Hui Huang

EnvSocial-Diff: A Diffusion-Based Crowd Simulation Model with Environmental Conditioning and Individual-Group Interaction

StreetDiffusion: Street Scenes Generation via Multi-view Stable Diffusion with Structure Prompts

Augmented Radiance Field: A General Framework for Enhanced Gaussian Splatting

3D Shape Generation via Tri-Vectors: a Parsimonious Representation

Class-Adaptive Rectification with Experts for Robust Long-Tailed Noisy Label Learning

Active View Selection for Scene-level Multi-view Crowd Counting and Localization with Limited Labels

Learning Fast and Slow: Addressing Task-Imbalanced Continual Learning with Dual-Speed Adaptation

STM4D: 4D Occupancy Forecasting with 2D and 3D Spatio-Temporal Modeling

STT: Towards Training-Free Zero-Shot Composed Image Retrieval via Semantic Transition and Transportation

MVMP-HMR: Multiview Multi-Person Human Mesh Recovery Under Large Scenes with Occlusions

Reconstruct and Match: Out-of-Distribution Robustness via Topological Homogeneity

CRAYM: Neural Field Optimization via Camera RAY Matching

Improving Visual Prompt Tuning by Gaussian Neighborhood Minimization for Long-Tailed Visual Recognition