AI Paper Atlas

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

RTM3D: Real-time Monocular 3D Detection from Object Keypoints for Autonomous Driving

Peixuan Li, Huaici Zhao, Pengfei Liu, Feidao Cao

ECCV 2020 · Detection and segmentation › 3D detection and driving · approach: Monocular 3D object detection · 382 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 keypoint FPN (ablation)RTM3D DLA34 · KITTI val1 AP3D easyAP3D: 50.14 -> 54.36Improved
add keypoint FPN (ablation)RTM3D DLA34 · KITTI val1 AP3D moderateAP3D: 15.99 -> 16.86Improved
add keypoint FPN (ablation)RTM3D DLA34 · KITTI val1inference time (s): 0.054 -> 0.055No clear effect
add orientation to dimension prior (ablation)RTM3D DLA34 · KITTI val1 AP3D IoU=0.5 easyAP3D: 51.21 -> 54.18Improved
add orientation to dimension prior (ablation)RTM3D DLA34 · KITTI val1 AP3D IoU=0.7 moderateAP3D: 17.05 -> 16.02Hurt
add distance prior (ablation)RTM3D DLA34 · KITTI val1 AP3D IoU=0.7 easyAP3D: 20.23 -> 20.76Improved
add keypoint offset (ablation)RTM3D DLA34 · KITTI val1 AP3D IoU=0.5 hardAP3D: 35.13 -> 35.84Improved
add dimension prior to orientation only (ablation)RTM3D DLA34 · KITTI val1 AP3D IoU=0.7 easyAP3D: 3.12 -> 20.23Improved
use all optional components instead of dimension only (ablation)RTM3D DLA34 · KITTI val1inference time (s): 0.058 -> 0.055Improved
DLA34 backbone instead of ResNet18RTM3D · KITTI val1 AP3D IoU=0.7 moderateAP3D: 14.14 -> 16.86Improved
DLA34 backbone instead of ResNet18RTM3D · KITTI val1inference time (s): 0.035 -> 0.055Hurt
RTM3D vs M3D-RPN on test setRTM3D DLA34 · KITTI test AP3D easyAP3D: 14.76 -> 13.61Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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