AI Paper Atlas

Research map / 3D vision / 3D generation

ALOcc: Adaptive Lifting-Based 3D Semantic Occupancy and Cost Volume-Based Flow Predictions

Dubing Chen, Jin Fang, Wencheng Han, Xinjing Cheng, Junbo Yin, Chengzhong Xu, Fahad Shahbaz Khan, Jianbing Shen

ICCV 2025 · 3D vision › 3D generation · approach: Vision-based 3D occupancy prediction · 8 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
add adaptive lifting (ablation)ALOcc-2D-40 · Occ3D with maskmIoU^m: 43.5 -> 44.5Improved
add semantic prototype-based occupancy head (vs FBOcc head) (ablation)ALOcc-2D-40 · Occ3D with maskmIoU^m: 42.1 -> 44.5Improved
add semantic prototype head (ablation)ALOcc-2D-40 · Occ3D with maskRayIoU: 39.9 -> 42.5Improved
add adaptive lifting without SP head (ablation)ALOcc-2D-40 · Occ3D with maskmIoU^m: 41.2 -> 42.1Improved
add flow head with simple convolution (ablation)ALOcc-2D-40 · OpenOccRayIoU: 42.4 -> 39.7Hurt
add bin classification to flow head (ablation)flow head · OpenOccmAVE: 0.597 -> 0.565Improved
add BEV cost volume to flow head (ablation)flow head · OpenOccOcc Score: 40.7 -> 41.1Improved
add channel scaling from 40 to 80 (ablation)ALOcc-Flow-2D · OpenOccOcc Score: 41.1 -> 42.1Improved
add conversion of depth weights to occlusion weights (ablation)adaptive lifting · Occ3D without maskmIoU^m: 41.2 -> 41.6Improved
add depth denoising (ablation)adaptive lifting · Occ3D without maskmIoU^m: 41.8 -> 42.1Improved
set inter-object occlusion m to 3 instead of 0 (ablation)adaptive lifting · Occ3DmIoU^m: 41.6 -> 42.1Improved
use 3D volume encoding instead of 2D height-compressedALOcc · Occ3D with mask (ResNet-50)mIoU^m: 44.8 -> 45.5Improved

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