文献类型：期刊文献

英文题名：VT-NeRF: Neural radiance field with a vertex-texture latent code for high-fidelity dynamic human-body rendering

作者：Hao, Fengyu[1];Shang, Xinna[1,2];Li, Wenfa[1,3];Zhang, Liping[4];Lu, Baoli[4]

第一作者：Hao, Fengyu

通讯作者：Shang, XN[1];Li, WF[1];Shang, XN[2];Li, WF[3]

机构：[1]Beijing Union Univ, Beijing Key Lab Informat Serv Engn, Beijing, Peoples R China;[2]Beijing Union Univ, Coll Robot, Beijing, Peoples R China;[3]Univ Sci & Technol Beijing, Inst Artificial Intelligence, Beijing, Peoples R China;[4]Chinese Acad Sci, Inst Semicond, Beijing, Peoples R China

第一机构：北京联合大学北京市信息服务工程重点实验室

通讯机构：[1]corresponding author), Beijing Union Univ, Beijing Key Lab Informat Serv Engn, Beijing, Peoples R China;[2]corresponding author), Beijing Union Univ, Coll Robot, Beijing, Peoples R China;[3]corresponding author), Univ Sci & Technol Beijing, Inst Artificial Intelligence, Beijing, Peoples R China.|[1141739]北京联合大学机器人学院;[11417]北京联合大学;[11417103]北京联合大学北京市信息服务工程重点实验室;

年份：0

外文期刊名：IET COMPUTER VISION

收录：;EI(收录号：20231313809633);Scopus(收录号：2-s2.0-85150871713);WOS:【SCI-EXPANDED(收录号:WOS:000951045200001)】；

基金：ACKNOWLEDGEMENT National Natural Science Foundation of China, Grant/Award Numbers: 61972040.

语种：英文

外文关键词：3D human reconstruction; dynamic human body; neural radiation field; novel-view synthesis

摘要：The fusion of a human prior with neural rendering techniques has recently emerged as one of the most promising approaches to processing dynamic human-body scenes with sparse inputs. However, learning geometric details and appearance in dynamic human-body scenes based solely on a human prior model represents a severely under-constrained problem. A new human-body representation method to solve this problem: a neural radiance field with vertex-texture latent codes (VT-NeRF) is proposed. VT-NeRF uses joint latent code to improve access to detailed information, combining vertex latent codes with 2D texture latent codes for the body surface. Referencing a 3D human skeleton for accurate guidance, the human model can quickly match poses and learn information about the body in different frames. VT-NeRF can integrate body information from different frames and different poses quickly because it uses an information-rich human prior: a 3D human skeleton and parametric models. A 3D human scene is then presented as an implied field of density and colour. Experiments with the ZJU-MoCap dataset show that our method outperforms previous methods in terms of both novel-view synthesis and 3D human reconstruction quality. It is twice as fast as Neural Body, and its average accuracy reaches 95.9%.