Haodong Li

DA$^{2}$: Depth Anything in Any Direction

D$^2$GS: Depth-and-Density Guided Gaussian Splatting for Stable and Accurate Sparse-View Reconstruction

Jasmine: Harnessing Diffusion Prior for Self-supervised Depth Estimation

Lotus: Diffusion-based Visual Foundation Model for High-quality Dense Prediction

DisEnvisioner: Disentangled and Enriched Visual Prompt for Customized Image Generation

DOME: Taming Diffusion Model into High-Fidelity Controllable Occupancy World Model