SceneFlowFields++: Multi-frame Matching, Visibility Prediction, and Robust Interpolation for Scene Flow Estimation
arXiv:1902.10099 · doi:10.1007/s11263-019-01258-1
Abstract
State-of-the-art scene flow algorithms pursue the conflicting targets of accuracy, run time, and robustness. With the successful concept of pixel-wise matching and sparse-to-dense interpolation, we push the limits of scene flow estimation. Avoiding strong assumptions on the domain or the problem yields a more robust algorithm. This algorithm is fast because we avoid explicit regularization during matching, which allows an efficient computation. Using image information from multiple time steps and explicit visibility prediction based on previous results, we achieve competitive performances on different data sets. Our contributions and results are evaluated in comparative experiments. Overall, we present an accurate scene flow algorithm that is faster and more generic than any individual benchmark leader.
arXiv commentarXiv admin note: text overlap with arXiv:1710.10096
References in corpus (6)
- A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation
- Deep Visual Domain Adaptation: A Survey
- Virtual Worlds as Proxy for Multi-Object Tracking Analysis
- Fast Multi-frame Stereo Scene Flow with Motion Segmentation
- Combining Stereo Disparity and Optical Flow for Basic Scene Flow
- Cascaded Scene Flow Prediction using Semantic Segmentation