Research map / Detection and segmentation / 3D detection and driving
MonoNeRD: NeRF-like Representations for Monocular 3D Object Detection
Junkai Xu, Liang Peng, Haoran Cheng, Hao Li, Wei Qian, Ke Li, Wenxiao Wang, Deng Cai
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 LiDAR depth loss to the NeRF-like representation (ablation) | MonoNeRD · KITTI val Car (Moderate) | AP_3D: 13.65 -> 14.54 | Improved |
| add RGB loss only (no depth supervision) (ablation) | MonoNeRD · KITTI val Car (Moderate) | AP_3D: 13.65 -> 13.11 | Hurt |
| add RGB loss on top of depth loss (ablation) | MonoNeRD · KITTI val Car (Moderate) | AP_3D: 14.54 -> 15.03 | Improved |
| add SDF loss (ablation) | MonoNeRD · KITTI val Car (Moderate) | AP_BEV: 20.16 -> 22.03 | Improved |
| add extra 3D conv layers to baseline (ablation) | baseline frustum voxel features · KITTI val Car (Moderate) | AP_3D: 13.38 -> 13.65 | No clear effect |
| use QKV position-aware module instead of concatenation (ablation) | MonoNeRD · KITTI val Car (Moderate) | AP_3D: 15.16 -> 15.44 | Improved |
| use NeRF-like representation instead of depth-based representation | monocular 3D detection · Waymo val Level 1 (IoU 0.7, 50m-inf) | 3D mAP: 0.10 -> 0.72 | Improved |
Later papers that compared with this method
1 later accepted paper reports MonoNeRD as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- MonoMAE: Enhancing Monocular 3D Detection through Depth-Aware Masked Autoencoders (NeurIPS 2024 · better on 4 of 4 shared results)
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.
- DID-M3D — DID-M3D: Decoupling Instance Depth for Monocular 3D Object Detection (ECCV 2022) · better on 3 of 4 shared results
- DEVIANT — DEVIANT: Depth EquiVarIAnt NeTwork for Monocular 3D Object Detection (ECCV 2022) · 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
- MonoDGP: Monocular 3D Object Detection with Decoupled-Query and Geometry-Error Priors (CVPR 2025 · similarity 0.90)
- MonoDETR: Depth-guided Transformer for Monocular 3D Object Detection (ICCV 2023 · similarity 0.90)
- MonoMAE: Enhancing Monocular 3D Detection through Depth-Aware Masked Autoencoders (NeurIPS 2024 · similarity 0.90)
- 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 0.89)
- MonoCD: Monocular 3D Object Detection with Complementary Depths (CVPR 2024 · 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.
