Metraipolis › archive › dc_cb10cafe0a9d
Privacy-Preserving Semantic Segmentation from High-Resolution Depth and Ultra-Low-Resolution RGB — arXiv:2609.28360
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.28360
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T12:35:26.178Z
- SHA-256 of the archived text
5f62794194e88ce558d2a039d4959ec8b97b209347f3e6ac47a2872f03a2d142- Stable URL of this page
https://metraipolis.com/documento/dc_cb10cafe0a9d
How to cite
Privacy-Preserving Semantic Segmentation from High-Resolution Depth and Ultra-Low-Resolution RGB — arXiv:2609.28360 — arXiv (en), https://arxiv.org/abs/2609.28360 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cb10cafe0a9d (Metraipolis archive dc_cb10cafe0a9d, sha256 5f62794194e88ce558d2a039d4959ec8b97b209347f3e6ac47a2872f03a2d142)
BibTeX
@misc{dccb10cafe0a9d,
title = {Privacy-Preserving Semantic Segmentation from High-Resolution Depth and Ultra-Low-Resolution RGB — arXiv:2609.28360},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.28360},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cb10cafe0a9d; sha256 5f62794194e88ce558d2a039d4959ec8b97b209347f3e6ac47a2872f03a2d142},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.28360. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
As mobile robots become increasingly integrated into everyday environments, privacy risks arising from onboard cameras have become a growing concern. Ultra-low-resolution (ULR) RGB can mitigate visual privacy exposure at the source, but ULR appearance alone substantially limits semantic and spatial understanding. We therefore introduce a privacy-preserving asymmetric sensing setting that combines high-resolution (HR) depth with ULR RGB, preserving dense geometry while restricting fine-grained visual information. To address the severe information imbalance between HR depth and ULR RGB, we propose a joint 2D framework using HR geometry to guide semantic-oriented RGB reconstruction and RGB-D segmentation. Despite reliable frame-level predictions, consistent scene-level understanding remains challenging under the asymmetric HR depth--ULR RGB setting. We therefore develop an end-to-end 2D-to-3D pipeline that consolidates 2D semantic features for 3D segmentation. Experiments on ScanNet show that our method achieves the best 2D and 3D segmentation performance among privacy-preserving approaches and delivers the strongest zero-shot transfer to SUN RGB-D and SceneNN. Privacy recoverability analysis shows that our proposed HR depth--ULR RGB input reduces the recoverability of sensitive data, and real-robot experiments demonstrate the utility of the resulting 3D semantics for object-goal navigation. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-24 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Robotics (cs.RO). Pagina del lavoro: https://arxiv.org/abs/2609.28360 — 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 2026-10-08T12:12:35.811Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).