AI Paper Atlas

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

DID-M3D: Decoupling Instance Depth for Monocular 3D Object Detection

Liang Peng, Xiaopei Wu, Zheng Yang, Haifeng Liu, Deng Cai

ECCV 2022 · Detection and segmentation › 3D detection and driving · approach: Monocular 3D object detection · 92 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
decouple instance depth into visual and attribute depth (ablation)grid baseline · KITTI val Car moderateAP3D R40: 11.24 -> 13.24Improved
decouple instance depth on the naive baseline (ablation)naive baseline · KITTI val Car moderateAP_BEV/AP3D: 13.43/8.70 -> 16.49/10.94Improved
add both depth uncertainties (ablation)DID-M3D decoupled depth · KITTI val Car moderateAP3D R40: 13.24 -> 13.91Improved
add instance depth confidence to 2D confidence (ablation)DID-M3D · KITTI val Car moderateAP3D R40: 13.91 -> 15.57Improved
add adaptive aggregation over grids (ablation)DID-M3D · KITTI val Car moderateAP3D R40: 15.57 -> 16.12Improved
add adaptive aggregation to coupled baseline (ablation)coupled baseline · KITTI val Car moderateAP_BEV/AP3D: 0.1/0.03 gainsNo clear effect
add affine augmentation with scaled visual depth (ablation)DID-M3D · KITTI val Car moderateAP3D R40: 12.76 -> 16.12Improved
add affine augmentation but scale attribute depth (ablation)DID-M3D · KITTI val Car moderateAP3D R40: 12.76 -> 12.65Hurt
use grid 1x1 instead of 7x7 (ablation)DID-M3D · KITTI val Car moderateAP3D R40: 16.12 -> 13.01Hurt
use grid 19x19 instead of 7x7 (ablation)DID-M3D · KITTI val Car moderateAP3D R40: 16.12 -> 15.13Hurt
add grid design to naive baseline (ablation)naive baseline · KITTI val Car moderateAP_BEV/AP3D: 1.0/0.24 gainsImproved
add DID-M3D components to baselinebaseline detector · KITTI val Pedestrian moderateAP3D R40: 3.88 -> 5.87Improved

Later papers that compared with this method

5 later accepted papers report DID-M3D as a baseline in their results tables; 4 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