AI Paper Atlas

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

Geometry-Based Distance Decomposition for Monocular 3D Object Detection

Xuepeng Shi, Qi Ye, Xiaozhi Chen, Chuangrong Chen, Zhixiang Chen, Tae-Kyun Kim

ICCV 2021 · Detection and segmentation › 3D detection and driving · approach: Monocular 3D object detection · 170 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 direct distance regression with geometry-based decomposition (ablation)MonoRCNN baseline · KITTI val (Car)AP3D R40 Mod: 10.52 -> 10.97Improved
use decomposition instead of eight projected corners plus physical size (ablation)MonoRCNN · KITTI val (Car)AP3D R40 Mod: 8.96 -> 10.97Improved
add uncertainty-aware regression loss on H and h_rec (ablation)MonoRCNN (D) · KITTI val (Car)AP3D R40 Mod: 10.97 -> 12.00Improved
add uncertainty-aware regression loss on H and h_rec (ablation)MonoRCNN (D) · KITTI val (Car)APBEV R40 Mod: 15.52 -> 17.23Improved
sort boxes by score/(f H sigma_hrec) instead of score (ablation)MonoRCNN (D+U) · KITTI val (Car)AP3D R40 Mod: 12.00 -> 13.19Improved
sort boxes by score/(f H sigma_hrec) instead of score (ablation)MonoRCNN (D+U) · KITTI val (Car)AP3D R40 Easy: 16.94 -> 16.61Hurt
sort boxes by score/(f H sigma_hrec) instead of score (ablation)MonoRCNN (D+U) · KITTI val (Car)APBEV R40 Mod: 17.23 -> 19.22Improved
replace predicted physical height with groundtruth at inferenceMonoRCNN · KITTI val (Car), self-consistencyAP3D R40 Mod: 12.00 -> 10.82Hurt
replace predicted physical size with groundtruth at inferencekeypoint-based K · KITTI val (Car), self-consistencyAP3D R40 Mod: 8.96 -> 9.51Improved
use decomposition instead of M3D-RPN distance regression in cross-dataset testMonoRCNN · nuScenes cross-testmean distance error (m): 2.75 -> 2.39Improved
evaluate far objects in cross-dataset testMonoRCNN vs M3D-RPN · nuScenes cross-test, 40m+mean distance error (m): 10.73 -> 8.65Improved

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