Liwen Hu

8

Papers

29

Total Citations

Papers (8)

VOODOO 3D: Volumetric Portrait Disentanglement For One-Shot 3D Head Reenactment

SpikeGS: Reconstruct 3D Scene Captured by a Fast-Moving Bio-Inspired Camera

Photorealistic Facial Texture Inference Using Deep Neural Networks

Normalized Avatar Synthesis Using StyleGAN and Perceptual Refinement

Optical Flow Estimation for Spiking Camera

Learning To Listen: Modeling Non-Deterministic Dyadic Facial Motion

Learning to Robustly Reconstruct Dynamic Scenes from Low-light Spike Streams

1000 FPS HDR Video With a Spike-RGB Hybrid Camera