Generating Multiple Hypotheses for 3D Human Pose Estimation with Mixture Density Network

Benchmark Model Rank Results
multi-hypotheses-3d-human-pose-estimation-on-ah36mSMPL-MDN (by 3D Multi-bodies)#4Best-Hypothesis PMPJPE (n = 25): 69.5H36M PMPJPE (n = 25): 42.7…
multi-hypotheses-3d-human-pose-estimation-on-human36mMDN#8Average MPJPE (mm): 52.7Average PMPJPE (mm): 42.6
monocular-3d-human-pose-estimation-on-human3-6mMultimodal Mixture Density Networks#32Average MPJPE (mm): 52.7Use Video Sequence: NoFrames Needed: 1…
3d-human-pose-estimation-on-human36mMDN (Multi-View)#46Average MPJPE (mm): 49.6Using 2D ground-truth joints: No…
3d-human-pose-estimation-on-human36mMDN#60Average MPJPE (mm): 52.7Using 2D ground-truth joints: No…
3d-human-pose-estimation-on-mpi-inf-3dhpMDM#90PCK: 67.9