HyperAI

Optical Flow Estimation On Sintel Clean

المقاييس

Average End-Point Error

النتائج

نتائج أداء النماذج المختلفة على هذا المعيار القياسي

اسم النموذج
Average End-Point Error
Paper TitleRepository
FDFlowNet-ft3.71FDFlowNet: Fast Optical Flow Estimation using a Deep Lightweight Network-
RAPIDFlow2.03RAPIDFlow: Recurrent Adaptable Pyramids with Iterative Decoding for Efficient Optical Flow Estimation
ScopeFlow3.592ScopeFlow: Dynamic Scene Scoping for Optical Flow
LiteFlowNet2-ft3.48A Lightweight Optical Flow CNN -- Revisiting Data Fidelity and Regularization
MaskFlownet2.52MaskFlownet: Asymmetric Feature Matching with Learnable Occlusion Mask
DEQ-Flow-H1.519Deep Equilibrium Optical Flow Estimation
GMFlow1.03Unifying Flow, Stereo and Depth Estimation
RPKNet1.315Recurrent Partial Kernel Network for Efficient Optical Flow Estimation
RAFT (warm-start)1.609RAFT: Recurrent All-Pairs Field Transforms for Optical Flow
IRR-PWC3.84Iterative Residual Refinement for Joint Optical Flow and Occlusion Estimation
SelFlow3.74SelFlow: Self-Supervised Learning of Optical Flow
GMA1.388Learning to Estimate Hidden Motions with Global Motion Aggregation
LiteFlowNet3-S3.03LiteFlowNet3: Resolving Correspondence Ambiguity for More Accurate Optical Flow Estimation
Ef-RAFT1.27Rethinking RAFT for Efficient Optical Flow
ProFlow+ft 2.82ProFlow: Learning to Predict Optical Flow-
UnrolledCost4.69Cost Function Unrolling in Unsupervised Optical Flow
FlowNet23.96FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks
Perceiver IO1.81Perceiver IO: A General Architecture for Structured Inputs & Outputs
FlowFormer1.16FlowFormer: A Transformer Architecture for Optical Flow
FastFlowNet-ft4.89FastFlowNet: A Lightweight Network for Fast Optical Flow Estimation
0 of 28 row(s) selected.