AI Paper Atlas

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

M3D-RPN: Monocular 3D Region Proposal Network for Object Detection

Garrick Brazil, Xiaoming Liu

ICCV 2019 · Detection and segmentation › 3D detection and driving · approach: Monocular 3D object detection · 603 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 3D->2D post-optimization of orientation (ablation)M3D-RPN · KITTI val1 car ModAP_BEV: 12.99 -> 17.47Improved
add 3D->2D post-optimization of orientation (ablation)M3D-RPN · KITTI val1 car ModAP_3D: 10.99 -> 15.08Improved
add 3D->2D post-optimization of orientation (ablation)M3D-RPN · KITTI val1 car Modruntime (ms): 118 -> 128Hurt
add depth-aware convolution with b=32 bins (with post-opt) (ablation)M3D-RPN · KITTI val1 car ModAP_BEV: 17.47 -> 21.18Improved
add depth-aware convolution with b=32 bins (with post-opt) (ablation)M3D-RPN · KITTI val1 car ModAP_3D: 15.08 -> 17.06Improved
add depth-aware convolution with b=32 bins (with post-opt) (ablation)M3D-RPN · KITTI val1 car ModAP_2D: 82.16 -> 83.67Improved
add depth-aware convolution with b=1 bin (two global streams) (ablation)M3D-RPN · KITTI val1 car ModAP_3D: 15.08 -> 12.87Hurt
add depth-aware convolution with b=4 bins (ablation)M3D-RPN · KITTI val1 car ModAP_3D: 15.08 -> 14.46Hurt
add depth-aware convolution with b=4 bins (ablation)M3D-RPN · KITTI val1 car ModAP_BEV: 17.47 -> 19.14Improved
add depth-aware convolution with b=8 bins (ablation)M3D-RPN · KITTI val1 car ModAP_3D: 15.08 -> 16.04Improved
increase bins from b=8 to b=32 (ablation)M3D-RPN · KITTI val1 car ModAP_3D: 16.04 -> 17.06Improved
increase bins b from 1 to 32 (ablation)M3D-RPN · KITTI val1 car Modruntime (ms): 133 -> 161Hurt

Later papers that compared with this method

15 later accepted papers report M3D-RPN as a baseline in their results tables; 14 of them report a better number on most of the results they share with it.

7 more not listed.

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