为了探索 MVHumanNet 在各种 2D 和 3D 视觉任务中的潜力,我们对视图一致的动作识别、人类 NeRF 重建、文本驱动的视图无约束的人类图像生成以及 2D 视图无约束的人类图像和 3D 进行了试点研究 阿凡达一代。 大量的实验证明了 MVHumanNet 提供的规模所带来的性能改进和有效的应用程序。 作为当前规模最大的 3D 人体数...
MVHumanNet: A Large-scale Dataset of Multi-view Daily Dressing Human Captures (CVPR 2024) Project Page|Paper (Arxiv)|Dataset by Zhangyang Xiong#, Chenghong Li#, Kenkun Liu#, Hongjie Liao, Jianqiao Hu, Junyi Zhu, Shuliang Ning, Lingteng Qiu, Chongjie Wang, Shijie Wang, Shuguang Cui and...
def read_camera_mvhumannet(intri_name, extri_name, camera_scale ,cam_names=[]): assert os.path.exists(intri_name), intri_name assert os.path.exists(extri_name), extri_name import json with open(intri_name, 'r') as f: camera_intrinsics = json.load(f) with open(extri_name, 'r...
GAP-LAB-CUHK-SZ / MVHumanNet Public Notifications Fork 1 Star 123 Code Issues 5 Pull requests Actions Projects Security Insights CommitUpdate visualize_json2smplx.py Browse files Loading branch information X-zhangyang committed Jun 20, 2024 Verified 1 parent c9d376f commit 098b3...