HumanNeRF: Efficiently Generated Human Radiance Field from Sparse Inputs

• Published in: Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) pp. 7733 - 7743
• Main Authors: Zhao, Fuqiang, Yang, Wei, Zhang, Jiakai, Lin, Pei, Zhang, Yingliang, Yu, Jingyi, Xu, Lan
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.06.2022
• Subjects: Cameras; Computer vision; Dynamics; Entertainment industry; Image and video synthesis and generation; 3D from multi-view and sensors; Face and gestures; Motion and tracking; Pose estimation and tracking; Rendering (computer graphics); Telepresence; Training

Recent neural human representations can produce high-quality multi-view rendering but require using dense multi-view inputs and costly training. They are hence largely limited to static models as training each frame is infeasible. We present HumanNeRF - a neural representation with efficient general...