Sicheng Xu

geometry learning (2) depth map (2) diffusion model (2) depth estimation (2) audio-visual synthesis (1) text-to-image synthesis (1) adversarial learning (1) facial animation (1) self-supervised learning (1) point cloud (1) monocular depth estimation (1) gaussian splatting (1) 3d generation (1) latent space (1) generative adversarial network (1) geometry estimation (1) mesh generation (1) vision foundation model (1) 3d content generation (1) 3d reconstruction (1)