Research map / Detection and segmentation / 3D detection and driving
MonoUNI: A Unified Vehicle and Infrastructure-side Monocular 3D Object Detection Network with Sufficient Depth Clues
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 |
|---|---|---|---|
| add focal-length normalization of depth (ablation) | MonoUNI baseline · Rope3D val Car | AP3D: 79.37 -> 83.42 | Helped |
| add pitch-angle normalization of depth (ablation) | MonoUNI baseline · Rope3D val Car | AP3D: 79.37 -> 81.55 | Helped |
| combine focal and pitch normalization (ablation) | MonoUNI baseline · Rope3D val Car | AP3D: 79.37 -> 86.69 | Helped |
| add 3D normalized cube depth (ablation) | MonoUNI baseline · Rope3D val Car | AP3D: 79.37 -> 87.07 | Helped |
| add cube depth on top of normalized depth (ablation) | MonoUNI · Rope3D val Car | AP3D: 86.69 -> 92.45 | Helped |
| add normalized depth (focal and pitch) (ablation) | MonoUNI baseline · KITTI val Car Moderate | AP3D: 14.93 -> 14.94 | No clear effect |
| add 3D normalized cube depth (ablation) | MonoUNI baseline · KITTI val Car Moderate | AP3D: 14.93 -> 17.07 | Helped |
| mixed focal-length training (train_all) with GUPNet (ablation) | GUPNet · Rope3D val_2700 | AP3D@0.5: 21.65 -> 5.85 | Hurt |
| train MonoUNI on all focal lengths (ablation) | MonoUNI · Rope3D val_2700 | AP3D@0.5: 23.42 -> 38.10 | Helped |
Closest papers by meaning
- MonoCD: Monocular 3D Object Detection with Complementary Depths (CVPR 2024 · similarity 0.91)
- MonoDTR: Monocular 3D Object Detection With Depth-Aware Transformer (CVPR 2022 · similarity 0.90)
- MonoDGP: Monocular 3D Object Detection with Decoupled-Query and Geometry-Error Priors (CVPR 2025 · similarity 0.89)
- UniMODE: Unified Monocular 3D Object Detection (CVPR 2024 · similarity 0.88)
- MonoMAE: Enhancing Monocular 3D Detection through Depth-Aware Masked Autoencoders (NeurIPS 2024 · similarity 0.88)
- Geometry-Guided Domain Generalization for Monocular 3D Object Detection (AAAI 2024 · similarity 0.88)
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.