Zhixin Shu

17

Papers

29

Total Citations

Papers (17)

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

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

Relightful Harmonization: Lighting-aware Portrait Background Replacement

Neural Face Editing With Intrinsic Image Disentangling

DocUNet: Document Image Unwarping via a Stacked U-Net

Content-Aware GAN Compression

RigNeRF: Fully Controllable Neural 3D Portraits

Learning Motion-Dependent Appearance for High-Fidelity Rendering of Dynamic Humans From a Single Camera

Point-NeRF: Point-Based Neural Radiance Fields

PaletteNeRF: Palette-Based Appearance Editing of Neural Radiance Fields

LightPainter: Interactive Portrait Relighting With Freehand Scribble

DewarpNet: Single-Image Document Unwarping With Stacked 3D and 2D Regression Networks

3D-FM GAN: Towards 3D-Controllable Face Manipulation

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

Learning an Isometric Surface Parameterization for Texture Unwrapping

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