Research map / 3D vision / Human pose estimation
Mono3D++: Monocular 3D Vehicle Detection with Two-Scale 3D Hypotheses and Task Priors
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| jointly use coarse 3D box projection with fine-scale landmark projection and shape priors (ablation) | Mono3D++ · KITTI val1/val2, Easy/Moderate/Hard | ALP at 1 meter: 68.5 / 68.2 -> 76.1 / 73.2; 58.3 / 57.5 -> 64.5 / 60.2; 50.8 / 47.6 -> 53.6 / 50.0 | Helped |
| add unsupervised monocular depth (ablation) | Mono3D++ · KITTI val1/val2, Easy/Moderate/Hard | ALP at 1 meter: 76.1 / 73.2 -> 80.6 / 80.2; 64.5 / 60.2 -> 67.7 / 65.1; 53.6 / 50.0 -> 56.0 / 54.6 | Helped |
| add fine-scale landmark projection and vehicle shape priors (ablation) | Mono3D++ · KITTI val1/val2, Easy | AP3D at 3D IoU 0.25: 68.33 / 58.50 -> 71.39 / 66.59 | Helped |
| add unsupervised monocular depth (ablation) | Mono3D++ · KITTI val1/val2, Easy | AP3D at 3D IoU 0.25: 71.39 / 66.59 -> 79.45 / 71.86 | Helped |
| add fine-scale landmark projection and vehicle shape priors (ablation) | Mono3D++ · KITTI val1/val2, Easy | APloc at 2D IoU 0.5: 37.27 / 30.18 -> 42.68 / 37.25 | Helped |
| add unsupervised monocular depth (ablation) | Mono3D++ · KITTI val1/val2, Easy | APloc at 2D IoU 0.5: 42.68 / 37.25 -> 50.50 / 46.68 | Helped |
| use joint coarse and fine 3D hypotheses with task priors | Mono3D++ · KITTI val2, Moderate and Hard | ALP at 1 / 2 / 3 meters: 65.1 / 80.8 / 85.4; 54.6 / 70.5 / 75.9 vs 66.9 / 80.0 / 84.2; 59.4 / 71.9 / 76.0 | Mixed |
Closest papers by meaning
- MonoUNI: A Unified Vehicle and Infrastructure-side Monocular 3D Object Detection Network with Sufficient Depth Clues (NeurIPS 2023 · similarity 0.89)
- Rethinking Geometric Depth in Monocular 3D Object Detection: A Projection-Consistent Reformulation (NeurIPS 2026 · similarity 0.89)
- Monocular Vehicle Pose and Shape Reconstruction via Dynamic Context Adaptation and Progressive Geometry Refinement (AAAI 2026 · similarity 0.89)
- MonoDiff: Monocular 3D Object Detection and Pose Estimation with Diffusion Models (CVPR 2024 · similarity 0.87)
- MonoDGP: Monocular 3D Object Detection with Decoupled-Query and Geometry-Error Priors (CVPR 2025 · similarity 0.87)
- Geometry-Guided Domain Generalization for Monocular 3D Object Detection (AAAI 2024 · similarity 0.87)
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.