We conduct qualitative and quantitative experiments with user studies to demonstrate that the proposed approach performs favorably against existing image-to-image translation and caricature generation methods. We perform extensive ablation studies to validate each component of the proposed shape transformation algorithm. To evaluate the proposed framework, we conduct experiments on the photo-caricature benchmark dataset (Huo et al. To learn effective shape transformation, we design a spatial transformer network (STN) to allow larger and flexible shape changes, while a few loss functions are introduced to better maintain facial structures. Instead, we learn the model directly on the face parsing map, which is the shape transformation of interest. Nevertheless, operating this learning process in the image domain may involve noise from unnecessary information in pixels. Specifically, given an unpaired caricature with a normal photo, we leverage the cycle consistency strategy and an encoder–decoder architecture to model the shape transformation. As such, this can provide more accurate mapping for facial details, e.g., shapes of eyebrows, noses, and face contours, to name a few. 2019), we use a semantic face parsing map, i.e., a dense pixel-wise parsing map, to guide the shape transformation process. Different from existing methods that only consider facial landmarks or sparse points (Cao et al. Meanwhile, a rendered caricature should still maintain the facial structure and personal traits. In this work, we aim to create shape exaggerations on standard photos with shape transformations similar to those drawn by artists. 2017a) algorithms have been developed, but most techniques can be applied to two domains with local texture variations, not for scenarios where large shape discrepancy exists. 2018) and neural style transfer (Gatys et al. Recently, image-to-image translation (Isola et al. However, such methods may have limitations on generating diverse and visually pleasing results due to inaccurate shape transformations. 2000) or hand-crafted rules (Brennan 2007 Liao et al. Numerous efforts have been made to perform shape exaggeration by computing warping parameters between photos and caricatures from user-defined shapes (Akleman et al. One crucial factor to generate a desirable caricature is to distort facial components properly, i.e., to render personal traits with certain exaggerations.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |