Sign inGet started
Paper · arXiv

Orbia: Do Generated Videos Form a Consistent 3D World?

Video generators serve as interactive worlds for exploration and simulation, yet realistic and visually appealing frames do not necessarily depict a consistent 3D world. Existing benchmarks assess selected geometric properties or use vision-language models to judge memory and consistency, leaving systematic 3D evaluation underexplored. We introduce Orbia, the first benchmark dedicated to a systematic and comprehensive evaluation of 3D consistency in interactive world models. Through controlled exploration and revisit, we organize the evaluation into three dimensions: input preservation, generated-content persistence, and 3D self-consistency. For input preservation, registered RGB-D refere...

AuthorsDongyue Lu, Guian Fang, Hur Lim et al.
Primary categorycs.CV
Published14 October 2026
Last updated at source14 October 2026
cs.CV
Embed this entry
<iframe src="https://silytics.si/embed/item/743fe4a8-2f4b-4bcf-bc7e-e947bf01b5a2" width="420" height="190" style="border:0" loading="lazy" title="Silytics entry"></iframe>

Free, no tracking. More about feeds and embeds.

Popularity, last 2 days

0 now. Counts as reported by the source, snapshotted daily by Silytics.

Recent changes

  • 16 Oct 2026 Description: Video generators serve as interactive worlds for exploration and simulation, yet realistic and visually appealing frames do not necessarily depict a consistent 3D world. Existing benchmarks assess selected geometric properties or use vision → Video generators serve as interactive worlds for exploration and simulation, yet realistic and visually appealing frames do not necessarily depict a consistent 3D world. Existing benchmarks assess selected geometric properties or use vision
  • 16 Oct 2026 Topics added cs.CV removed hf-daily-papers, rgb-d references, gaussian rendering, cross-view depth correspondence, feature correspondence, 3d self-consistency, interactive world models, video generators

Changes detected by Silytics between refreshes of the source.

Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.