Research map / 3D vision / Depth and stereo
MonoGround: Detecting Monocular 3D Objects From the Ground
Check 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 |
|---|---|---|---|
| introduce the ground-plane prior, dense grounded-depth supervision, depth alignment, and two-stage inference | MonoFlex-based monocular detector · KITTI test car | AP3D|R40 moderate: 13.89 -> 14.36 | Helped |
| introduce the ground-plane prior, dense grounded-depth supervision, depth alignment, and two-stage inference | MonoFlex-based monocular detector · KITTI test car | BEV moderate: 19.75 -> 20.47 | Helped |
| add grounded-depth branch with sparse supervision (ablation) | Baseline detector · KITTI val car, IoU=0.7 | AP3D|R40 easy: 22.18 -> 19.23 | Hurt |
| add grounded-depth branch with sparse supervision (ablation) | Baseline detector · KITTI val car, IoU=0.7 | AP3D|R40 moderate: 16.37 -> 14.14 | Hurt |
| add grounded-depth branch with dense supervision instead of sparse supervision (ablation) | Baseline detector · KITTI val car, IoU=0.7 | AP3D|R40 moderate: 14.14 -> 15.54 | Helped |
| add coord convolution to dense grounded-depth branch (ablation) | Baseline+de. · KITTI val car, IoU=0.7 | AP3D|R40 moderate: 15.54 -> 16.23 | Helped |
| add dilated convolution to dense grounded-depth branch (ablation) | Baseline+de. · KITTI val car, IoU=0.7 | AP3D|R40 moderate: 15.54 -> 16.67 | Helped |
| add both coord and dilated convolutions to dense grounded-depth branch (ablation) | Baseline+de. · KITTI val car, IoU=0.7 | AP3D|R40 moderate: 15.54 -> 17.37 | Helped |
| use grounded depth rather than geometry depth (ablation) | MonoGround depth estimation · KITTI validation depth evaluation | MPE | Helped |
| use dense bottom-surface ground sampling for the depth prior | MonoGround pedestrian detection · KITTI test pedestrian | AP3D|R40: MonoGround: 12.37, 7.89, 7.13 | Mixed |
Closest papers by meaning
- MonoDGP: Monocular 3D Object Detection with Decoupled-Query and Geometry-Error Priors (CVPR 2025 · similarity 0.91)
- MonoCD: Monocular 3D Object Detection with Complementary Depths (CVPR 2024 · similarity 0.90)
- MonoDiff: Monocular 3D Object Detection and Pose Estimation with Diffusion Models (CVPR 2024 · similarity 0.88)
- FD3D: Exploiting Foreground Depth Map for Feature-Supervised Monocular 3D Object Detection (AAAI 2024 · similarity 0.88)
- MonoPlace3D: Learning 3D-Aware Object Placement for 3D Monocular Detection (CVPR 2025 · similarity 0.87)
- MonoTAKD: Teaching Assistant Knowledge Distillation for Monocular 3D Object Detection (CVPR 2025 · 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.