CHARM3R: Towards Unseen Camera Height Robust Monocular 3D Detector
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912539141472256 |
|---|---|
| author | Kumar, Abhinav Guo, Yuliang Zhang, Zhihao Huang, Xinyu Ren, Liu Liu, Xiaoming |
| author_facet | Kumar, Abhinav Guo, Yuliang Zhang, Zhihao Huang, Xinyu Ren, Liu Liu, Xiaoming |
| contents | Monocular 3D object detectors, while effective on data from one ego camera height, struggle with unseen or out-of-distribution camera heights. Existing methods often rely on Plucker embeddings, image transformations or data augmentation. This paper takes a step towards this understudied problem by first investigating the impact of camera height variations on state-of-the-art (SoTA) Mono3D models. With a systematic analysis on the extended CARLA dataset with multiple camera heights, we observe that depth estimation is a primary factor influencing performance under height variations. We mathematically prove and also empirically observe consistent negative and positive trends in mean depth error of regressed and ground-based depth models, respectively, under camera height changes. To mitigate this, we propose Camera Height Robust Monocular 3D Detector (CHARM3R), which averages both depth estimates within the model. CHARM3R improves generalization to unseen camera heights by more than $45\%$, achieving SoTA performance on the CARLA dataset. Codes and Models at https://github.com/abhi1kumar/CHARM3R |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_11185 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | CHARM3R: Towards Unseen Camera Height Robust Monocular 3D Detector Kumar, Abhinav Guo, Yuliang Zhang, Zhihao Huang, Xinyu Ren, Liu Liu, Xiaoming Computer Vision and Pattern Recognition Machine Learning Monocular 3D object detectors, while effective on data from one ego camera height, struggle with unseen or out-of-distribution camera heights. Existing methods often rely on Plucker embeddings, image transformations or data augmentation. This paper takes a step towards this understudied problem by first investigating the impact of camera height variations on state-of-the-art (SoTA) Mono3D models. With a systematic analysis on the extended CARLA dataset with multiple camera heights, we observe that depth estimation is a primary factor influencing performance under height variations. We mathematically prove and also empirically observe consistent negative and positive trends in mean depth error of regressed and ground-based depth models, respectively, under camera height changes. To mitigate this, we propose Camera Height Robust Monocular 3D Detector (CHARM3R), which averages both depth estimates within the model. CHARM3R improves generalization to unseen camera heights by more than $45\%$, achieving SoTA performance on the CARLA dataset. Codes and Models at https://github.com/abhi1kumar/CHARM3R |
| title | CHARM3R: Towards Unseen Camera Height Robust Monocular 3D Detector |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2508.11185 |