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

机构：[1] Beijing Key Laboratory of Information Service Engineering, Beijing Union University, Beijing, China; [2] College of Robotics, Beijing Union University, Beijing, China; [3] Institute of Artificial Intelligence, University of Science and Technology Beijing, Beijing, China; [4] Institute of Semiconductors, Chinese Academy of Sciences, Beijing, 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]Beijing Key Laboratory of Information Service Engineering, Beijing Union University, Beijing, China;[1]Beijing Key Laboratory of Information Service Engineering, Beijing Union University, Beijing, China|[11417103]北京联合大学北京市信息服务工程重点实验室;[11417]北京联合大学;

年份：2025

卷号：19

期号：1

外文期刊名：IET Computer Vision

收录：EI(收录号：20231313809633);Scopus(收录号：2-s2.0-85150871713)

语种：英文

外文关键词：Computer vision - Image reconstruction - Musculoskeletal system - Rendering (computer graphics) - Three dimensional computer graphics

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%. ? 2023 The Authors. IET Computer Vision published by John Wiley & Sons Ltd on behalf of The Institution of Engineering and Technology.