Metraipolis › archive › dc_960f4834b2f2

EPIC: Epipolar-Consistent 360° Immersive Stereo Video Generation — arXiv:2609.38689

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.38689
License (as archived): CC0-1.0
Archived: 2026-10-07T13:44:33.937Z
SHA-256 of the archived text: 7b5234b302bd633d8d41a973f6fdb8841eecbb55785668e96c653a3e923f957e
Stable URL of this page: https://metraipolis.com/documento/dc_960f4834b2f2

How to cite

EPIC: Epipolar-Consistent 360° Immersive Stereo Video Generation — arXiv:2609.38689 — arXiv (en), https://arxiv.org/abs/2609.38689 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_960f4834b2f2 (Metraipolis archive dc_960f4834b2f2, sha256 7b5234b302bd633d8d41a973f6fdb8841eecbb55785668e96c653a3e923f957e)

BibTeX

@misc{dc960f4834b2f2,
  title = {EPIC: Epipolar-Consistent 360° Immersive Stereo Video Generation — arXiv:2609.38689},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.38689},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_960f4834b2f2; sha256 7b5234b302bd633d8d41a973f6fdb8841eecbb55785668e96c653a3e923f957e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.38689. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Immersive displays can enable rich and diverse virtual experiences. Manually authoring every possible experience to realize this potential, however, is prohibitively expensive, difficult to scale, and impractical. Generative AI models could remove this bottleneck, but today's models are built for conventional displays and cannot generate the high-resolution, stereoscopic $360^\circ$ content required for immersive viewing. Further, temporal and stereo inconsistencies that may be tolerable on conventional displays can become highly disruptive when viewed through an immersive headset. Here, we address this gap with a zero-shot generative pipeline that extends existing video diffusion models into 4K stereoscopic $360^\circ$ videos. Inspired from binocular vision and depth perception, we develop an epipolar-aware $360^\circ$ image matching metric that captures the temporal and stereo geometric inconsistencies across views. We then use this metric as a preference signal for direct preference optimization with limited training data. Our work enables $360^\circ$ stereo video generation and provides a scalable path for bringing generative content to immersive displays, allowing diverse mixed reality experiences on demand.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-01 in cs.HC).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Human-Computer Interaction (cs.HC).
Pagina del lavoro: https://arxiv.org/abs/2609.38689 — 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 2026-10-07T13:17:28.265Z dalla pagina https://arxiv.org/catchup/cs.HC/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).