Research map / Detection and segmentation / 3D detection and driving
MonoATT: Online Monocular 3D Object Detection With Adaptive Token Transformer
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 |
|---|---|---|---|
| Use MonoATT instead of MonoDETR | KITTI test car detection · KITTI test, car | AP3D Hard: +2.01 | Helped |
| Add a 3-stage DETR with regular tokens (ablation) | GUPNet · KITTI val, car | AP3D Hard: 13.72 -> 13.95 | Helped |
| Replace regular tokens with adaptive clustering by feature distance, random centers, and mean merging (ablation) | GUPNet + 3-stage DETR · KITTI val, car | AP3D Hard: 13.95 -> 16.23 | Helped |
| Add the image-distance constraint to feature-distance grouping (ablation) | ATT with feature-distance grouping · KITTI val, car | AP3D Hard: 16.23 -> 16.57 | Helped |
| Add attention-weighted token feature merging (ablation) | Outline-preferred grouping · KITTI val, car | AP3D Hard: 16.57 -> 17.76 | Helped |
| Add depth-based cluster-center scoring (ablation) | Attention-based merging · KITTI val, car | AP3D Hard: 17.76 -> 18.15 | Helped |
| Add semantic scoring to depth-based cluster-center scoring (ablation) | Depth-scored cluster centers · KITTI val, car | AP3D Hard: 18.15 -> 18.87 | Helped |
| Add multi-stage feature reconstruction (ablation) | Depth-and-semantic cluster centers · KITTI val, car | AP3D Hard: 18.87 -> 19.60 | Helped |
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 0.89)
- MonoTAKD: Teaching Assistant Knowledge Distillation for Monocular 3D Object Detection (CVPR 2025 · similarity 0.89)
- MonoDiff: Monocular 3D Object Detection and Pose Estimation with Diffusion Models (CVPR 2024 · similarity 0.88)
- MonoCD: Monocular 3D Object Detection with Complementary Depths (CVPR 2024 · similarity 0.88)
- UniMODE: Unified Monocular 3D Object Detection (CVPR 2024 · similarity 0.87)
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.