Charles Herrmann

diffusion model (5) optical flow (3) video generation (3) zero-shot learning (3) 3d scene generation (3) single image (2) semantic correspondence (2) data augmentation (2) differentiable rendering (2) vision language model (2) self-supervised learning (2) motion estimation (2) video processing (2) view synthesis (2) depth estimation (2) generative model (2) novel view synthesis (2) synthetic data generation (2) point cloud generation (1) model robustness (1)