Hongyu Yang

4

Papers

89

Total Citations

Papers (4)

InitNO: Boosting Text-to-Image Diffusion Models via Initial Noise Optimization

Micro-macro Wavelet-based Gaussian Splatting for 3D Reconstruction from Unconstrained Images

GaussianIP: Identity-Preserving Realistic 3D Human Generation via Human-Centric Diffusion Prior

3D²-Actor: Learning Pose-Conditioned 3D-Aware Denoiser for Realistic Gaussian Avatar Modeling