Occ3D: A Large-Scale 3D Occupancy Prediction Benchmark for Autonomous Driving

Tao Jiang, Yue Wang, Hang Zhao, Yilun Wang, Xiaoyu Tian, Longfei Yun, Yucheng Mao, Huitong Yang

Code that ran

We lifted 1 functions out of this paper's own repositories and ran 0 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

Repository	Role	Ran
Tsinghua-MARS-Lab/Occ3D	canonical	0 of 1

Function	Status	Where it lives
array_converter	Not yet run	Tsinghua-MARS-Lab/Occ3D/utils/array_converter.py code served (permissive licence) · get_code("f1de3c53f2d16082")

Repositories linked to this paper

Tsinghua-MARS-Lab/Occ3D — marked official in Papers with Code; named in the paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Figure 1: Our Occ3D dataset demonstrates rich semantic and geometric expressiveness. (a) Diversity of scenes in the Occ3D dataset; (b) Out-of-vocabulary objects, also known as General Objects (GOs), that cannot be extensively enumerated in the real world; (c) Irregularly-shaped objects that 3D bounding boxes fail to represent their accurate geometry.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2304.14365")
get_code_for_paper("2304.14365")
have("2304.14365")

Connect an agent — have() is free.