Metraipolis › archive › dc_d60fc256a99b
DynOSeg: Dynamic Object Segmentation via Motion-Geometry Fusion — arXiv:2611.04452
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.04452
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-04T12:56:26.558Z
- SHA-256 of the archived text
91168e6291de837501e681d625c46178a88e8c61f21c0625d6791b544aa6fe63- Stable URL of this page
https://metraipolis.com/documento/dc_d60fc256a99b
How to cite
DynOSeg: Dynamic Object Segmentation via Motion-Geometry Fusion — arXiv:2611.04452 — arXiv (en), https://arxiv.org/abs/2611.04452 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d60fc256a99b (Metraipolis archive dc_d60fc256a99b, sha256 91168e6291de837501e681d625c46178a88e8c61f21c0625d6791b544aa6fe63)
BibTeX
@misc{dcd60fc256a99b,
title = {DynOSeg: Dynamic Object Segmentation via Motion-Geometry Fusion — arXiv:2611.04452},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.04452},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d60fc256a99b; sha256 91168e6291de837501e681d625c46178a88e8c61f21c0625d6791b544aa6fe63},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.04452. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Moving Object Segmentation (MOS) detects and separates dynamic objects from the static background in a video, which plays a fundamental role in dynamic-scene understanding. Most MOS methods rely on pure visual motion cues alone, such as optical flow or point tracks, which is inherently ambiguous due to the compounded camera and object motions as well as motion-induced appearance changes, e.g. shadows and reflections. Naive fusion of additional information such as depth and semantics, however, cannot leverage their complementarity to the fullest extent. We therefore propose DynOSeg, a novel MOS approach that takes on a two-stage fusion structure. DynOSeg first combines a geometry-aware residual map and depth encoding into a geometric representation of motion, delineating camera motions and object dynamics. We then further incorporate semantic features to refine object understanding. We have additionally curated a diverse training corpus including CARLA-MOS, a new synthetic urban-driving dataset for MOS training. Our experiments show that DynOSeg consistently outperforms published state-of-the-art MOS methods across a diverse range of datasets. Our code and pretrained models can be found at this https URL Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2611.04452 — 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 2026-11-04T12:33:47.149Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).