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.

Email  /  Google Scholar  /  Github

We adopt a 3DGS-Mesh coupled representation with pre-trained human video diffusion models for one-shot vivid talking avatars.

We integrate a neural physics simulation engine with the 3DGS avatar for realistic clothed body animation.

We combine FlashAvatar with multimodal generative models to achieve consistent portrait video editing.

We attach 3DGS on mesh UV space to achieve 300FPS head avatar rendering.

We utilize prior-guided implicit neural rendering to reconstruct the 3D head model.

We address the talking head problem with the aid of dynamic neural radiance fields.

We present a method to jointly learn a 3D face parametric model and 3D face reconstruction from diverse sources.

Given the video stream from a single camera, we generate a stream that emulates the view from a virtual camera at a designated location.

StereoPIFu integrates the geometric constraints of stereo vision with implicit representation to recover the 3D shape of the clothed human.

We propose the first automatic method for landmark detection and 3D face reconstruction for caricature by a 3D approach.

We present a framework to recover high-fidelity face shapes from one-to-three images captured under near lights.

We present a novel face data generation method to train the 3DFaceNet for real-time dense face reconstruction from a monocular RGB video.

Wonderful template from Jon Barron.