A survey on deep learning methods for scene flow estimation

作者：Liu, Jiajie; Li, Han; Wu, Ruihong; Zhao, Qingyun; Guo, Yiyou; Chen, Long

来源：Pattern Recognition, 2020, 106: 107378.

DOI：10.1016/j.patcog.2020.107378

• Scene flow
• Optical flow
• Depth estimation
• Deep learning

Recently, computer vision has achieved remarkable accomplishments in many domains under the thriving of deep learning. Scene flow estimation turns from the classical manual feature construction to the deep convolutional neural network (DCNN) approaches. In this paper, we review recent works about scene flow, mainly focusing on DCNN methods. We present some milestones of scene flow in recent years, and categorize these methods into supervised and unsupervised based methods. Meanwhile, we also review some multi-task methods related to scene flow. At last, we present a performance comparison among different methods.

• 单位
  上海交通大学; 中山大学