Synthesizing Obama

作者：Supasorn Suwajanakorn, Steven M. Seitz, Ira Kemelmacher-Shlizerman · 发表于：ACM Transactions on Graphics · 年份：2017 · DOI：10.1145/3072959.3073640 · 被引用次数：1095 · 研究领域：Face recognition and analysis、Speech and Audio Processing、Generative Adversarial Networks and Image Synthesis

Given audio of President Barack Obama, we synthesize a high quality video of him speaking with accurate lip sync, composited into a target video clip. Trained on many hours of his weekly address footage, a recurrent neural network learns the mapping from raw audio features to mouth shapes. Given the mouth shape at each time instant, we synthesize high quality mouth texture, and composite it with proper 3D pose matching to change what he appears to be saying in a target video to match the input audio track. Our approach produces photorealistic results.