Metraipolis › archive › dc_62a4fc00149b
Feedforward Novel View Synthesis for Heterogeneous Cameras — arXiv:2610.03522
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.03522
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T09:08:47.154Z
- SHA-256 of the archived text
56c59a1294be15e90aa00bffd94520c71c748b716bb9a3c21b3765ac817d5937- Stable URL of this page
https://metraipolis.com/documento/dc_62a4fc00149b
How to cite
Feedforward Novel View Synthesis for Heterogeneous Cameras — arXiv:2610.03522 — arXiv (en), https://arxiv.org/abs/2610.03522 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_62a4fc00149b (Metraipolis archive dc_62a4fc00149b, sha256 56c59a1294be15e90aa00bffd94520c71c748b716bb9a3c21b3765ac817d5937)
BibTeX
@misc{dc62a4fc00149b,
title = {Feedforward Novel View Synthesis for Heterogeneous Cameras — arXiv:2610.03522},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.03522},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_62a4fc00149b; sha256 56c59a1294be15e90aa00bffd94520c71c748b716bb9a3c21b3765ac817d5937},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.03522. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Feed-forward novel view synthesis has recently shown promising results from sparse posed images, but most existing methods assume that context and target views share a fixed camera family. This homogeneous-camera assumption breaks in practical multi-sensor systems, where perspective, fisheye, and panoramic cameras may coexist and where the target projection may be unseen during training. We study feed-forward NVS across heterogeneous central cameras and identify a key ambiguity introduced by tokenization: a visual token aggregates a projection-dependent bundle of pixel rays, while existing camera encodings mainly expose absolute rays or token-center relations. To address this, we combine token-center relative Camera Positional Encodings and proposed local raymaps, a token-level representation that explicitly describes the intra-patch ray distribution summarized by each token. We further propose projection-aware 2D RoPE, which replaces raw image-grid coordinates with ray-induced angular coordinates so that relative positional reasoning is aligned across camera projections. Together, these components treat diverse cameras as calibrated samplings of a shared ray space rather than separate visual domains. On ScanNet++ with heterogeneous-camera system, our method improves over camera-conditioned baselines under mixed-camera evaluation and demonstrates zero-shot generalization to panoramic views. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-10-05 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2610.03522 — 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 2026-10-06T08:21:44.261Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-10-05?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).