Zhixin Shu

6

Papers

29

Total Citations

Papers (6)

Carve3D: Improving Multi-view Reconstruction Consistency for Diffusion Models with RL Finetuning

In-N-Out: Faithful 3D GAN Inversion with Volumetric Decomposition for Face Editing

Augmented Mass-Spring Model for Real-Time Dense Hair Simulation

FaceLift: Learning Generalizable Single Image 3D Face Reconstruction from Synthetic Heads

Holo-Relighting: Controllable Volumetric Portrait Relighting from a Single Image

Relightful Harmonization: Lighting-aware Portrait Background Replacement