Wensheng Li(李文盛)

I am currently working toward the Ph.D. degree with School of Computer Science and Engineering, Sun Yat-sen University, supervised by Prof. Chengying Gao and Prof. Ning Liu in Intelligent and Multimedia Science Laboratory. I received the B.S. and M.S. degree in Software Engineering from Sun Yat-sen University, Guangzhou, China, in 2018 and 2021, respectively.

I'm interested in computer vision and computer graphics, with a particular focus on human pose estimation, human body reconstruction, and neural rendering.

I expect to graduate by the end of this year and am currently looking for a job opportunity.

Email  /  Github  /  CV

Education

Experience

Publications

We propose a novel framework that mitigates density imbalance in 3D Gaussian Splatting for few-shot reconstruction.

We introduce IR-HGP, a framework that achieves robust disentanglement using three synergistic modules:First, a Hybrid Visibility Decomposition module ensures physical visibility consistency. Second, a Generative Illumination Field Prior module infers detailed and high-dynamic range environmental lighting. Finally, a Physics-Aware Radiance Correction module stabilizes optimization and mitigates illumination artifacts.

We propose a photometrically consistent integration of human and scene reconstruction based on 3D Gaussian Splatting, with a key focus on modeling spatially-varying illumination and shadows.

We propose a novel approach called ReGA, which leverages efficient 3D Gaussian Splatting to create animatable and relightable avatars from sparse-view human motion.

We introduce a feature replacement module that utilizes reversible network to decouple content and style features, ensuring the effective substitution of style information while preserving scene content.

We present a novel approach for efficiently modeling dynamic humans and achieving realistic renderings by integrating neural human representations.

We propose DanceComposer, a framework for the automatic generation of appropriate music from dance videos.

In this paper, we tackle the shape and pose estimation task of interacting hands from a single RGB image and outperform other methods by a large margin on the InterHand2.6M dataset.

Page inspired by Jon Barron.