Code for human pose estimation with VAE-GAN hybrid model.

Presentation Thesis

• Concetps
• 3D HPE
  • 2D-3D Lifting
• 2D HPE
• Datasets
• More Stuff

• Reprojection Error Optimization - 3D human body model is deformed such that it satisfies a reprojection error
• Direct NN inference - estimate 3D poses directly from images or detected keypoints
• Kinematic Chain Space (KCS) - Projecting 3D human pose into KCS, a contraint is derived that is based on the assumption that the bone lengths are constant. This can be benificial as giving an additional feature matrix to the network, it doesnt have to learn joint length computation and angular constraints on its own KCS for monocular MoCap
• Non rigid structure from motion (NRSfM) - aims to obtain the varying 3D structure and camera motion from uncalibrated 2D point tracks NR-SFM video explanation
• Kinematic Feature updates (in 2D) - encode the kinematic structure via feature updates at coarse resolution RePose
• Real-time: Casading, Long short skip connections XNect
• Ordinal Ranking Ordinal+CVAE DRPose3D - Depth Ranking
• C-VAE Ordinal+CVAE

[Paper] [Code] [Code] [ICCV 2019] [image-2Dheatmap-3D, absolute pose, multi person, pose depth, cascade]

[Paper] [CVPR 2019] [2D-3D, self supervised, discriminator, domain adaptation, temporal consistency]

[Paper] [2019,2020] [image-2D-3D, project w/ focal length, learn human size, absolute pose, noise, errors, cascade]

[Paper] [Code] [CVPR 2019] [2D-3D, KCS, weakly supervised, adversial training, GAN]

[Paper] [ICCV 2019] [Image features+2D-3D, NRSfM, teacher student, weakly supervised]

[Paper] [Code] [ICCV 2019] [2D-3D, NRSFM, canonicalization network, self-supervised]

[Paper] [Code] [2018] [2D-3D, GAN, unsupervised]

[Paper] [ICCV 2019] [2Dheatmap-3D, ambigious use of 3D GT, C-VAE, ordinal ranking and score, condition on 2d pose]

[Paper] [ICCV 2019] [2Dheatmap-3D, reprojection+GT, adversarial, occlusion, video]

[Paper] [2020] [kinematic priors]

• Human3.6[2014] - 2D and 3D relative joint pose, multi view
• MPI-INF-3DHP[2017] - 2D and 3D relative joint pose, mutli view
• JTA Joint Track Auto[2018] - 2D, 3D, occulusion annotation, synthetic

• Learning to Reconstruct people
• Gyeongsik Moon - Seoul National University
• awesome-human-pose-estimation
• 3d-human-pose-estimation