Unblur-SLAM: Dense Neural SLAM for Blurry Inputs

• URL: http://arxiv.org/abs/2603.26810v1
• Date: Thu, 26 Mar 2026 14:29:47 GMT
• Title: Unblur-SLAM: Dense Neural SLAM for Blurry Inputs
• Abstract summary: 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.
• Score: 68.94602568657164
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We propose Unblur-SLAM, a novel RGB SLAM pipeline for sharp 3D reconstruction from blurred image inputs. In contrast to previous work, our approach is able to handle different types of blur and demonstrates state-of-the-art performance in the presence of both motion blur and defocus blur. Moreover, we adjust the computation effort with the amount of blur in the input image. As a first stage, our method uses a feed-forward image deblurring model for which we propose a suitable training scheme that can improve both tracking and mapping modules. Frames that are successfully deblurred by the feed-forward network obtain refined poses and depth through local-global multi-view optimization and loop closure. Frames that fail the first stage deblurring are directly modeled through the global 3DGS representation and an additional blur network to model multiple blurred sub-frames and simulate the blur formation process in 3D space, thereby learning sharp details and refined sub-frame poses. Experiments on several real-world datasets demonstrate consistent improvements in both pose estimation and sharp reconstruction results of geometry and texture.

Related papers

• 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)
• EVolSplat: Efficient Volume-based Gaussian Splatting for Urban View Synthesis [61.1662426227688]
  Existing NeRF and 3DGS-based methods show promising results in achieving photorealistic renderings but require slow, per-scene optimization.<n>We introduce EVolSplat, an efficient 3D Gaussian Splatting model for urban scenes that works in a feed-forward manner.
  arXiv  Detail & Related papers  (2025-03-26T02:47:27Z)
• Deblur Gaussian Splatting SLAM [57.35366732452066]
  Deblur-SLAM is a robust RGB SLAM pipeline designed to recover sharp reconstructions from motion-blurred inputs.<n>We model the physical image formation process of motion-blurred images and minimize the error between the observed blurry images and rendered blurry images.<n>We achieve state-of-the-art results for sharp map estimation and sub-frame trajectory recovery both on synthetic and real-world blurry input data.
  arXiv  Detail & Related papers  (2025-03-16T16:59:51Z)
• GS-Blur: A 3D Scene-Based Dataset for Realistic Image Deblurring [50.72230109855628]
  We propose GS-Blur, a dataset of synthesized realistic blurry images created using a novel approach. We first reconstruct 3D scenes from multi-view images using 3D Gaussian Splatting (3DGS), then render blurry images by moving the camera view along the randomly generated motion trajectories. By adopting various camera trajectories in reconstructing our GS-Blur, our dataset contains realistic and diverse types of blur, offering a large-scale dataset that generalizes well to real-world blur.
  arXiv  Detail & Related papers  (2024-10-31T06:17:16Z)
• PonderV2: Pave the Way for 3D Foundation Model with A Universal Pre-training Paradigm [111.16358607889609]
  We introduce a novel universal 3D pre-training framework designed to facilitate the acquisition of efficient 3D representation.<n>For the first time, PonderV2 achieves state-of-the-art performance on 11 indoor and outdoor benchmarks, implying its effectiveness.
  arXiv  Detail & Related papers  (2023-10-12T17:59:57Z)
• Differentiable Blocks World: Qualitative 3D Decomposition by Rendering Primitives [70.32817882783608]
  We present an approach that produces a simple, compact, and actionable 3D world representation by means of 3D primitives. Unlike existing primitive decomposition methods that rely on 3D input data, our approach operates directly on images. We show that the resulting textured primitives faithfully reconstruct the input images and accurately model the visible 3D points.
  arXiv  Detail & Related papers  (2023-07-11T17:58:31Z)
• Depth-Aware Image Compositing Model for Parallax Camera Motion Blur [4.170640862518009]
  Camera motion introduces spatially varying blur due to the depth changes in the 3D world. We present a simple, yet accurate, Image ting Blur (ICB) model for depth-dependent varying blur.
  arXiv  Detail & Related papers  (2023-03-16T14:15:32Z)
• Pixel2Mesh++: 3D Mesh Generation and Refinement from Multi-View Images [82.32776379815712]
  We study the problem of shape generation in 3D mesh representation from a small number of color images with or without camera poses. We adopt to further improve the shape quality by leveraging cross-view information with a graph convolution network. Our model is robust to the quality of the initial mesh and the error of camera pose, and can be combined with a differentiable function for test-time optimization.
  arXiv  Detail & Related papers  (2022-04-21T03:42:31Z)
• Using Adaptive Gradient for Texture Learning in Single-View 3D Reconstruction [0.0]
  Learning-based approaches for 3D model reconstruction have attracted attention owing to its modern applications. We present a novel sampling algorithm by optimizing the gradient of predicted coordinates based on the variance on the sampling image. We also adopt Frechet Inception Distance (FID) to form a loss function in learning, which helps bridging the gap between rendered images and input images.
  arXiv  Detail & Related papers  (2021-04-29T07:52:54Z)
• Real-time Dense Reconstruction of Tissue Surface from Stereo Optical Video [10.181846237133167]
  We propose an approach to reconstruct dense three-dimensional (3D) model of tissue surface from stereo optical videos in real-time. The basic idea is to first extract 3D information from video frames by using stereo matching, and then to mosaic the reconstructed 3D models. Experimental results on ex- and in vivo data showed that the reconstructed 3D models have high resolution texture with an accuracy error of less than 2 mm.
  arXiv  Detail & Related papers  (2020-07-16T19:14:05Z)

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.