Research map / 3D vision / Human pose estimation
Deep MANTA: A Coarse-To-Fine Many-Task Network for Joint 2D and 3D Vehicle Analysis From Monocular Image
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 |
|---|---|---|---|
| Pool regions on conv1 instead of conv5 without refinement (ablation) | Deep MANTA · KITTI val2 | AP, Moderate: 62.45 -> 86.85 | Helped |
| Add iterative refinement while pooling on conv1 (ablation) | Deep MANTA · KITTI val2 | AP, Moderate: 86.85 -> 90.89 | Helped |
| Add visibility prediction to detection, parts, and template tasks (ablation) | Deep MANTA · KITTI validation, averaged over splits and difficulty | AP: 89.73 -> 90.54 | No clear effect |
| Set λparts to 3 rather than 1 (ablation) | Deep MANTA with all tasks · KITTI validation, averaged over splits and difficulty | ALP at 1 meter: 51.47 -> 57.44 | Helped |
Closest papers by meaning
- Mono3D++: Monocular 3D Vehicle Detection with Two-Scale 3D Hypotheses and Task Priors (AAAI 2019 · similarity 0.86)
- Exploring intermediate representation for monocular vehicle pose estimation (CVPR 2021 · similarity 0.83)
- CarFusion: Combining Point Tracking and Part Detection for Dynamic 3D Reconstruction of Vehicles (CVPR 2018 · similarity 0.83)
- 3D-MAN: 3D Multi-Frame Attention Network for Object Detection (CVPR 2021 · similarity 0.83)
- Deep Multi-Task Learning for Joint Localization, Perception, and Prediction (CVPR 2021 · similarity 0.83)
- DALDet: Depth-Aware Learning Based Object Detection for Autonomous Driving (AAAI 2024 · similarity 0.82)
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.