Optical Flow Estimation On Kitti 2012

Metrics

Average End-Point Error

Results

Performance results of various models on this benchmark

		Paper Title
FastFlowNet-ft	1.8	FastFlowNet: A Lightweight Network for Fast Optical Flow Estimation
IRR-PWC	1.6	Iterative Residual Refinement for Joint Optical Flow and Occlusion Estimation
LiteFlowNet-ft	1.6	LiteFlowNet: A Lightweight Convolutional Neural Network for Optical Flow Estimation
PWC-Net + ft - axXiv	1.5	Models Matter, So Does Training: An Empirical Study of CNNs for Optical Flow Estimation
FDFlowNet-ft	1.5	FDFlowNet: Fast Optical Flow Estimation using a Deep Lightweight Network
SelFlow	1.5	SelFlow: Self-Supervised Learning of Optical Flow
LiteFlowNet2-ft	1.4	A Lightweight Optical Flow CNN - Revisiting Data Fidelity and Regularization
LiteFlowNet3-S	1.3	LiteFlowNet3: Resolving Correspondence Ambiguity for More Accurate Optical Flow Estimation
LiteFlowNet3	1.3	LiteFlowNet3: Resolving Correspondence Ambiguity for More Accurate Optical Flow Estimation
MaskFlownet	1.1	MaskFlownet: Asymmetric Feature Matching with Learnable Occlusion Mask
MaskFlownet-S	1.1	MaskFlownet: Asymmetric Feature Matching with Learnable Occlusion Mask
CroCo-Flow	0.8	CroCo v2: Improved Cross-view Completion Pre-training for Stereo Matching and Optical Flow

0 of 12 row(s) selected.