Metraipolis › archive › dc_acb6cb53261c

Reflection-aware Generative Novel View Synthesis — arXiv:2609.05382

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.05382
License (as archived)
CC0-1.0
Archived
2026-10-16T22:29:26.254Z
SHA-256 of the archived text
993942285f32a3c7ca0c407af619a128982f1b8d18d30ff1b5fdb4aee12c1bf3
Stable URL of this page
https://metraipolis.com/documento/dc_acb6cb53261c

How to cite

Reflection-aware Generative Novel View Synthesis — arXiv:2609.05382 — arXiv (en), https://arxiv.org/abs/2609.05382 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_acb6cb53261c (Metraipolis archive dc_acb6cb53261c, sha256 993942285f32a3c7ca0c407af619a128982f1b8d18d30ff1b5fdb4aee12c1bf3)
BibTeX
@misc{dcacb6cb53261c,
  title = {Reflection-aware Generative Novel View Synthesis — arXiv:2609.05382},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.05382},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_acb6cb53261c; sha256 993942285f32a3c7ca0c407af619a128982f1b8d18d30ff1b5fdb4aee12c1bf3},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.05382. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We propose Ref-GeNVS, a training-free, reflection-aware method for generative novel view synthesis (NVS) in mirror scenes. Existing multi-view diffusion models often fail to recognize the mirror in the scene and cannot exploit reflected content for scene generation. To fix this issue without additional training, our key idea is to treat a mirror image as two complementary views. From input images, we estimate the mirror plane and reflect camera poses to form virtual views. Based on this virtual view setup, we propose a two-stage generation method consisting of Mirror-gated attention and Reflection injection, which enables reflection-consistent NVS by explicitly leveraging reflection relationships in a multi-view diffusion model. Ref-GeNVS inherits the strong generalizability of the multi-view diffusion backbone, while it does not require finetuning. On synthetic and real scenes including mirrors, Ref-GeNVS outperforms recent generative NVS methods by generating reflection-consistent and contextually coherent novel views, revealing scene structure visible only through mirrors. Project page: this https URL

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-07 in cs.AI).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.05382 — 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 2026-10-16T22:18:11.594Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).