Model Zoo Statistics¶
Number of papers: 9
Number of checkpoints: 62 ckpts
FlowNet: Learning Optical Flow with Convolutional Networks (5 ckpts)
FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks (7 ckpts)
PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume (6 ckpts)
LiteFlowNet: A Lightweight Convolutional Neural Network for Optical Flow Estimation (9 ckpts)
A Lightweight Optical Flow CNN-Revisiting Data Fidelity and Regularization (8 ckpts)
Iterative Residual Refinement for Joint Optical Flow and Occlusion Estimation (5 ckpts)
MaskFlownet: Asymmetric Feature Matching with Learnable Occlusion Mask (4 ckpts)
RAFT: Recurrent All-Pairs Field Transforms for Optical Flow (5 ckpts)
GMA: Learning to Estimate Hidden Motions with Global Motion Aggregation (13 ckpts)