Research map / Detection and segmentation / 3D detection and driving
3D-MOOD: Lifting 2D to 3D for Monocular Open-Set Object Detection
Yung-Hsu Yang, Luigi Piccinelli, Mattia Segu, Siyuan Li, Rui Huang, Yuqian Fu, Marc Pollefeys, Hermann Blum, Zuria Bauer
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 canonical image space (ablation) | 3D-MOOD · Omni3D closed-set (AP omni) | AP3D: 24.1 -> 25.5 | Improved |
| add canonical image space (ablation) | 3D-MOOD · Open-set average (AV2, ScanNet) | ODS open: 23.6 -> 24.5 | Improved |
| add auxiliary metric depth head (ablation) | 3D-MOOD · Omni3D closed-set (AP omni) | AP3D: 25.5 -> 26.2 | Improved |
| add auxiliary metric depth head (ablation) | 3D-MOOD · Open-set average (AV2, ScanNet) | ODS open: 24.5 -> 24.7 | No clear effect |
| add geometry-aware 3D query generation (ablation) | 3D-MOOD · Open-set average (AV2, ScanNet) | ODS open: 24.7 -> 26.0 | Improved |
| add geometry-aware 3D query generation (ablation) | 3D-MOOD · Omni3D closed-set (AP omni) | AP3D: 26.2 -> 26.8 | Improved |
| end-to-end 2D-to-3D lifting instead of pseudo-GT pipeline (OVM3D-Det) | open-set 3D detection · ScanNet | ODS: 16.3 -> 31.5 | Improved |
| scale backbone from Swin-T to Swin-B | 3D-MOOD · Omni3D test | AP3D omni: 28.4 -> 30.0 | Improved |
| open-vocabulary 2D detector for novel class recognition vs closed-vocabulary Cube R-CNN | 3D-MOOD · Argoverse 2 novel classes | ODS (N): 0.0 -> 14.8 | Improved |
Later papers that compared with this method
1 later accepted paper reports 3D-MOOD as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- Map-Det3D: Metric Feed-Forward 3D Reconstruction Prior for Multi-view 3D Object Detection from Streaming Inputs (ECCV 2026 · better on 2 of 2 shared results)
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- Uni-MODE — UniMODE: Unified Monocular 3D Object Detection (CVPR 2024) · better on 1 of 1 shared result
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
- Training an Open-Vocabulary Monocular 3D Detection Model without 3D Data (NeurIPS 2024 · similarity 0.91)
- MonoPlace3D: Learning 3D-Aware Object Placement for 3D Monocular Detection (CVPR 2025 · similarity 0.90)
- MonoDGP: Monocular 3D Object Detection with Decoupled-Query and Geometry-Error Priors (CVPR 2025 · similarity 0.90)
- MonoMAE: Enhancing Monocular 3D Detection through Depth-Aware Masked Autoencoders (NeurIPS 2024 · similarity 0.89)
- MonoDiff: Monocular 3D Object Detection and Pose Estimation with Diffusion Models (CVPR 2024 · similarity 0.89)
- UniMODE: Unified Monocular 3D Object Detection (CVPR 2024 · similarity 0.89)
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.
