Metraipolis › archive › dc_71eebd17036f
EviSplat: Preserving Multi-View Evidence in 3D Gaussian Splatting for Open-Vocabulary Segmentation — arXiv:2609.34853
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.34853
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T21:02:59.839Z
- SHA-256 of the archived text
c1050493481e097f9d8ac135232abab64db4183c3637add0b6e6a810ac16a436- Stable URL of this page
https://metraipolis.com/documento/dc_71eebd17036f
How to cite
EviSplat: Preserving Multi-View Evidence in 3D Gaussian Splatting for Open-Vocabulary Segmentation — arXiv:2609.34853 — arXiv (en), https://arxiv.org/abs/2609.34853 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_71eebd17036f (Metraipolis archive dc_71eebd17036f, sha256 c1050493481e097f9d8ac135232abab64db4183c3637add0b6e6a810ac16a436)
BibTeX
@misc{dc71eebd17036f,
title = {EviSplat: Preserving Multi-View Evidence in 3D Gaussian Splatting for Open-Vocabulary Segmentation — arXiv:2609.34853},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.34853},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_71eebd17036f; sha256 c1050493481e097f9d8ac135232abab64db4183c3637add0b6e6a810ac16a436},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.34853. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Open-vocabulary 3D scene understanding enables object localization and segmentation from free-form text queries without a fixed category vocabulary. Many recent methods build on 3D Gaussian Splatting and consolidate multi-view observations, such as masked crops from individual views, into language features or compact object descriptors before the query is known. However, observations of the same object vary across viewpoints and are not equally informative: some reveal cues relevant to a particular query, whereas others provide incomplete or misleading evidence. Pre-query consolidation can therefore suppress cues on which a later query depends. We introduce EviSplat, which preserves individual observation features as evidence for later text queries. EviSplat retains individual observation features within class-agnostic 3D instances that represent objects, object parts, or background regions. It also learns, for each Gaussian, a distribution describing which visual appearances its observations support. Given a text query, EviSplat scores each instance using its most relevant observations. It then computes a score for each Gaussian by combining instance-level relevance with locally supported evidence, weighted by how often and how unambiguously that Gaussian was observed. Different queries can thus draw on different visual cues from the same preserved evidence. Experiments across diverse datasets and evaluation protocols demonstrate state-of-the-art performance, supporting the benefit of preserving multi-view evidence until query time and aggregating it according to the query. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.34853 — 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 2026-10-07T20:29:03.170Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).