AI Paper Atlas

Research map / Detection and segmentation / 3D detection and driving

GUPNet++: Geometry Uncertainty Propagation Network for Monocular 3D Object Detection

Yan Lu, Xinzhu Ma, Lei Yang, Tianzhu Zhang, Yating Liu, Qi Chu, Tong He, Yonghui Li, Wanli Ouyang

TPAMI 2024 · Detection and segmentation › 3D detection and driving · approach: Monocular 3D object detection · 21 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 RoI feature maps (coordinate and category maps) to the baseline (ablation)two-stage baseline · KITTI val Car 3D@0.7AP Moderate: 11.00 -> 12.44Improved
add geometry projection depth (GeP) with directly learned uncertainty (ablation)baseline + RoI-FM · KITTI val Car 3D@0.7AP Moderate: 12.44 -> 12.79Improved
add vanilla uncertainty confidence UnC (no GeP) (ablation)baseline + RoI-FM · KITTI val Car 3D@0.7AP Moderate: 12.44 -> 13.53Improved
add GeP when depth uncertainty is learned directly (with UnC) (ablation)baseline + UnC · KITTI val Car 3D@0.7AP Easy: 19.69 -> 18.23Hurt
add geometry-guided uncertainty GeU (ablation)GeP + UnC · KITTI val Car 3D@0.7AP Moderate: 13.57 -> 15.70Improved
add Hierarchical Task Learning (HTL) to GUPNet (ablation)GeP + UnC + GeU · KITTI val Car 3D@0.7AP Easy: 20.86 -> 22.76Improved
replace GeU with GeU++ (uncertainty from both 2D and 3D heights) (ablation)GUPNet · KITTI val Car 3D@0.7AP Moderate: 16.46 -> 16.71Improved
add HTL on top of GeU++ (ablation)GUPNet++ (GeU++, UnC) · KITTI val Car 3D@0.7AP Moderate: 16.53 -> 16.71No clear effect
replace vanilla UnC with IoU-guided IoUnC (ablation)GeU++ model · KITTI val Car 3D@0.7AP Moderate: 16.53 -> 17.43Improved
replace NLL with beta-NLL Laplacian loss (ablation)GeU++ + IoUnC · KITTI val Car 3D@0.7AP Moderate: 17.43 -> 17.85Improved
replace 2D NMS with 3D-level NMS (ablation)GUPNet++ · KITTI val Car 3D@0.7AP Moderate: 17.85 -> 19.06Improved
add deformable convolution (DCN) in DLA backbone (ablation)GUPNet++ + NMS3D · KITTI val Car 3D@0.7AP Moderate: 19.06 -> 20.45Improved

Later papers that compared with this method

2 later accepted papers report GUPNet as a baseline in their results tables; 2 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