AI Paper Atlas

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

Object-Scene-Camera Decomposition and Recomposition for Data Efficient Monocular 3D Object Detection

Zhaonian Kuang, Rui Ding, Meng Yang, Xinhu Zheng, Gang Hua

IJCV 2026 · Detection and segmentation › 3D detection and driving · approach: Monocular 3D object detection · 1 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 the decomposition-recomposition scheme to base detectorsMonoDLE · KITTI test carAP3D moderate: 12.23 -> 18.04Improved
add the scheme to MonoDGPMonoDGP · KITTI test carAP3D moderate: 18.72 -> 21.10Improved
add the scheme to MonoDETRMonoDETR · KITTI val carAP3D moderate: 20.61 -> 23.43Improved
train with only 10% annotation plus the scheme vs baseline with the same 10%MonoDLE · KITTI val carAP3D moderate: 4.67 -> 15.73Improved
train with 10% annotation plus the scheme vs full annotation baselineDID-M3D · KITTI val carAP3D moderate: 17.30 -> 17.22No clear effect
add the scheme to DID-M3D on Waymo-MonoDID-M3D · Waymo-Mono vehicle IoU 0.7 Level_1AP3D: 2.64 -> 3.73Improved
add the scheme to PETR with 10% sparse labelsPETR · Waymo-Ring allNDS*: 0.132 -> 0.375Improved
add the scheme to DID-M3D at far range 50m+DID-M3D · Waymo-Mono 50-inf m, Level_1AP3D: 0.89 -> 0.75Hurt
add object-scene recomposition (ablation)MonoDLE · KITTI valAP3D moderate: 12.76 -> 16.92Improved
add object-scene decomposition (ablation)MonoDLE · KITTI valAP3D moderate: 16.92 -> 19.02Improved
add camera pose perturbation (ablation)MonoDLE · KITTI valAP3D moderate: 19.02 -> 20.42Improved
mix raw and empty scenes (r_empty 0.5) instead of only empty scenes (ablation)MonoDLE · KITTI valAP3D moderate: 13.65 -> 20.42Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 5 of 5 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