.png){kind=icon}
返回
RAFT-MSF: Self-Supervised Monocular Scene Flow Using Recurrent Optimizer
.png){kind=icon}
PRE
AI
DOI：10.1007/s11263-023-01828-4.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
A popular approach to estimate scene flow is to utilize point cloud data from various Lidar scans. However, there is little attention to learning 3D motion from camera images. Learning scene flow from a monocular camera remains a challenging task due to its ill-posedness as well as lack of annotated data. Self-supervised methods demonstrate learning scene flow estimation from unlabeled data, yet their accuracy lags behind (semi-)supervised methods. In this paper, we introduce a self-supervised monocular scene flow method that substantially improves the accuracy over the previous approaches. Based on RAFT, a state-of-the-art optical flow model, we design a new decoder to iteratively update 3D motion fields and disparity maps simultaneously. Furthermore, we propose an enhanced upsampling layer and a disparity initialization technique, which overall further improves accuracy up to 7.2%. Our method achieves state-of-the-art accuracy among all self-supervised monocular scene flow methods, improving accuracy by 34.2%. Our fine-tuned model outperforms the best previous semi-supervised method with 228 times faster runtime. Code will be publicly available to ensure reproducibility.
Keyword:
Scene flow
Disparity estimation
Self-supervised learning
Autonomous driving
期刊
IF:
9.3
论文数:
3.9K
被引数:
2.8W
机构
引用论文
分享收藏Wireless Underground Communications in Sewer and Stormwater Overflow Monitoring: Radio Waves through Soil and Asphalt Medium.png)
Information
OAAI
InformationIF0
OAAI分享收藏分享收藏Coupled Simulations of Indoor-Outdoor Flow Fields for Cross-Ventilation of a Building in a Simplified Urban ArrayAtmosphereOAAI
AtmosphereIF0
OAAI分享收藏
查看更多内容