Scene Flow Estimation: A Survey

Abstract

This paper is the first to review the scene flow estimation field, which analyzes and compares methods, technical challenges, evaluation methodologies and performance of scene flow estimation. Existing algorithms are categorized in terms of scene representation, data source, and calculation scheme, and the pros and cons in each category are compared briefly. The datasets and evaluation protocols are enumerated, and the performance of the most representative methods is presented. A future vision is illustrated with few questions arisen for discussion. This survey presents a general introduction and analysis of scene flow estimation.

51 pages, 12 figures, 10 tables, 108 references

References in corpus (2)

• Computing the Stereo Matching Cost with a Convolutional Neural Network
• Dense Wide-Baseline Scene Flow From Two Handheld Video Cameras

Cited by in corpus (7)

• Driving Datasets Literature Review
• HPLFlowNet: Hierarchical Permutohedral Lattice FlowNet for Scene Flow Estimation on Large-scale Point Clouds
• Shape2Motion: Joint Analysis of Motion Parts and Attributes from 3D Shapes
• SceneEDNet: A Deep Learning Approach for Scene Flow Estimation
• Unsupervised Pose-Aware Part Decomposition for 3D Articulated Objects
• Self-Supervised Learning of Part Mobility from Point Cloud Sequence
• Extracting Contact and Motion from Manipulation Videos