Self-Supervised Bird's Eye View Motion Prediction with Cross-Modality Signals
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917572101799936 |
|---|---|
| author | Fang, Shaoheng Liu, Zuhong Wang, Mingyu Xu, Chenxin Zhong, Yiqi Chen, Siheng |
| author_facet | Fang, Shaoheng Liu, Zuhong Wang, Mingyu Xu, Chenxin Zhong, Yiqi Chen, Siheng |
| contents | Learning the dense bird's eye view (BEV) motion flow in a self-supervised manner is an emerging research for robotics and autonomous driving. Current self-supervised methods mainly rely on point correspondences between point clouds, which may introduce the problems of fake flow and inconsistency, hindering the model's ability to learn accurate and realistic motion. In this paper, we introduce a novel cross-modality self-supervised training framework that effectively addresses these issues by leveraging multi-modality data to obtain supervision signals. We design three innovative supervision signals to preserve the inherent properties of scene motion, including the masked Chamfer distance loss, the piecewise rigidity loss, and the temporal consistency loss. Through extensive experiments, we demonstrate that our proposed self-supervised framework outperforms all previous self-supervision methods for the motion prediction task. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_11499 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Self-Supervised Bird's Eye View Motion Prediction with Cross-Modality Signals Fang, Shaoheng Liu, Zuhong Wang, Mingyu Xu, Chenxin Zhong, Yiqi Chen, Siheng Computer Vision and Pattern Recognition Learning the dense bird's eye view (BEV) motion flow in a self-supervised manner is an emerging research for robotics and autonomous driving. Current self-supervised methods mainly rely on point correspondences between point clouds, which may introduce the problems of fake flow and inconsistency, hindering the model's ability to learn accurate and realistic motion. In this paper, we introduce a novel cross-modality self-supervised training framework that effectively addresses these issues by leveraging multi-modality data to obtain supervision signals. We design three innovative supervision signals to preserve the inherent properties of scene motion, including the masked Chamfer distance loss, the piecewise rigidity loss, and the temporal consistency loss. Through extensive experiments, we demonstrate that our proposed self-supervised framework outperforms all previous self-supervision methods for the motion prediction task. |
| title | Self-Supervised Bird's Eye View Motion Prediction with Cross-Modality Signals |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2401.11499 |