AutoToon: Automatic Geometric Warping for Face Cartoon Generation
This work addresses the problem of automating face warping for caricature generation, which is incremental as it builds on existing stylization methods by introducing a novel supervised deep learning approach.
The authors tackled the challenge of generating high-quality geometric warps for face caricatures, which previous automated methods struggled with, and achieved appealing exaggerations that amplify distinguishing facial features while preserving detail, as validated by user studies.
Caricature, a type of exaggerated artistic portrait, amplifies the distinctive, yet nuanced traits of human faces. This task is typically left to artists, as it has proven difficult to capture subjects' unique characteristics well using automated methods. Recent development of deep end-to-end methods has achieved promising results in capturing style and higher-level exaggerations. However, a key part of caricatures, face warping, has remained challenging for these systems. In this work, we propose AutoToon, the first supervised deep learning method that yields high-quality warps for the warping component of caricatures. Completely disentangled from style, it can be paired with any stylization method to create diverse caricatures. In contrast to prior art, we leverage an SENet and spatial transformer module and train directly on artist warping fields, applying losses both prior to and after warping. As shown by our user studies, we achieve appealing exaggerations that amplify distinguishing features of the face while preserving facial detail.