Sign inGet started
Model · Hugging Face

fengyi233/PanoBench

PanoBench Code · Paper · Models · Project PanoBench supports semantic occupancy prediction, panoptic occupancy prediction, and 4D occupancy forecasting across three complementary driving subsets. Downloads under panobench/ mirror the local data/ directory. They include occupancy labels, preprocessed CarlaOcc and KITTI360 images, calibration, poses, frame splits and nuScenes sweep information. KITTI360 benchmark frame lists, class definitions and mappings are included in the code… See the full description on the dataset page: https://huggingface.co/datasets/fengyi233/PanoBench.

Author / organizationfengyi233
License (as declared)mit
Downloads1.2K (as reported by Hugging Face)
Likes1
Created14 August 2026
Last updated at source21 October 2026
panoptic-occupancyautonomous-driving3d-scene-understanding
Embed this entry
<iframe src="https://silytics.si/embed/item/49eb0d5d-ae60-478f-ab27-5d676f0af151" width="420" height="190" style="border:0" loading="lazy" title="Silytics entry"></iframe>

Free, no tracking. More about feeds and embeds.

Popularity, last 3 days

1,197 now (+1,197 since 2026-10-21). Counts as reported by the source, snapshotted daily by Silytics.

Connected in the knowledge graph

Explore this entry in the graph

Recent changes

  • 23 Oct 2026 Description: none → PanoBench Code · Paper · Models · Project PanoBench supports semantic occupancy prediction, panoptic occupancy prediction, and 4D occupancy forecasting across three complementary driving subsets. Downloads under panobench/ mirror the local
  • 23 Oct 2026 Topics removed pytorch, dataset:fengyi233/PanoBench
  • 21 Oct 2026 License: none → mit
  • 21 Oct 2026 Topics added pytorch, panoptic-occupancy, autonomous-driving, 3d-scene-understanding, dataset:fengyi233/PanoBench

Changes detected by Silytics between refreshes of the source.

Related papers

Silytics shows public metadata from Hugging Face and links to the original. Information may be incomplete or out of date. Last refreshed 24 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.