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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add the decomposition-recomposition scheme to base detectors | MonoDLE · KITTI test car | AP3D moderate: 12.23 -> 18.04 | Improved |
| add the scheme to MonoDGP | MonoDGP · KITTI test car | AP3D moderate: 18.72 -> 21.10 | Improved |
| add the scheme to MonoDETR | MonoDETR · KITTI val car | AP3D moderate: 20.61 -> 23.43 | Improved |
| train with only 10% annotation plus the scheme vs baseline with the same 10% | MonoDLE · KITTI val car | AP3D moderate: 4.67 -> 15.73 | Improved |
| train with 10% annotation plus the scheme vs full annotation baseline | DID-M3D · KITTI val car | AP3D moderate: 17.30 -> 17.22 | No clear effect |
| add the scheme to DID-M3D on Waymo-Mono | DID-M3D · Waymo-Mono vehicle IoU 0.7 Level_1 | AP3D: 2.64 -> 3.73 | Improved |
| add the scheme to PETR with 10% sparse labels | PETR · Waymo-Ring all | NDS*: 0.132 -> 0.375 | Improved |
| add the scheme to DID-M3D at far range 50m+ | DID-M3D · Waymo-Mono 50-inf m, Level_1 | AP3D: 0.89 -> 0.75 | Hurt |
| add object-scene recomposition (ablation) | MonoDLE · KITTI val | AP3D moderate: 12.76 -> 16.92 | Improved |
| add object-scene decomposition (ablation) | MonoDLE · KITTI val | AP3D moderate: 16.92 -> 19.02 | Improved |
| add camera pose perturbation (ablation) | MonoDLE · KITTI val | AP3D moderate: 19.02 -> 20.42 | Improved |
| mix raw and empty scenes (r_empty 0.5) instead of only empty scenes (ablation) | MonoDLE · KITTI val | AP3D moderate: 13.65 -> 20.42 | Improved |
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.
- DID-M3D — DID-M3D: Decoupling Instance Depth for Monocular 3D Object Detection (ECCV 2022) · better on 4 of 4 shared results
- MonoDGP — MonoDGP: Monocular 3D Object Detection with Decoupled-Query and Geometry-Error Priors (CVPR 2025) · better on 2 of 2 shared results
- GUPNet — GUPNet++: Geometry Uncertainty Propagation Network for Monocular 3D Object Detection (TPAMI 2024) · better on 2 of 2 shared results
- MonoDETR — MonoDETR: Depth-guided Transformer for Monocular 3D Object Detection (ICCV 2023) · better on 2 of 2 shared results
- PETR — PETR: Position Embedding Transformation for Multi-View 3D Object Detection (ECCV 2022) · better on 2 of 2 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
- Diversity Matters: Fully Exploiting Depth Clues for Reliable Monocular 3D Object Detection (CVPR 2022 · similarity 0.90)
- Geometry-Guided Domain Generalization for Monocular 3D Object Detection (AAAI 2024 · similarity 0.88)
- MonoDiff: Monocular 3D Object Detection and Pose Estimation with Diffusion Models (CVPR 2024 · similarity 0.88)
- ImOV3D: Learning Open Vocabulary Point Clouds 3D Object Detection from Only 2D Images (NeurIPS 2024 · similarity 0.87)
- MonoMAE: Enhancing Monocular 3D Detection through Depth-Aware Masked Autoencoders (NeurIPS 2024 · similarity 0.86)
- MonoPlace3D: Learning 3D-Aware Object Placement for 3D Monocular Detection (CVPR 2025 · similarity 0.86)
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.
