HyperAIHyperAI
الرئيسيةالأخبارالأوراق البحثيةالدروسمجموعات البياناتالموسوعةSOTAنماذج LLMلوحة الأداء GPUالفعاليات
البحث
حول
HyperAIHyperAI

Optical Flow Estimation On Kitti 2015 Train

المقاييس

EPE
F1-all

النتائج

نتائج أداء النماذج المختلفة على هذا المعيار القياسي

اسم النموذج
EPE
F1-all
Paper TitleRepository
VCN8.3625.1Volumetric Correspondence Networks for Optical Flow-
CRAFT4.8817.5CRAFT: Cross-Attentional Flow Transformer for Robust Optical Flow
RAFT5.0417.4RAFT: Recurrent All-Pairs Field Transforms for Optical Flow
PWC-Net10.3533.7PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume
FastFlowNet12.2433.1FastFlowNet: A Lightweight Network for Fast Optical Flow Estimation
GMA4.6917.1Learning to Estimate Hidden Motions with Global Motion Aggregation
FlowNet210.0830.0FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks
FlowFormer4.0914.7FlowFormer: A Transformer Architecture for Optical Flow
HD313.1724.0Hierarchical Discrete Distribution Decomposition for Match Density Estimation
Ef-RAFT4.8316.45Rethinking RAFT for Efficient Optical Flow
RPKNet3.7913.0Recurrent Partial Kernel Network for Efficient Optical Flow Estimation-
RAPIDFlow5.8717.7RAPIDFlow: Recurrent Adaptable Pyramids with Iterative Decoding for Efficient Optical Flow Estimation-
DEQ-Flow3.7613.0Deep Equilibrium Optical Flow Estimation
GMFlowNet4.2415.4Global Matching with Overlapping Attention for Optical Flow Estimation
MaskFlowNet-23.1MaskFlownet: Asymmetric Feature Matching with Learnable Occlusion Mask
SCV6.8019.3Learning Optical Flow from a Few Matches
SeparableFlow4.6015.9Separable Flow: Learning Motion Cost Volumes for Optical Flow Estimation-
DPFlow3.3711.1DPFlow: Adaptive Optical Flow Estimation with a Dual-Pyramid Framework
0 of 18 row(s) selected.