List your company
ResearchFormerly WizWand

Optical Flow on MVSEC 1.0 (indoor_flying2)

0.38EPEScaleEvent
0.15121.69563.244.7844Apr 17, 2019Jun 8, 2020Aug 1, 2021Sep 24, 2022Nov 17, 2023Jan 9, 2025Mar 4, 2026
Updated 8mo ago

Evaluation results

MethodLinks
ScaleEventBackbone=ViT-S/16, Protocol=Event Pretraining + Fully-Supervised2026.030.380.001
STPBackbone=Swin-T/7, Protocol=Event Pretraining + Fully-Supervised2026.030.410.001
ECDDPBackbone=Swin-T/7, Protocol=Event Pretraining + Fully-Supervised2026.030.450.002
EDCFlow (+in3)dt=1, Input=E, Learning paradigm=SL, training_inclusion=flying32025.060.540.34
MultiCM (Burgers')dt=1, Input=E, Learning paradigm=MB2025.060.60.59
EDCFlow (+in1)dt=1, Input=E, Learning paradigm=SL, training_inclusion=flying12025.060.651.85
ECDDPBackbone=ViT-S/16, Protocol=Event Pretraining + Fully-Supervised2026.030.690.29
EV-MGRFlowNetdt=1, Input=E, Learning paradigm=USL2025.060.72.35
STE-FlowNetdt=1, Input=E, Learning paradigm=SSL2025.060.791.6
DCEIFlowdt=1, Input=E+I1, Learning paradigm=SL2025.060.92.1
Brebion et al.dt=1, Input=E, Learning paradigm=MB2025.060.985.5
Zhu et al.dt=1, Input=E, Learning paradigm=USL2025.061.024
STPBackbone=ViT-S/16, Protocol=Event Pretraining + Fully-Supervised2026.031.226.34
ECDPBackbone=ViT-S/16, Protocol=Event Pretraining + Fully-Supervised2026.031.266.69
ECDPBackbone=ResNet-50, Protocol=Event Pretraining + Fully-Supervised2026.031.358.57
ESTMeasurement=time stamps, Kernel=learnt2019.041.388.2
DCEFlowProtocol=RGB initialization + Fully-Supervised2026.031.398.01
EDCFlowdt=1, Input=E, Learning paradigm=SL2025.061.4910.79
ESTMeasurement=time stamps, Kernel=alpha2019.041.5211.7
IDNet-4dt=1, Input=E, Learning paradigm=SL, re-implemented=true2025.061.5510.84
ESTMeasurement=time stamps, Kernel=exponential2019.041.5810.5
EDCFlow (+in3)dt=4, Input=E, Learning paradigm=SL, training_inclusion=flying32025.061.6111.19
Voxel GridMeasurement=polarity, Kernel=trilinear2019.041.6514.6
IDNet-8dt=1, Input=E, Learning paradigm=SL, re-implemented=true2025.061.6713.64
Voxel GridMeasurement=time stamps, Kernel=trilinear2019.041.714.3
ESTMeasurement=time stamps, Kernel=trilinear2019.041.7111.4
EV-FlowNetdt=1, Input=E, Learning paradigm=SSL2025.061.7215.1
EV-FlowNetMeasurement=count, Kernel=trilinear2019.041.7215.1
TMAdt=1, Input=E, Learning paradigm=SL2025.061.8127.29
Event FrameMeasurement=time stamps, Kernel=trilinear2019.041.9318.9
E-RAFTdt=1, Input=E, Learning paradigm=SL2025.061.9430.79
EDCFlow (+in1)dt=4, Input=E, Learning paradigm=SL, training_inclusion=flying12025.061.9715.56
Two-Channel ImageMeasurement=time stamps, Kernel=trilinear2019.041.9714.9
Two-Channel ImageMeasurement=count, Kernel=trilinear2019.042.0322.8
ESTBackbone=ResNet-18, Protocol=RGB initialization + Fully-Supervised2026.032.0519.9
EV-MGRFlowNetdt=4, Input=E, Learning paradigm=USL2025.062.3923.7
MultiCM (Burgers')dt=4, Input=E, Learning paradigm=MB2025.062.4926.35
STE-FlowNetdt=4, Input=E, Learning paradigm=SSL2025.062.5226.1
DCEIFlowdt=4, Input=E+I1, Learning paradigm=SL2025.063.4842.05
Zhu et al.dt=4, Input=E, Learning paradigm=USL2025.063.8546.8
EV-FlowNetdt=4, Input=E, Learning paradigm=SSL2025.064.0545.3
EDCFlowdt=4, Input=E, Learning paradigm=SL2025.064.1644.29
TMAdt=4, Input=E, Learning paradigm=SL2025.064.3252.74
IDNet-4dt=4, Input=E, Learning paradigm=SL, re-implemented=true2025.064.8256.82
E-RAFTdt=4, Input=E, Learning paradigm=SL2025.065.0964.19
IDNet-8dt=4, Input=E, Learning paradigm=SL, re-implemented=true2025.066.172.97