AI Paper Atlas

Research map / 3D vision / 3D generation

DualBEV: Unifying Dual View Transformation with Probabilistic Correspondences

Peidong Li, Wancheng Shen, Qihao Huang, Dixiao Cui

ECCV 2024 · 3D vision › 3D generation · approach: Learning 3D reconstruction from images · 22 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 ProbNet BEV probability (ablation)BEVDepth baseline · nuScenes valNDS: 40.7 -> 41.1Improved
add HeightTrans (3D-to-2D features) (ablation)Prob-LSS · nuScenes valNDS: 41.1 -> 41.5Improved
add CAF module for soft feature selection (ablation)DualBEV · nuScenes valNDS: 41.5 -> 41.6Improved
add SAE module (spatial attention for BEV probability) (ablation)DualBEV · nuScenes valNDS: 41.6 -> 42.5Improved
add SAE module on mAP (ablation)DualBEV · nuScenes valmAP: 35.3 -> 35.2No clear effect
use projection probability P_proj (disable by uniform depth) (ablation)DualBEV · nuScenes valNDS: 40.0 -> 50.4Improved
add both image and BEV probabilities to projection probability (ablation)DualBEV · nuScenes valNDS: 48.8 -> 50.4Improved
replace BEV Pooling with Prob-SamplingBEVDet · nuScenes valNDS: 38.2 -> 39.0Improved
replace BEV Pooling with Prob-Sampling on mAPBEVDet · nuScenes valmAP: 30.7 -> 30.6No clear effect
use multi-resolution height sampling (13 points) instead of uniform sampling (ablation)HeightTrans · nuScenes valNDS: 41.9 -> 42.5 (vs 4 uniform), 42.3 -> 42.5 (vs 16 uniform)Improved
use DFF one-stage fusion instead of FB-BEV style refinement (ablation)DualBEV fusion · nuScenes valNDS: 41.7 -> 42.5Improved
extend probability filtering from image space (SA-BEV) to BEV space (Prob-LSS) (ablation)LSS · nuScenes valmAP: 30.9 -> 31.5Improved

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