Metraipolis › archive › dc_a862cd771d84

Think in 360°: Benchmarking and Bootstrapping Panoramic Video Reasoning — arXiv:2610.42082

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.42082
License (as archived)
CC0-1.0
Archived
2026-11-03T05:46:35.710Z
SHA-256 of the archived text
fb71d415c6e211c435284f58d84881e98f32e71deb55df657158c06b86036d57
Stable URL of this page
https://metraipolis.com/documento/dc_a862cd771d84

How to cite

Think in 360°: Benchmarking and Bootstrapping Panoramic Video Reasoning — arXiv:2610.42082 — arXiv (en), https://arxiv.org/abs/2610.42082 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a862cd771d84 (Metraipolis archive dc_a862cd771d84, sha256 fb71d415c6e211c435284f58d84881e98f32e71deb55df657158c06b86036d57)
BibTeX
@misc{dca862cd771d84,
  title = {Think in 360°: Benchmarking and Bootstrapping Panoramic Video Reasoning — arXiv:2610.42082},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.42082},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a862cd771d84; sha256 fb71d415c6e211c435284f58d84881e98f32e71deb55df657158c06b86036d57},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.42082. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

A panoramic video captures all directions around the camera, but relevant evidence can appear in different directions and at different times. Understanding it requires models to connect observations across the viewing sphere and time. We introduce PanoVideoBench, the first manually annotated benchmark for comprehensive panoramic video understanding. Its 1,000 questions span five categories and 15 question types, with diagnostic annotations for target search and panoramic capabilities. Evaluation of 11 proprietary, open-source, and panoramic-specialized models identifies cross-view tracking and sphere-time evidence integration as their weakest capabilities. To strengthen these capabilities, we construct PanoVideoCoT, the first reasoning dataset grounded in real panoramic video, through sphere-time-grounded synthesis that converts verified panoramic observations and successful agentic explorations into 13,465 QA-CoT pairs. Starting from a general video MLLM, PanoVideoReasoner learns from this corpus through Panoramic CoT SFT and Evidence-Privileged On-Policy Self-Distillation, a panoramic instantiation of Vision-OPD's OPSD in which the teacher uses verified perspective views to guide student-generated trajectories. It reaches 55.7% on PanoVideoBench, improving the backbone by 12.5 points and the previous SOTA by 2.6. The gains concentrate on the same spatial, cross-view, and temporal capabilities exposed by the benchmark, showing that grounded sphere-time supervision can equip a general video MLLM with panoramic reasoning.

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/2610.42082 — 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 2026-11-03T05:33:32.325Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).