Optical Flow Estimation On Sintel Clean

评估指标

Average End-Point Error

评测结果

各个模型在此基准测试上的表现结果

		Paper Title	Repository
Spynet	6.64	Optical Flow Estimation using a Spatial Pyramid Network
FastFlowNet-ft	4.89	FastFlowNet: A Lightweight Network for Fast Optical Flow Estimation
UnrolledCost	4.69	Cost Function Unrolling in Unsupervised Optical Flow
LiteFlowNet-ft	4.54	LiteFlowNet: A Lightweight Convolutional Neural Network for Optical Flow Estimation
FlowNet2	3.96	FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks
IRR-PWC	3.84	Iterative Residual Refinement for Joint Optical Flow and Occlusion Estimation
SelFlow	3.74	SelFlow: Self-Supervised Learning of Optical Flow
FDFlowNet-ft	3.71	FDFlowNet: Fast Optical Flow Estimation using a Deep Lightweight Network	-
ScopeFlow	3.592	ScopeFlow: Dynamic Scene Scoping for Optical Flow
LiteFlowNet2-ft	3.48	A Lightweight Optical Flow CNN - Revisiting Data Fidelity and Regularization
LiteFlowNet3-S	3.03	LiteFlowNet3: Resolving Correspondence Ambiguity for More Accurate Optical Flow Estimation
LiteFlowNet3	2.99	LiteFlowNet3: Resolving Correspondence Ambiguity for More Accurate Optical Flow Estimation
ProFlow+ft	2.82	ProFlow: Learning to Predict Optical Flow	-
MaskFlownet-S	2.77	MaskFlownet: Asymmetric Feature Matching with Learnable Occlusion Mask
MR-Flow	2.53	Optical Flow in Mostly Rigid Scenes	-
MaskFlownet	2.52	MaskFlownet: Asymmetric Feature Matching with Learnable Occlusion Mask
RAPIDFlow	2.03	RAPIDFlow: Recurrent Adaptable Pyramids with Iterative Decoding for Efficient Optical Flow Estimation	-
Perceiver IO	1.81	Perceiver IO: A General Architecture for Structured Inputs & Outputs
RAFT (warm-start)	1.609	RAFT: Recurrent All-Pairs Field Transforms for Optical Flow
DEQ-Flow-H	1.519	Deep Equilibrium Optical Flow Estimation

0 of 28 row(s) selected.