Metraipolis › archive › dc_e77433be5a78
Dynamic-Robust Photometric-Semantic Reconstruction for Open-Vocabulary 3D Scene Understanding — arXiv:2608.29177
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.29177
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T09:53:44.905Z
- SHA-256 of the archived text
5668229bc0b342539a65aa403d7b7954c8db0dda3c34653d151328da6b34b208- Stable URL of this page
https://metraipolis.com/documento/dc_e77433be5a78
How to cite
Dynamic-Robust Photometric-Semantic Reconstruction for Open-Vocabulary 3D Scene Understanding — arXiv:2608.29177 — arXiv (en), https://arxiv.org/abs/2608.29177 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e77433be5a78 (Metraipolis archive dc_e77433be5a78, sha256 5668229bc0b342539a65aa403d7b7954c8db0dda3c34653d151328da6b34b208)
BibTeX
@misc{dce77433be5a78,
title = {Dynamic-Robust Photometric-Semantic Reconstruction for Open-Vocabulary 3D Scene Understanding — arXiv:2608.29177},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.29177},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e77433be5a78; sha256 5668229bc0b342539a65aa403d7b7954c8db0dda3c34653d151328da6b34b208},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.29177. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
The integration of novel view synthesis (NVS) and open-vocabulary segmentation (OVS) has recently yielded powerful feed-forward 3D foundation models. However, their inherent reliance on static-scene assumptions leads to severe misalignment of spatial features in unconstrained dynamic environments. To bridge this critical gap, we propose SPAR, a novel joint semantic-geometric encoding architecture that explicitly isolates transient dynamic noise prior to latent space aggregation. Furthermore, we introduce a dynamic-region-aware end-to-end training paradigm that structurally couples motion estimation with multi-view visual and semantic learning. This unified approach enables the network to inherently resolve motion conflicts and distill multi-view consistent, temporally stable scene representations from dynamic inputs. Extensive experiments on the challenging D-RE10K benchmark demonstrate that SPAR achieves state-of-the-art performance. Our end-to-end approach achieves exceptional novel view synthesis quality, yielding a PSNR of 22.15 dB and 23.33 dB given only 3 and 4 input views respectively. Despite being trained in a self-supervised manner, our model achieves an mIoU of 88.5% for motion mask prediction. Furthermore, our analysis reveals a strong inter-task synergy between photometric scene reconstruction and semantic understanding, where semantic synthesis learning consistently enhances photometric fidelity in novel view rendering. Code will be available at this https URL . Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-01 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2608.29177 — 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 2026-10-17T09:28:47.995Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).