AI Paper Atlas

Research map / 3D vision / 3D generation

OccGen: Generative Multi-modal 3D Occupancy Prediction for Autonomous Driving

Guoqing Wang, Zhongdao Wang, Pin Tang, Jilai Zheng, Xiangxuan Ren, Bailan Feng, Chao Ma

ECCV 2024 · 3D vision › 3D generation · approach: Vision-based 3D occupancy prediction · 42 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 discriminative one-shot occupancy prediction with diffusion-based noise-to-occupancy decoder (multi-modal)CONet · nuScenes-Occupancy val (multi-modal)mIoU: 20.1 -> 22.0Improved
apply generative OccGen on camera-only inputC-CONet · nuScenes-Occupancy val (camera-only)mIoU: 12.8 -> 14.5Improved
apply OccGen to camera-based SemanticKITTIOccFormer · SemanticKITTI valmIoU: 13.46 -> 13.74Improved
OccGen IoU on SemanticKITTI vs VoxFormerOccGen · SemanticKITTI valIoU: 44.02 -> 36.87Hurt
add the progressive refinement (generative) decoder (ablation)baseline occupancy network · nuScenes-Occupancy multi-modalmIoU: 20.4 -> 21.6Improved
add the proposed multi-modal conditional encoder only (ablation)baseline occupancy network · nuScenes-Occupancy multi-modalmIoU: 20.4 -> 20.7Improved
add 3D deformable cross-attention and self-attention (ablation)OccGen decoder · nuScenes-Occupancy multi-modalmIoU: 20.7 -> 22.0Improved
add diffusion time module (ablation)OccGen decoder · nuScenes-Occupancy multi-modalmIoU: 21.7 -> 22.0Improved
add hard 2D-to-3D view transformation alone (ablation)OccGen encoder · nuScenes-Occupancy multi-modalmIoU: 21.4 -> 21.5No clear effect
add both hard LSS and geometry mask (ablation)OccGen encoder · nuScenes-Occupancy multi-modalmIoU: 21.4 -> 22.0Improved
increase sampling steps from 1 to 2 (multi-modal) (ablation)OccGen · nuScenes-Occupancy multi-modalmIoU: 21.7 -> 21.8Improved
OccGen latency vs CONet at one sampling step (multi-modal)OccGen · nuScenes-Occupancy multi-modallatency (ms): 344.8 -> 357.1Hurt

Later papers that compared with this method

3 later accepted papers report OccGen as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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