paper-with-me

Papers

SpotlessSplats: Ignoring Distractors in 3D Gaussian Splatting

2024-06-28 · Sara Sabour, Lily Goli, George Kopanas, Mark Matthews, Dmitry Lagun, Leonidas Guibas, Alec Jacobson, David J. Fleet, Andrea Tagliasacchi

3D Gaussian Splatting (3DGS) is a promising technique for 3D reconstruction, offering efficient training and rendering speeds, making it suitable for real-time applications.However, current methods require highly controlled environments (no moving people or wind-blown elements, and consistent lighting) to meet the inter-view consistency assumption of 3DGS. This makes reconstruction of real-world captures problematic. We present SpotLessSplats, an approach that leverages pre-trained and general-purpose features coupled with robust optimization to effectively ignore transient distractors. Our method achieves state-of-the-art reconstruction quality both visually and quantitatively, on casual captures. Additional results available at: https://spotlesssplats.github.io

📄 PDF Abstract BibTeX arXiv:2406.20055

Code (1)

lilygoli/SpotLessSplats jax

Tasks

3DGS3D Reconstruction

Similar Papers 제목 키워드 기반

Robust 3D Gaussian Splatting for Novel View Synthesis in Presence of Distractors

2024-08-21 · Paul Ungermann, Armin Ettenhofer, Matthias Nießner, Barbara Roessle

3D Gaussian Splatting has shown impressive novel view synthesis results; nonetheless, it is vulnerable to dynamic objects polluting the input data of an otherwise static scene, so called distractors. Distractors have sev…

Novel View Synthesis

DeSplat: Decomposed Gaussian Splatting for Distractor-Free Rendering

2024-11-29 · CVPR 2025 1 · Yihao Wang, Marcus Klasson, Matias Turkulainen, Shuzhe Wang 외

Gaussian splatting enables fast novel view synthesis in static 3D environments. However, reconstructing real-world environments remains challenging as distractors or occluders break the multi-view consistency assumption …

3D ReconstructionNovel View Synthesis

PDF-GS: Progressive Distractor Filtering for Robust 3D Gaussian Splatting

2026-04-14 · Kangmin Seo, MinKyu Lee, Tae-Young Kim, ByeongCheol Lee 외 arxiv

Recent advances in 3D Gaussian Splatting (3DGS) have enabled impressive real-time photorealistic rendering. However, conventional training pipelines inherently assume full multi-view consistency among input images, which…

MVGSR: Multi-View Consistency Gaussian Splatting for Robust Surface Reconstruction

2025-03-11 · Chenfeng Hou, Qi Xun Yeo, Mengqi Guo, YongXin Su 외

3D Gaussian Splatting (3DGS) has gained significant attention for its high-quality rendering capabilities, ultra-fast training, and inference speeds. However, when we apply 3DGS to surface reconstruction tasks, especiall…

3DGSSurface Reconstruction

HarmoGS: Robust 3D Gaussian Splatting in the Wild via Conflict-Aware Gradient Harmonization

2026-05-13 · Yulei Kang, Tianze Zhu, Jian-Fang Hu, Jianhuang Lai 외 arxiv

In-the-wild 3D Gaussian Splatting remains challenging due to transient distractors and illumination-induced cross-view appearance inconsistencies. Existing methods mainly rely on image-level masking to suppress unreliabl…