Research map / Detection and segmentation / 3D detection and driving
MonoDTR: Monocular 3D Object Detection With Depth-Aware Transformer
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 |
|---|---|---|---|
| Add MonoDTR's depth-aware feature and transformer modules (ablation) | Image-only monocular 3D detection with DLA-102 · KITTI validation, Car | 3D AP40@IoU=0.7, Moderate: 15.47 -> 18.57 | Helped |
| Use depth-aware features instead of object queries in the transformer decoder (ablation) | MonoDTR · KITTI validation, Car | 3D AP40@IoU=0.7, Moderate: 16.10 -> 18.57 | Helped |
| Learn depth-aware features with auxiliary depth supervision rather than use DORN depth-image features (ablation) | MonoDTR · KITTI validation, Car | 3D AP40@IoU=0.7, Moderate: 17.10 -> 18.57 | Helped |
| Integrate context- and depth-aware features with DTR instead of convolutional concatenation (ablation) | MonoDTR · KITTI validation, Car | 3D AP40@IoU=0.7, Moderate: 17.65 -> 18.57 | Helped |
| Add depth prototype enhancement (ablation) | MonoDTR · KITTI validation, Car | 3D AP40@IoU=0.7, Moderate: 18.22 -> 18.57 | Helped |
| Use depth positional encoding instead of no positional encoding (ablation) | MonoDTR · KITTI validation, Car | 3D AP40@IoU=0.7, Moderate: 17.76 -> 18.57 | Helped |
| Use depth positional encoding instead of sinusoidal positional encoding (ablation) | MonoDTR · KITTI validation, Car | 3D AP40@IoU=0.7, Moderate: 17.63 -> 18.57 | Helped |
| Use depth positional encoding instead of absolute positional encoding (ablation) | MonoDTR · KITTI validation, Car | 3D AP40@IoU=0.7, Moderate: 17.55 -> 18.57 | Helped |
| Use depth positional encoding instead of conditional positional encoding (ablation) | MonoDTR · KITTI validation, Car | 3D AP40@IoU=0.7, Moderate: 18.04 -> 18.57 | Helped |
| Use linear self-attention instead of vanilla self-attention (ablation) | MonoDTR · KITTI validation, Car | inference time: 136 ms -> 37 ms | Helped |
| Use linear self-attention instead of vanilla self-attention (ablation) | MonoDTR · KITTI validation, Car | 3D AP40@IoU=0.7, Moderate: 18.39 -> 18.57 | Helped |
| Use linear-increasing depth discretization rather than uniform discretization (ablation) | MonoDTR auxiliary depth supervision · KITTI validation, Car | 3D AP40@IoU=0.7, Moderate: 17.67 -> 18.57 | Helped |
Closest papers by meaning
- MonoDGP: Monocular 3D Object Detection with Decoupled-Query and Geometry-Error Priors (CVPR 2025 · similarity 0.90)
- MonoUNI: A Unified Vehicle and Infrastructure-side Monocular 3D Object Detection Network with Sufficient Depth Clues (NeurIPS 2023 · similarity 0.90)
- MonoMAE: Enhancing Monocular 3D Detection through Depth-Aware Masked Autoencoders (NeurIPS 2024 · similarity 0.89)
- MonoCD: Monocular 3D Object Detection with Complementary Depths (CVPR 2024 · similarity 0.89)
- MonoTAKD: Teaching Assistant Knowledge Distillation for Monocular 3D Object Detection (CVPR 2025 · similarity 0.87)
- MonoDiff: Monocular 3D Object Detection and Pose Estimation with Diffusion Models (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.