Details for DIGIT-HRNet

AuthorsZicong Fan, Adrian Spurr, Muhammed Kocabas, Siyu Tang, Michael J. Black, Otmar Hilliges
Paper titleLearning to Disambiguate Strongly Interacting Hands via Probabilistic Per-Pixel Part Segmentation
Publication venue3DV
Publication year2021
URLhttps://arxiv.org/pdf/2107.00434.pdf
Additional Information Adaptation of DIGIT to ARCTIC setting. Changes: - Estimate the object mask as well on top of the hand segmentation masks. - Keep the segmentation and fusion U-Net, but swap the pose regressor to ArcticNet-SF heads. - Use HRNet as backbone Code: https://github.com/XueYing126/arctic-digit/tree/Digit
Note
Use a single algorithm per method. All tasks can be submitted via the same algorithm.
Tasks:
AAE 5.24
MPJPE_RA_H 17.92
MPJPE_RA_L 0.00
MPJPE_RA_R 0.00
MRRPE_R_L 44.19
MRRPE_R_O 35.43
SUCCESS_RATE 76.52
CDEV_HO 34.92
MDEV_H 8.37
ACC_H 4.86
ACC_O 6.63
AVG_HO 0.00
AVG_OH 0.00
ACC_OH 0.00
ACC_HO 0.00
CD_H 0.00
CD_ICP 0.00
CD_L 0.00
CD_R 0.00
F10_ICP 0.00
F5_ICP 0.00
AAE 6.60
MPJPE_RA_H 16.74
MPJPE_RA_L 0.00
MPJPE_RA_R 0.00
MRRPE_R_L 25.49
MRRPE_R_O 32.61
SUCCESS_RATE 53.33
CDEV_HO 41.31
MDEV_H 9.48
ACC_H 4.01
ACC_O 8.32
AVG_HO 0.00
AVG_OH 0.00
ACC_OH 0.00
ACC_HO 0.00
CD_H 0.00
CD_ICP 0.00
CD_L 0.00
CD_R 0.00
F10_ICP 0.00
F5_ICP 0.00