OneGT: One-Shot Geometry-Texture Neural Rendering for Head Avatars
Jinshu Chen, Bingchuan Li, Fan Zhang, Songtao Zhao, Qian He
2025年份
摘要
Figure 1. Inspired by the traditional rendering tools (shown in the upper part), we propose OneGT, a one-shot neural rendering pipeline (shown in the lower part). Explicitly following the traditional rendering process, our framework contains a prior skeleton-anchoring stage and a posterior texture-rendering stage, thus completely decoupling the geometry and the textures. The final rendered head avatars can be easily edited through simple manipulations of the given control conditions without professional skills.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
它引用的顶会 Paper31
- Denoising Diffusion Probabilistic ModelsJonathan Ho, Ajay Jain, Pieter AbbeelNeurIPS 2020 · 被引用 35,902 次
- High-Resolution Image Synthesis with Latent Diffusion ModelsRobin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser 等CVPR 2022 · 被引用 13,123 次
- Directly Denoising Diffusion ModelsDan Zhang, Jingjing Wang, Feng LuoICML 2024 · 被引用 11,724 次
- 3D Gaussian Splatting for Real-Time Radiance Field RenderingBernhard Kerbl, Georgios Kopanas, Thomas Leimkühler, George DrettakisSIGGRAPH 2023 · 被引用 5,687 次
- Scalable Diffusion Models with TransformersWilliam Peebles, Saining XieICCV 2023 · 被引用 5,568 次
相关 Paper
- OTAvatar: One-Shot Talking Face Avatar with Controllable Tri-Plane RenderingZhiyuan Ma, Xiangyu Zhu, Guojun Qi, Zhen Lei 等CVPR 2023
- SVG-Head: Hybrid Surface-Volumetric Gaussians for High-Fidelity Head Reconstruction and Real-Time EditingHeyi Sun, Cong Wang, Tian-Xing Xu, Jingwei Huang 等ICCV 2025 · 被引用 8 次
- AvatarReX: Real-time Expressive Full-body AvatarsZerong Zheng, Xiaochen Zhao, Hongwen Zhang, Boning Liu 等SIGGRAPH 2023 · 被引用 80 次
- InvertAvatar: Incremental GAN Inversion for Generalized Head AvatarsXiaochen Zhao, Jingxiang Sun, Lizhen Wang, Jinli Suo 等SIGGRAPH 2024 · 被引用 10 次
- ANR: Articulated Neural Rendering for Virtual AvatarsAmit Raj, Julian Tanke, James Hays, Minh Vo 等CVPR 2021
