Baidu Geek Talk
Mar 8, 2023 · Artificial Intelligence
Understanding Motion Decomposition in AI-Based Image Animation: From Sparse to Dense Optical Flow
The article details how AI‑based image animation and face‑swapping decompose video motion into zero‑order rigid and first‑order affine components via Taylor expansion, using unsupervised U‑Net keypoint extraction, sparse-to-dense optical flow conversion, and dense motion networks that learn masks for region‑wise rigidity and non‑rigid deformation.
Neural NetworksTaylor expansionaffine transformation
0 likes · 21 min read