List your company
ResearchFormerly WizWand

Human Pose Estimation on ExLPose Low-light-normal (LL-N)

42.3AP (IoU 0.5:0.95)Ours
14.2221.5128.836.09Mar 27, 2023Jun 15, 2023Sep 4, 2023Nov 23, 2023Feb 12, 2024May 2, 2024Jul 22, 2024
Updated 8mo ago

Evaluation results

MethodLinks
OursTraining data (LL)=true, Training data (WL)=true, Param. (M)=27.53, Latency (sec)=1.072023.0342.3
LIME + Baseline-allTraining data (WL)=true, Training data (Enhanced-LL)=true, Param. (M)=27.37, Latency (sec)=1.652023.0338.3
DA-LLPose (Ours)Architecture=Bottom-up, Training Labels=Well-lit labels alone2024.0735.6
AdvEntTraining data (LL)=true, Training data (WL)=true, Param. (M)=27.37, Latency (sec)=1.072023.0335.6
OursDetection Model=Cascade R-CNN, Components=LSBN + LUPI2023.0335.6
LLFlow + Baseline-allTraining data (WL)=true, Training data (Enhanced-LL)=true, Param. (M)=66.23, Latency (sec)=3.342023.0335.2
DANNTraining data (LL)=true, Training data (WL)=true, Param. (M)=27.37, Latency (sec)=1.072023.0334.9
Baseline-allTraining data (LL)=true, Training data (WL)=true, Param. (M)=27.37, Latency (sec)=1.072023.0333.8
Baseline-lowTraining data (LL)=true, Param. (M)=27.37, Latency (sec)=1.072023.0332.6
LIMEArchitecture=Top-down2024.0731.9
LIME + Baseline-allDetection Model=Cascade R-CNN, Pre-processing=LIME2023.0331.9
LLFlow†Architecture=Top-down, Training Labels=Low-light and well-lit2024.0728.7
LLFlow + Baseline-allDetection Model=Cascade R-CNN, Pre-processing=LLFlow2023.0328.7
DANNArchitecture=Top-down2024.0728
DANNDetection Model=Cascade R-CNN, Method Category=UDA2023.0328
CPN-all†Architecture=Top-down, Training Labels=Low-light and well-lit2024.0726.4
Baseline-allDetection Model=Cascade R-CNN, Training Data=All2023.0326.4
CPN-lowArchitecture=Top-down2024.0725.4
Baseline-lowDetection Model=Cascade R-CNN, Training Data=Low-light2023.0325.4
Baseline-wellTraining data (WL)=true, Param. (M)=27.37, Latency (sec)=1.072023.0323.5
CPN-well†Architecture=Top-down, Training Labels=Low-light and well-lit2024.0715.3
Baseline-wellDetection Model=Cascade R-CNN, Training Data=Well-lit2023.0315.3