TalkingAvatar: Learning 3D talking human avatar via NeRF
Authors:
- Lingyun YuLYLingyun Yu
- Chuang ChenCCChuang Chen
- Chuanbin LiuCLChuanbin Liu
- Wu LiuWLWu Liu
- Quanwei YangQYQuanwei Yang
- Yizhi LiuYLYizhi Liu
- Meng ShaoMSMeng Shao
- 13 September 2025
- journal article
- Published by Elsevier in Neurocomputing
- Vol. 656
Abstract
No abstract availableFunding Information
- National Natural Science Foundation of China (62472395)
- National Natural Science Foundation of China (62272436)
- National Key Research and Development Program of China (2024YFE0203200)
This publication has 14 references indexed in Scilit:
- Dual-Path Transformer for 3D Human Pose EstimationIEEE Transactions on Circuits and Systems for Video Technology, 2023
- X-Avatar: Expressive Human Avatars2023
- Toward Realistic 3D Human Motion Prediction With a Spatio-Temporal Cross- Transformer ApproachIEEE Transactions on Circuits and Systems for Video Technology, 2023
- A Progressive Quadric Graph Convolutional Network for 3D Human Mesh RecoveryIEEE Transactions on Circuits and Systems for Video Technology, 2022
- 3D Hand Pose Estimation From Monocular RGB With Feature Interaction ModuleIEEE Transactions on Circuits and Systems for Video Technology, 2022
- HyperNeRFACM Transactions on Graphics, 2021
- An Integrated Platform for Live 3D Human Reconstruction and Motion CapturingIEEE Transactions on Circuits and Systems for Video Technology, 2016
- SMPLACM Transactions on Graphics, 2015
- Scope of validity of PSNR in image/video quality assessmentElectronics Letters, 2008
- Image quality assessment: from error visibility to structural similarityIEEE Transactions on Image Processing, 2004