RAFT: Recurrent All-Pairs Field Transforms for Optical Flow

@article{Teed2020RAFTRA,
  title={RAFT: Recurrent All-Pairs Field Transforms for Optical Flow},
  author={Zachary Teed and Jun Deng},
  journal={ArXiv},
  year={2020},
  volume={abs/2003.12039}
}
We introduce Recurrent All-Pairs Field Transforms (RAFT), a new deep network architecture for optical flow. RAFT extracts per-pixel features, builds multi-scale 4D correlation volumes for all pairs of pixels, and iteratively updates a flow field through a recurrent unit that performs lookups on the correlation volumes. RAFT achieves state-of-the-art performance. On KITTI, RAFT achieves an F1-all error of 5.10%, a 16% error reduction from the best published result (6.10%). On Sintel (final pass… Expand
DRO: Deep Recurrent Optimizer for Structure-from-Motion
Optical Flow Estimation via Motion Feature Recovery
VideoClick: Video Object Segmentation with a Single Click
Comparing Correspondences: Video Prediction with Correspondence-wise Losses
GyroFlow: Gyroscope-Guided Unsupervised Optical Flow Learning
High-Resolution Optical Flow from 1D Attention and Correlation
HumanGPS: Geodesic PreServing Feature for Dense Human Correspondences
LIFE: Lighting Invariant Flow Estimation
Learning Optical Flow from a Few Matches
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 58 REFERENCES
MaskFlownet: Asymmetric Feature Matching With Learnable Occlusion Mask
Volumetric Correspondence Networks for Optical Flow
FlowNet: Learning Optical Flow with Convolutional Networks
Decoupled Weight Decay Regularization
Hierarchical Deep Stereo Matching on High-Resolution Images
Iterative Residual Refinement for Joint Optical Flow and Occlusion Estimation
  • Junhwa Hur, S. Roth
  • Computer Science
  • 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2019
SelFlow: Self-Supervised Learning of Optical Flow
LiteFlowNet: A Lightweight Convolutional Neural Network for Optical Flow Estimation
PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume
FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks
...
1
2
3
4
5
...