IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2026
We propose a personalized head representation that disentangles expression and identity for highly expressive portrait video synthesis.
Yudong Guo
I am an assistant professor at University of Science and Technology of China (USTC). I got my Ph.D. degree from USTC in 2021, supervised by Prof. Juyong Zhang. Before that, I received bachelor degree in Statistics in 2015 from USTC. From fall 2016 to spring 2017, I was a research assistant in the MultiMedia Lab at Nanyang Technological University under supervision of Prof. Jianfei Cai and Prof. Jianmin Zheng. My research interests include 3D vision and digital human.
Publications
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2026
We propose a feed-forward 3D editing framework operating in sparse voxel space for fast, globally consistent, and high-fidelity 3D asset editing.
IEEE Transactions on Visualization and Computer Graphics (TVCG), 2026
We embed a 3D Gaussian feature field within SMPL-X surface for high-fidelity, 3D-consistent video head swapping with natural head-torso blending.
IEEE International Conference on Computer Vision (ICCV), 2025
We adopt a 3DGS-Mesh coupled representation with pre-trained human video diffusion models for one-shot vivid talking avatars.
IEEE Transactions on Visualization and Computer Graphics (TVCG), 2025
We integrate a neural physics simulation engine with the 3DGS avatar for realistic clothed body animation.
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2025
IEEE Transactions on Visualization and Computer Graphics (TVCG), 2025
IEEE Transactions on Visualization and Computer Graphics (TVCG), 2025
SIGGRAPH Asia Conference Proceedings, 2024
We combine FlashAvatar with multimodal generative models to achieve consistent portrait video editing.
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2024
We attach 3DGS on mesh UV space to achieve 300FPS head avatar rendering.
SIGGRAPH Asia (Journal Track), 2022
IEEE Transactions on Multimedia (TMM), 2021
We utilize prior-guided implicit neural rendering to reconstruct the 3D head model.
IEEE International Conference on Computer Vision (ICCV), 2021
We address the talking head problem with the aid of dynamic neural radiance fields.
IEEE Transactions on Image Processing (TIP), 2021
We present a method to jointly learn a 3D face parametric model and 3D face reconstruction from diverse sources.
StereoPIFu: Depth Aware Clothed Human Digitization via Stereo Vision
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021
StereoPIFu integrates the geometric constraints of stereo vision with implicit representation to recover the 3D shape of the clothed human.
Graphical Models, 2021
We propose the first automatic method for landmark detection and 3D face reconstruction for caricature by a 3D approach.
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020
We present a framework to recover high-fidelity face shapes from one-to-three images captured under near lights.
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2018
We present a novel face data generation method to train the 3DFaceNet for real-time dense face reconstruction from a monocular RGB video.