High‐Resolution Neural Face Swapping for Visual Effects

• DOI: 10.1111/cgf.14062
• Publication Date: 2020-07-20T19:56:20Z
• Authors: J. Naruniec; L. Helminger; C. Schroers; R.M. Weber
• Keywords: Compositing; Landmark

Abstract In this paper, we propose an algorithm for fully automatic neural face swapping in images and videos. To the best of our knowledge, is first method capable rendering photo‐realistic temporally coherent results at megapixel resolution. end, introduce a progressively trained multi‐way comb network light‐ contrast‐preserving blending method. We also show that while progressive training enables generation high‐resolution images, extending architecture data beyond two people allows us to achieve higher fidelity generated expressions. When compositing expression onto target face, how adapt strategy preserve contrast low‐frequency lighting. Finally, incorporate refinement into landmark stabilization temporal stability, which crucial working with conduct extensive ablation study influence design choices on quality swap compare work popular state‐of‐the‐art methods.