HyperAIHyperAI

Optical Flow Estimation On Kitti 2015

Metrics

Average End-Point Error

Results

Performance results of various models on this benchmark

Model Name
Average End-Point Error
Paper TitleRepository
Perceiver IO4.98Perceiver IO: A General Architecture for Structured Inputs & Outputs-
CroCo-Flow-CroCo v2: Improved Cross-view Completion Pre-training for Stereo Matching and Optical Flow-
LiteFlowNet2-ft-A Lightweight Optical Flow CNN - Revisiting Data Fidelity and Regularization-
RPKNet-Recurrent Partial Kernel Network for Efficient Optical Flow Estimation
MaskFlownet-S-MaskFlownet: Asymmetric Feature Matching with Learnable Occlusion Mask-
DPFlow-DPFlow: Adaptive Optical Flow Estimation with a Dual-Pyramid Framework-
UnrolledCost-Cost Function Unrolling in Unsupervised Optical Flow-
LiteFlowNet-ft-LiteFlowNet: A Lightweight Convolutional Neural Network for Optical Flow Estimation-
MaskFlownet-MaskFlownet: Asymmetric Feature Matching with Learnable Occlusion Mask-
LiteFlowNet3-LiteFlowNet3: Resolving Correspondence Ambiguity for More Accurate Optical Flow Estimation-
GMFlowNet-Global Matching with Overlapping Attention for Optical Flow Estimation-
SelFlow-SelFlow: Self-Supervised Learning of Optical Flow-
CamLiRAFT-Learning Optical Flow and Scene Flow with Bidirectional Camera-LiDAR Fusion-
RAPIDFlow-RAPIDFlow: Recurrent Adaptable Pyramids with Iterative Decoding for Efficient Optical Flow Estimation
FastFlowNet-ft-FastFlowNet: A Lightweight Network for Fast Optical Flow Estimation-
IRR-PWC-Iterative Residual Refinement for Joint Optical Flow and Occlusion Estimation-
LiteFlowNet3-S-LiteFlowNet3: Resolving Correspondence Ambiguity for More Accurate Optical Flow Estimation-
0 of 17 row(s) selected.
Optical Flow Estimation On Kitti 2015 | SOTA | HyperAI