Research map / Detection and segmentation / 3D detection and driving
Learning Auxiliary Monocular Contexts Helps Monocular 3D Object Detection
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 auxiliary monocular context heads (ablation) | MonoCon · KITTI car validation | AP R40, moderate: 10.20 -> 19.01 | Helped |
| add projected keypoint heatmaps and quantization residual heads alongside the tested keypoint offset context (ablation) | MonoCon · KITTI car validation | AP R40, moderate: 16.09 -> 19.01 | Helped |
| add the 2D box size context head (ablation) | MonoCon · KITTI car validation | AP R40, moderate: 16.68 -> 19.01 | Helped |
| add the keypoint quantization residual head (ablation) | MonoCon · KITTI car validation | AP R40, moderate: 17.76 -> 19.01 | Helped |
| add the 2D box-center quantization residual head (ablation) | MonoCon · KITTI car validation | AP R40, moderate: 18.28 -> 19.01 | Helped |
| add Attentive Normalization (ablation) | MonoCon · KITTI car validation | AP R40, moderate: 18.69 -> 19.01 | Helped |
| use class-agnostic instead of class-specific regression heads (ablation) | MonoCon · KITTI validation car, pedestrian, and cyclist | AP R40, moderate: 18.53 -> 19.01 (car); 6.85 -> 1.31 (pedestrian); 1.50 -> 4.35 (cyclist) | Mixed |
| train the categories jointly rather than train on car only (ablation) | MonoCon · KITTI car validation | AP R40, moderate: 18.15 -> 19.01 | Helped |
| learn projected 2D contexts as auxiliary training tasks without using them at inference | MonoCon · KITTI car test | AP3D R40, moderate: 15.02 -> 16.46 | Helped |
| use MonoCon rather than GUPNet | KITTI pedestrian test · KITTI pedestrian test, moderate | AP3D R40: 9.76 -> 8.41 | Hurt |
| use MonoCon rather than the strongest cyclist result in the table | KITTI cyclist test · KITTI cyclist test, moderate | AP3D R40: 3.41 -> 1.92 | Hurt |
Closest papers by meaning
- MonoDGP: Monocular 3D Object Detection with Decoupled-Query and Geometry-Error Priors (CVPR 2025 · similarity 0.90)
- MonoMAE: Enhancing Monocular 3D Detection through Depth-Aware Masked Autoencoders (NeurIPS 2024 · similarity 0.90)
- MonoCD: Monocular 3D Object Detection with Complementary Depths (CVPR 2024 · similarity 0.89)
- MonoDiff: Monocular 3D Object Detection and Pose Estimation with Diffusion Models (CVPR 2024 · similarity 0.89)
- MonoTAKD: Teaching Assistant Knowledge Distillation for Monocular 3D Object Detection (CVPR 2025 · similarity 0.88)
- MonoPlace3D: Learning 3D-Aware Object Placement for 3D Monocular Detection (CVPR 2025 · 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.