Research map / Detection and segmentation / 3D detection and driving
MoCA3D: Monocular 3D Bounding Box Prediction in the Image Plane
Changwoo Jeon, Rishi Upadhyay, Achuta Kadambi
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 |
|---|---|---|---|
| replace dense heatmap and depth heads with RoI direct regression head (ablation) | MoCA3D · Objectron | PAG_uv: 16.05 -> 17.38 | Hurt |
| replace dense heatmap and depth heads with RoI direct regression head (ablation) | MoCA3D · Objectron | PAG_d: 10.83 -> 14.89 | Hurt |
| replace dense heatmap and depth heads with RoI direct regression head (ablation) | MoCA3D · Objectron | IoU_3D: 0.3768 -> 0.3064 | Hurt |
| add box prior map conditioning (ablation) | MoCA3D · Objectron | PAG_uv: 16.35 -> 16.05 | Improved |
| add box prior map conditioning (ablation) | MoCA3D · Objectron | IoU_3D: 0.3736 -> 0.3768 | Improved |
| add box prior map conditioning (ablation) | MoCA3D · Objectron | PAG_d: 10.88 -> 10.83 | Improved |
| add Depth Anything v3 depth features (ablation) | MoCA3D · Objectron | PAG_uv: 16.05 -> 16.14 | No clear effect |
| add Depth Anything v3 depth features (ablation) | MoCA3D · Objectron | IoU_3D: 0.3768 -> 0.3682 | No clear effect |
| add Depth Anything v3 depth features (ablation) | MoCA3D · Objectron | Params (M): 19.0 -> 19.8 | Hurt |
| use MoCA3D instead of DetAny3D | DetAny3D · Omni3D KITTI | PAG_uv: 4.90 -> 3.12 | Improved |
| use MoCA3D instead of DetAny3D | DetAny3D · Omni3D Objectron | PAG_d: 12.55 -> 14.59 | Hurt |
| use MoCA3D instead of DetAny3D | DetAny3D · Omni3D Hypersim | IoU_3D: 0.1079 -> 0.0713 | Hurt |
Closest papers by meaning
- LabelAny3D: Label Any Object 3D in the Wild (NeurIPS 2025 · similarity 0.88)
- MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision (CVPR 2025 · similarity 0.87)
- MonoPlace3D: Learning 3D-Aware Object Placement for 3D Monocular Detection (CVPR 2025 · similarity 0.87)
- MonoDGP: Monocular 3D Object Detection with Decoupled-Query and Geometry-Error Priors (CVPR 2025 · similarity 0.86)
- RefineAny3D: Depth Refinement as Semantic Alignment for Monocular 3D Detection (NeurIPS 2026 · similarity 0.86)
- ImageNet3D: Towards General-Purpose Object-Level 3D Understanding (NeurIPS 2024 · 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.
