"Expressive body capture: 3d hands, face, and body from a single image." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. "Embodied hands: Modeling and capturing hands and bodies together." ACM Transactions on Graphics (ToG) 36.6 (2017): 1-17. Romero, Javier, Dimitrios Tzionas, and Michael J. "SMPL: A skinned multi-person linear model." ACM transactions on graphics (TOG) 34.6 (2015): 1-16. Please consider citing these works if you find this repo is useful for your easymocap, This project is a part of our work iMocap, Mirrored-Human, mvpose, Neural Body, MultiNeuralBody, enerf. We would also like to thank all the people who has helped EasyMocap in any way. We would like to thank Wenduo Feng, Di Huang, Yuji Chen, Hao Xu, Qing Shuai, Qi Fang, Ting Xie, Junting Dong, Sida Peng and Xiaopeng Ji who are the performers in the sample data. ContributorĮasyMocap is built by researchers from the 3D vision group of Zhejiang University: Qing Shuai, Qi Fang, Junting Dong, Sida Peng, Di Huang, Hujun Bao, and Xiaowei Zhou. We appreciate all contributions to improve our project. Please open an issue if you have any questions. easymocap/estimator/HRNet : a 2D human pose estimator 7.easymocap/estimator/YOLOv4: an object detector 6.easymocap/estimator/SPIN : an SMPL estimator 4.easymocap/estimator/mediapipe_wrapper.py: MediaPipe.We integrate some easy-to-use functions for previous great work:.The method for fitting 3D skeleton and SMPL model is similar to SMPLify-X(with 3D keypoints loss), TotalCapture(without using point clouds).Some functions are borrowed from SPIN, VIBE, SMPLify-X.
SMPL models and layer are from MPII SMPL-X model.Here are the great works this project is built upon: : The calibration tool and the annotator are released.: The real-time 3D visualization part is released!.: The Multi-view Multi-person part is released!.: Support mediapipe keypoints detector.Annotator for bounding box, keypoints and mask Updates
0 kommentar(er)
