Research map / 3D vision / Human pose estimation
MonoRUn: Monocular 3D Object Detection by Reconstruction and Uncertainty Propagation
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 |
|---|---|---|---|
| add LiDAR supervision alongside self-supervised reprojection (ablation) | MonoRUn · KITTI Car validation | 3D detection mAP: 28.57 -> 31.21 | Helped |
| use self-supervised reprojection alongside LiDAR supervision (ablation) | MonoRUn · KITTI Car validation | 3D detection mAP: 18.84 -> 31.21 | Helped |
| replace SmoothL1 reprojection with Robust KL (ablation) | MonoRUn with LiDAR supervision · KITTI Car validation | 3D detection mAP: 26.35 -> 31.21 | Helped |
| replace LapKL with Robust KL, adding mixed-KL robustness and weight normalization (ablation) | MonoRUn with LiDAR supervision · KITTI Car validation | 3D detection mAP: 29.47 -> 31.21 | Helped |
| add end-to-end refinement to the LapKL-trained model (ablation) | MonoRUn · KITTI Car validation | 3D detection mAP: 29.47 -> 29.73 | Helped |
| add end-to-end refinement to the Robust-KL-trained model (ablation) | MonoRUn · KITTI Car validation | 3D detection mAP: 31.21 -> 31.09 | Hurt |
| estimate epistemic uncertainty for dimensions alone (ablation) | MonoRUn · KITTI Car validation | 3D detection mAP: 31.21 -> 31.47 | Helped |
| estimate epistemic uncertainty by sampling the full reconstruction network (ablation) | MonoRUn · KITTI Car validation | 3D detection mAP: 31.21 -> 31.16 | Hurt |
| add the global latent vector (ablation) | MonoRUn · KITTI Car validation | 3D detection mAP: 29.78 -> 31.21 | Helped |
| use the latent vector with Robust KL aleatoric uncertainty (ablation) | MonoRUn · KITTI Car validation | 3D detection mAP: 29.23 -> 31.21 | Helped |
| use MLP confidence scoring instead of 2D score only (ablation) | MonoRUn · KITTI Car validation | 3D detection mAP: 25.40 -> 31.47 | Helped |
| use MLP confidence scoring instead of Monte Carlo scoring (ablation) | MonoRUn · KITTI Car validation | 3D detection mAP: 28.19 -> 31.47 | Helped |
Closest papers by meaning
- MonoDGP: Monocular 3D Object Detection with Decoupled-Query and Geometry-Error Priors (CVPR 2025 · similarity 0.91)
- MonoDiff: Monocular 3D Object Detection and Pose Estimation with Diffusion Models (CVPR 2024 · similarity 0.91)
- MonoPlace3D: Learning 3D-Aware Object Placement for 3D Monocular Detection (CVPR 2025 · similarity 0.90)
- MonoMAE: Enhancing Monocular 3D Detection through Depth-Aware Masked Autoencoders (NeurIPS 2024 · similarity 0.88)
- Weakly Supervised Monocular 3D Detection with a Single-View Image (CVPR 2024 · similarity 0.88)
- MonoCD: Monocular 3D Object Detection with Complementary Depths (CVPR 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.