AI Paper Atlas

Research map / 3D vision / 3D generation

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

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

NeurIPS 2023 · 3D vision › 3D generation · approach: Vision-based 3D occupancy prediction · 55 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace BEVFormer with CTF-Occ coarse-to-fine encoderBEVFormer · Occ3D-nuScenesmIoU: 26.88 -> 28.53Improved
replace BEVFormer with CTF-Occ coarse-to-fine encoderBEVFormer · Occ3D-WaymomIoU: 16.76 -> 18.73Improved
add OHEM loss to top-k token selection (ablation)CTF-Occ · Occ3D-WaymomIoU: 14.06 -> 18.43Improved
use top-k instead of random token selection (ablation)CTF-Occ · Occ3D-WaymomIoU: 16.62 -> 18.43Improved
use top-k instead of uncertain token selection (ablation)CTF-Occ · Occ3D-WaymomIoU: 17.37 -> 18.43No clear effect
add OHEM loss (small objects) (ablation)CTF-Occ · Occ3D-Waymo pedestrianIoU: 4.16 -> 7.04Improved
add multi-frame aggregation to single-frame points (ablation)label pipeline · 3D-2D consistencymIoU: 13.32 -> 17.65Improved
add voxelization (size 0.1) to multi-frame points (ablation)label pipeline · 3D-2D consistencymIoU: 17.65 -> 41.17Improved
add mesh reconstruction at voxel 0.1 (ablation)label pipeline · 3D-2D consistencymIoU: 41.17 -> 41.99Improved
reduce voxel size from 0.1 to 0.05 (with mesh) (ablation)label pipeline · 3D-2D consistencymIoU: 41.99 -> 43.58Improved
add image-guided voxel refinement (ablation)label pipeline · 3D-2D consistencymIoU: 43.58 -> 58.50Improved
add LiDAR input to BEVFormer (fusion)BEVFormer · Occ3D-WaymomIoU: 16.76 -> 39.05Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy