My research interests lie at the intersection of vision and graphics. Recently, I have been focusing on 3D human motion modeling and generation. Some papers are highlighted.
I am currently looking for research internship opportunities.
This paper proposes Sketch2Anim, which translates 2D storyboard sketches into 3D animations through multi-conditional motion diffusion and a neural 2D-to-3D mapper.
This paper introduces PoseTraj, which leverages a Two-Stage Pose-Aware Pretraining framework and a large-scale synthetic dataset to accurately model 6D object motion.
This paper introduces SMooDi, which enables stylized motion generation by incorporating style motion sequences into a text-conditioned human motion generation model.
This paper introduces OmniControl, which incorporates flexible spatial control signals into a text-conditioned human motion generation model based on the diffusion process.
This paper proposes an aesthetic-guided outward image cropping method that extends beyond the image border to achieve compositions unattainable with previous methods.