Haoqian Wang

14

Papers

80

Total Citations

Papers (14)

TranSplat: Generalizable 3D Gaussian Splatting from Sparse Multi-View Images with Transformers

HRAvatar: High-Quality and Relightable Gaussian Head Avatar

MergeVQ: A Unified Framework for Visual Generation and Representation with Disentangled Token Merging and Quantization

TexVocab: Texture Vocabulary-conditioned Human Avatars

HumanMM: Global Human Motion Recovery from Multi-shot Videos

LD-RPS: Zero-Shot Unified Image Restoration via Latent Diffusion Recurrent Posterior Sampling

Spatiotemporal Blind-Spot Network with Calibrated Flow Alignment for Self-Supervised Video Denoising

GUAVA: Generalizable Upper Body 3D Gaussian Avatar

Prompt-SID: Learning Structural Representation Prompt via Latent Diffusion for Single Image Denoising

MVReward: Better Aligning and Evaluating Multi-View Diffusion Models with Human Preferences

DPoser-X: Diffusion Model as Robust 3D Whole-body Human Pose Prior

High-Fidelity 3D Head Avatars Reconstruction through Spatially-Varying Expression Conditioned Neural Radiance Field

Motions as Queries: One-Stage Multi-Person Holistic Human Motion Capture

LangSplat: 3D Language Gaussian Splatting