AI Paper Atlas

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

MonoDETR: Depth-guided Transformer for Monocular 3D Object Detection

Renrui Zhang, Han Qiu, Tai Wang, Ziyu Guo, Ziteng Cui, Yu Qiao, Hongsheng Li, Peng Gao

ICCV 2023 · Detection and segmentation › 3D detection and driving · approach: Monocular 3D object detection · 271 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 depth-guided transformer and depth predictor (ablation)center-guided baseline (MonoDLE-like) · KITTI val (car, AP3D Mod.)AP3D: 15.15 -> 20.61Improved
add depth cross-attention guidance to visual transformer (ablation)MonoDETR · KITTI val (car, AP3D Mod.)AP3D: 17.81 -> 20.61Improved
add transformer on top of depth predictor (ablation)MonoDETR · KITTI val (car, AP3D Mod.)AP3D: 16.05 -> 20.61Improved
use one-block global self-attention depth encoder (ablation)MonoDETR · KITTI val (car, AP3D Mod.)AP3D: 18.38 -> 20.61Improved
place depth cross-attention first in each decoder block (ablation)depth-guided decoder · KITTI val (car, AP3D Mod.)AP3D: 19.28 -> 20.61Improved
supervise foreground depth with object-wise labels instead of dense depth (ablation)foreground depth map · KITTI val (car, AP3D Mod.)AP3D: 19.85 -> 20.61Improved
use linear-increasing discretization instead of uniform or spacing-increasing (ablation)foreground depth map · KITTI val (car, AP3D Mod.)AP3D: 18.90 -> 20.61Improved
use learnable meter-wise depth positional encoding instead of sinusoidal or per-bin (ablation)depth cross-attention · KITTI val (car, AP3D Mod.)AP3D: 19.57 -> 20.61Improved
2D sin/cos positional encoding instead of none (ablation)depth cross-attention · KITTI val (car, AP3D Mod.)AP3D: 18.94 -> 18.63Hurt
plug depth-guided modules into PETRv2PETRv2 · nuScenes valNDS: 0.496 -> 0.508Improved
plug depth-guided modules into BEVFormerBEVFormer · nuScenes valNDS: 0.517 -> 0.526Improved

Later papers that compared with this method

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

8 more not listed.

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