Research map / 3D vision / Human pose estimation
MonoLoco: Monocular 3D Pedestrian Localization and Uncertainty Estimation
Lorenzo Bertoni, Sven Kreiss, Alexandre Alahi
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 |
|---|---|---|---|
| use Laplace loss instead of Gaussian loss (ablation) | MonoLoco (PifPaf) · nuScenes teaser val | ALE (m): 1.97 -> 1.90 | Improved |
| use Laplace loss instead of L1 loss (ablation) | MonoLoco (PifPaf) · nuScenes teaser val | ALE (m): 1.92 -> 1.90 | Improved |
| use Laplace loss instead of Gaussian loss (ablation) | MonoLoco (Mask R-CNN) · nuScenes teaser val | ALE (m): 2.26 -> 2.12 | Improved |
| use Laplace loss instead of L1 loss (ablation) | MonoLoco (Mask R-CNN) · nuScenes teaser val | ALE (m): 2.14 -> 2.12 | No clear effect |
| replace Mask R-CNN with PifPaf pose detector (ablation) | MonoLoco (Laplace) · nuScenes teaser val | ALE (m): 2.12 -> 1.90 | Improved |
| replace geometric baseline with learned MonoLoco network | PifPaf poses · nuScenes teaser val | ALE (m): 2.05 -> 1.90 | Improved |
| replace geometric baseline with learned MonoLoco network | Mask R-CNN poses · nuScenes teaser val | ALE (m): 3.73 -> 2.12 | Improved |
| train MonoLoco on nuScenes instead of KITTI (cross-dataset) | MonoLoco · KITTI pedestrians | ALP <1m (%): 49.6 -> 51.7 | Improved |
| increase MC dropout probability from 0.05 to 0.4 (ablation) | MonoLoco · KITTI val | recall (%): 82.8 -> 88.3 | Mixed |
| use MonoLoco instead of monocular MonoDepth + PifPaf | KITTI pedestrians · KITTI pedestrians | ALP <1m (%): 35.3 -> 51.7 | Improved |
| use monocular MonoLoco instead of stereo 3DOP | KITTI pedestrians · KITTI pedestrians (Hard) | ALE (m): 1.94 -> 1.17 | Improved |
| use monocular MonoLoco instead of stereo 3DOP | KITTI pedestrians · KITTI pedestrians | ALP <0.5m (%): 41.4 -> 30.8 | Hurt |
Closest papers by meaning
- MonoRUn: Monocular 3D Object Detection by Reconstruction and Uncertainty Propagation (CVPR 2021 · similarity 0.89)
- Probabilistic Monocular 3D Human Pose Estimation With Normalizing Flows (ICCV 2021 · similarity 0.88)
- Neural Localizer Fields for Continuous 3D Human Pose and Shape Estimation (NeurIPS 2024 · similarity 0.87)
- MonoDiff: Monocular 3D Object Detection and Pose Estimation with Diffusion Models (CVPR 2024 · similarity 0.86)
- MonoPlace3D: Learning 3D-Aware Object Placement for 3D Monocular Detection (CVPR 2025 · similarity 0.86)
- MonoDGP: Monocular 3D Object Detection with Decoupled-Query and Geometry-Error Priors (CVPR 2025 · similarity 0.85)
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.
