Ashish Patel 🇮🇳’s Post

𝗗𝗮𝘆-𝟰𝟴𝟯 𝗖𝗼𝗺𝗽𝘂𝘁𝗲𝗿 𝗩𝗶𝘀𝗶𝗼𝗻 𝗟𝗲𝗮𝗿𝗻𝗶𝗻𝗴 HuMMan: Multi-Modal 4D Human Dataset for Versatile Sensing and Modeling by Shanghai Artificial Intelligence Research Institute Co., Ltd. Follow me for a similar post: Ashish Patel ------------------------------------------------------------------- 𝗜𝗻𝘁𝗲𝗿𝗲𝘀𝘁𝗶𝗻𝗴 𝗙𝗮𝗰𝘁𝘀 : 🔸 This paper is published arxiv2022. ------------------------------------------------------------------- 𝗜𝗠𝗣𝗢𝗥𝗧𝗔𝗡𝗖𝗘 👉 4D human sensing and modeling are fundamental tasks in vision and graphics with numerous applications.  👉 With the advances of new sensors and algorithms, there is an increasing demand for more versatile datasets.  👉 In this work, we contribute HuMMan, a large-scale multi-modal 4D human dataset with 1000 human subjects, 400k sequences and 60M frames. HuMMan has several appealing properties:  👉 1) multi-modal data and annotations including color images, point clouds, keypoints, SMPL parameters, and textured meshes;  👉 2) popular mobile device is included in the sensor suite;  👉 3) a set of 500 actions, designed to cover fundamental movements;  👉 4) multiple tasks such as action recognition, pose estimation, parametric human recovery, and textured mesh reconstruction are supported and evaluated. 👉 Extensive experiments on HuMMan voice the need for further study on challenges such as fine-grained action recognition, dynamic human mesh reconstruction, point cloud-based parametric human recovery, and cross-device domain gaps. #computervision #artificialintelligence #deeplearning