Research map / 3D vision / Face and shape
BAAM: Monocular 3D Pose and Shape Reconstruction With Bi-Contextual Attention Module and Attention-Guided Modeling
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 attention-guided modeling (AGM) for mesh shape estimation (ablation) | BAAM baseline · ApolloCar3D | Mesh IOU: 84.71 -> 85.55 | Helped |
| Add attention-guided modeling (AGM) for mesh shape estimation (ablation) | BAAM baseline · ApolloCar3D | A3DP-Abs mean: 21.08 -> 22.80 | Helped |
| Use AGM instead of direct regression, PCA-basis, or divide-and-conquer for shape estimation (ablation) | ApolloCar3D mesh reconstruction · ApolloCar3D | Mesh error: 8.58; 7.25; 7.71; 6.82 | Helped |
| Use AGM instead of direct regression, PCA-basis, or divide-and-conquer for shape estimation (ablation) | ApolloCar3D mesh reconstruction · ApolloCar3D | Mesh IOU: 82.61; 85.08; 84.60; 85.41 | Helped |
| Add bi-contextual attention (BCA) to integrate object relations and scene context (ablation) | BAAM with AGM · ApolloCar3D | A3DP-Abs mean: 22.80 -> 24.74 | Helped |
| Add relation-aware and scene-aware attention together (ablation) | BAAM translation estimation · ApolloCar3D | A3DP-Abs mean: 23.95; 23.66; 25.19 | Helped |
| Remove scene-aware attention from BCA (ablation) | BAAM translation estimation · ApolloCar3D | A3DP-Abs mean: 25.19 -> 23.95 | Hurt |
| Remove relation-aware attention from BCA (ablation) | BAAM translation estimation · ApolloCar3D | A3DP-Abs mean: 25.19 -> 23.66 | Hurt |
| Add 3D non-maximum suppression using Bird's-eye-view distance (ablation) | BAAM with AGM and BCA · ApolloCar3D | A3DP-Abs mean: 24.74 -> 25.19 | Helped |
| Add BCA | GUPNet · KITTI validation, moderate | 3D AP at IoU 0.7: 16.24 -> 16.48 | Helped |
| Add BCA and 3D NMS | GUPNet · KITTI validation, moderate | BEV AP at IoU 0.7: 22.42 -> 22.66 | Helped |
| Add BCA | DID-M3D · KITTI validation, moderate | 3D AP at IoU 0.7: 17.07 -> 17.66 | Helped |
Closest papers by meaning
- Monocular Vehicle Pose and Shape Reconstruction via Dynamic Context Adaptation and Progressive Geometry Refinement (AAAI 2026 · similarity 0.90)
- Mono3D++: Monocular 3D Vehicle Detection with Two-Scale 3D Hypotheses and Task Priors (AAAI 2019 · similarity 0.87)
- Monocular 3D Object Detection: An Extrinsic Parameter Free Approach (CVPR 2021 · similarity 0.85)
- ApolloCar3D: A Large 3D Car Instance Understanding Benchmark for Autonomous Driving (CVPR 2019 · similarity 0.85)
- Rethinking Lanes and Points in Complex Scenarios for Monocular 3D Lane Detection (CVPR 2025 · similarity 0.83)
- MUSt3R: Multi-view Network for Stereo 3D Reconstruction (CVPR 2025 · similarity 0.83)
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.