{"slug": "casdeblurgs-cascaded-2d-to-3d-multi-view-consistency-for-3d-gaussian-splatting", "title": "CasDeblurGS: Cascaded 2D-to-3D Multi-View Consistency for 3D Gaussian Splatting from Two Blurry Images", "summary": "Researchers propose CasDeblurGS, a cascaded framework that reconstructs a coherent 3D scene from only two motion-blurred images with known intrinsics, without input-view poses, auxiliary sharp images, or per-scene test-time optimization. The method improves PSNR by 1.19 dB on real-world Deblur-NeRF scenes and 2.11 dB on synthetic scenes over strong baselines.", "body_md": "arXiv:2608.10345v1 Announce Type: new\nAbstract: Free-viewpoint 3D scene media is increasingly important for immersive applications, yet practical capture often suffers from severe view sparsity and motion blur. Although neural rendering has advanced sparse-view synthesis, existing blur-aware methods typically require substantial multi-view redundancy, accurate camera poses, or costly per-scene optimization. We address a stringent yet practical setting: reconstructing a coherent 3D scene from only two motion-blurred images with known intrinsics, without input-view poses, auxiliary sharp images, or per-scene test-time optimization. To this end, we propose CasDeblurGS, a cascaded framework that progressively recovers reliable cross-view information from local 2D correspondences to global 3D guidance. Stage 1 constructs locally reliable guidance through occlusion-aware correspondence filtering, while Stage 2 aggregates the intermediate restorations into a provisional pose-free 3D Gaussian representation whose input-view re-renders provide dense global guidance for final restoration. The resulting views enable a more coherent 3D representation and higher-quality novel-view synthesis. Experiments on real-world and synthetic Deblur-NeRF scenes show consistent gains over strong baselines, improving PSNR by 1.19 dB and 2.11 dB, respectively. Progressive ablations, cross-view correspondence visualization, and camera reprojection analysis further demonstrate improvements in both rendering quality and multi-view geometric consistency.", "url": "https://wpnews.pro/news/casdeblurgs-cascaded-2d-to-3d-multi-view-consistency-for-3d-gaussian-splatting", "canonical_source": "https://arxiv.org/abs/2608.10345", "published_at": "2026-08-12 04:00:00+00:00", "updated_at": "2026-08-12 04:11:55.281416+00:00", "lang": "en", "topics": ["computer-vision", "machine-learning", "generative-ai"], "entities": ["CasDeblurGS", "Deblur-NeRF"], "alternates": {"html": "https://wpnews.pro/news/casdeblurgs-cascaded-2d-to-3d-multi-view-consistency-for-3d-gaussian-splatting", "markdown": "https://wpnews.pro/news/casdeblurgs-cascaded-2d-to-3d-multi-view-consistency-for-3d-gaussian-splatting.md", "text": "https://wpnews.pro/news/casdeblurgs-cascaded-2d-to-3d-multi-view-consistency-for-3d-gaussian-splatting.txt", "jsonld": "https://wpnews.pro/news/casdeblurgs-cascaded-2d-to-3d-multi-view-consistency-for-3d-gaussian-splatting.jsonld"}}