Research map / Detection and segmentation / 3D detection and driving
Towards Intrinsic-Aware Monocular 3D Object Detection
Zhihao Zhang, Abhinav Kumar, Xiaoming Liu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 intrinsic-aware modeling (MonoIA) instead of MonoCoP at unseen focal 1400 px | MonoCoP · KITTI Val, unseen focals | AP3D: 11.11 -> 16.99 | Improved |
| add intrinsic-aware modeling at perturbed focal +-15 px | MonoCoP · KITTI Val intrinsic mismatch | AP3D: 15.42 -> 18.98 | Improved |
| add MonoIA to MonoCoP on KITTI test | MonoCoP · KITTI Test Car IoU 0.7 | AP3D Moderate: 19.11 -> 20.29 | Improved |
| add MonoIA to MonoCoP on nuScenes | MonoCoP · nuScenes Val | AP3D Easy: 10.85 -> 12.33 | Improved |
| add intrinsic awareness for joint KITTI+nuScenes training | MonoCoP · Multi-dataset, KITTI | AP3D: 17.26 -> 26.54 | Improved |
| add Waymo to multi-dataset training | MonoIA · Multi-dataset, KITTI | AP3D: 26.54 -> 28.91 | Improved |
| add virtual-depth normalization to multi-dataset MonoCoP | MonoCoP · Multi-dataset, KITTI | AP3D: 17.26 -> 23.15 | Mixed |
| train baseline on synthetic multi-focal images without intrinsic modeling (ablation) | MonoCoP · KITTI Val ablation, IoU 0.7 Moderate | AP3D: 23.64 -> 21.71 | Hurt |
| add semantic Intrinsic Encoder instead of linear layer on raw intrinsics (ablation) | MonoIA · KITTI Val ablation, IoU 0.7 Moderate | AP3D: 22.16 -> 24.40 | Improved |
| freeze intrinsic embeddings (ablation) | MonoIA · KITTI Val ablation, IoU 0.7 Moderate | AP3D: 21.85 -> 24.40 | Improved |
| add Connector (ablation) | MonoIA · KITTI Val ablation, IoU 0.7 Moderate | AP3D: 22.85 -> 24.40 | Improved |
| add Feature-Level Adaptation (ablation) | MonoIA · KITTI Val ablation, IoU 0.7 Moderate | AP3D: 23.43 -> 24.40 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- MonoDGP — MonoDGP: Monocular 3D Object Detection with Decoupled-Query and Geometry-Error Priors (CVPR 2025) · better on 2 of 2 shared results
- MonoDETR — MonoDETR: Depth-guided Transformer for Monocular 3D Object Detection (ICCV 2023) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- MonoMAE: Enhancing Monocular 3D Detection through Depth-Aware Masked Autoencoders (NeurIPS 2024 · similarity 0.91)
- MonoPlace3D: Learning 3D-Aware Object Placement for 3D Monocular Detection (CVPR 2025 · similarity 0.90)
- MonoDGP: Monocular 3D Object Detection with Decoupled-Query and Geometry-Error Priors (CVPR 2025 · similarity 0.90)
- RefineAny3D: Depth Refinement as Semantic Alignment for Monocular 3D Detection (NeurIPS 2026 · similarity 0.89)
- MonoDiff: Monocular 3D Object Detection and Pose Estimation with Diffusion Models (CVPR 2024 · similarity 0.89)
- LabelAny3D: Label Any Object 3D in the Wild (NeurIPS 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.
