stage 3D Gaussian Splatting for Camera Motion Deblurring [32.5099324617965]
  Bi-Stage 3D Gaussian Splatting is a novel framework to reconstruct 3D scenes from motion-blurred images.<n>We propose a subframe gradient aggregation strategy to optimize both stages.<n>Experiments verify the effectiveness of our proposed deblurring method and show its superiority over the state of the arts.
  arXiv  Detail & Related papers  (2025-10-14T13:26:56Z)
• DeblurSplat: SfM-free 3D Gaussian Splatting with Event Camera for Robust Deblurring [50.21760380168387]
  We propose the first Structure-from-Motion (SfM)-free deblurring 3D Gaussian Splatting method via event camera, dubbed DeSplat.<n>We leverage the pretrained capability of the dense stereo module (DUSt3R) to directly obtain accurate initial point clouds from blurred images.
  arXiv  Detail & Related papers  (2025-09-23T11:21:54Z)
• PCR-GS: COLMAP-Free 3D Gaussian Splatting via Pose Co-Regularizations [102.0476991174456]
  COLMAP-free 3DGS has attracted increasing attention due to its remarkable performance in reconstructing high-quality 3D scenes from unposed images or videos.<n>We propose PCR-GS, an innovative COLMAP-free 3DGS technique that achieves superior 3D scene modeling and camera pose estimation via camera pose co-regularization.
  arXiv  Detail & Related papers  (2025-07-18T13:09:33Z)
• Dark-EvGS: Event Camera as an Eye for Radiance Field in the Dark [51.68144172958247]
  We propose Dark-EvGS, the first event-assisted 3D GS framework that enables the reconstruction of bright frames from arbitrary viewpoints.<n>Our method achieves better results than existing methods, conquering radiance field reconstruction under challenging low-light conditions.
  arXiv  Detail & Related papers  (2025-07-16T05:54:33Z)
• PhotonSplat: 3D Scene Reconstruction and Colorization from SPAD Sensors [17.636234096112446]
  We introduce PhotonSplat, a framework designed to reconstruct 3D scenes directly from SPAD binary images.<n>Our approach incorporates a novel 3D spatial filtering technique to reduce noise in the renderings.<n>We extend our method to incorporate dynamic scene representations, making it suitable for scenes with moving objects.
  arXiv  Detail & Related papers  (2025-06-26T18:04:28Z)
• High-Speed Dynamic 3D Imaging with Sensor Fusion Splatting [15.309934457166394]
  Capturing and reconstructing high-speed dynamic 3D scenes has numerous applications in computer graphics, vision, and interdisciplinary fields such as robotics, aerodynamics, and evolutionary biology.<n>Traditional RGB cameras suffer from low frame rates, limited exposure times, and narrow baselines.<n>We propose a novel sensor fusion approach using Gaussian splatting, which combines RGB, depth, and event cameras to capture and reconstruct scenes at high speeds.
  arXiv  Detail & Related papers  (2025-02-07T03:17:31Z)
• Deblur4DGS: 4D Gaussian Splatting from Blurry Monocular Video [55.704264233274294]
  We propose Deblur4DGS to reconstruct a high-quality 4D model from blurry monocular video.<n>We transform continuous dynamic representations within an exposure time into the exposure time estimation.<n>Beyond novel-view synthesis, Deblur4DGS can be applied to improve blurry video from multiple perspectives.
  arXiv  Detail & Related papers  (2024-12-09T12:02:11Z)
• MBA-SLAM: Motion Blur Aware Gaussian Splatting SLAM [15.752529196306648]
  We propose a dense visual deblur SLAM pipeline (i.e. MBA-SLAM) to handle severe motion-blurred inputs and enhance image deblurring.<n>Our approach integrates an efficient motion blur-aware tracker with either neural fields or Gaussian Splatting based mapper.<n>In experiments, we demonstrate that MBA-SLAM surpasses previous state-of-the-art methods in both camera localization and map reconstruction.
  arXiv  Detail & Related papers  (2024-11-13T01:38:06Z)
• 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)
• Shakes on a Plane: Unsupervised Depth Estimation from Unstabilized Photography [54.36608424943729]
  We show that in a ''long-burst'', forty-two 12-megapixel RAW frames captured in a two-second sequence, there is enough parallax information from natural hand tremor alone to recover high-quality scene depth. We devise a test-time optimization approach that fits a neural RGB-D representation to long-burst data and simultaneously estimates scene depth and camera motion.
  arXiv  Detail & Related papers  (2022-12-22T18:54:34Z)

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.