Metraipolis › archive › dc_35becfa4b0e7
Per-View Gaussian Predictions Enable Training-Free Distractor Filtering in Feed-Forward 3DGS — arXiv:2608.26951
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.26951
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T14:30:19.427Z
- SHA-256 of the archived text
569f46b17e0eb4a81009b6916ce9af170abe79babe0943560726f3e96719e776- Stable URL of this page
https://metraipolis.com/documento/dc_35becfa4b0e7
How to cite
Per-View Gaussian Predictions Enable Training-Free Distractor Filtering in Feed-Forward 3DGS — arXiv:2608.26951 — arXiv (en), https://arxiv.org/abs/2608.26951 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_35becfa4b0e7 (Metraipolis archive dc_35becfa4b0e7, sha256 569f46b17e0eb4a81009b6916ce9af170abe79babe0943560726f3e96719e776)
BibTeX
@misc{dc35becfa4b0e7,
title = {Per-View Gaussian Predictions Enable Training-Free Distractor Filtering in Feed-Forward 3DGS — arXiv:2608.26951},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.26951},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_35becfa4b0e7; sha256 569f46b17e0eb4a81009b6916ce9af170abe79babe0943560726f3e96719e776},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.26951. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Feed-forward 3D Gaussian Splatting reconstructs an explicit Gaussian representation from multiple input images in one network execution, making 3D reconstruction increasingly accessible for casual captures. However, such captures frequently contain transient objects that appear in only a subset of the views. Such content can be encoded into the per-view Gaussians associated with the inputs that observe it and remain in the combined representation despite being observed by no other input. As a result, it may produce blurred, duplicated, or floating artifacts in novel views. We introduce a training-free filtering procedure that exploits this per-view prediction structure. For each input, we exclude its associated Gaussians and render the same camera using the remaining representation, revealing content that is inconsistent with the other inputs. Feature similarity forms candidate regions, and rendering-based verification retains only candidates whose removal reduces reconstruction error in the other input views. The procedure operates on a single frozen prediction without retraining or scene-specific optimization. Across three reconstruction models and two distractor benchmarks, it consistently improves novel-view quality with varying numbers of input views. On clean scenes, evaluations across four models show that the original reconstructions are largely preserved. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-28 in cs.AI). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2608.26951 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-17T13:16:53.676Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).