These diverse images generated with retrieval guidance can effectively alleviate the overfitting problem troubling concrete category-specific training samples with high gradients. The retrieval module guides the synthesis module to generate large amounts of diverse photo-like images which gradually approach the photo domain, and thus better serve the retrieval module than ever to learn domain-agnostic representations and category-agnostic common knowledge for generalizing to unseen categories. The huge domain gap between sketches and photos and the highly abstract sketch representations pose challenges for sketch-based image retrieval (\underline'') to jointly optimize sketch-to-photo synthesis and the image retrieval. Extensive experiments have shown that given roughly sketched human portraits, our method produces more realistic images than the state-of-the-art sketch-to-image synthesis techniques. Finally, we use a global synthesis network for the sketch-to-image translation task, and a face refinement network to enhance facial details. Globally, we employ a cascaded spatial transformer network to refine the structure of body parts by adjusting their spatial locations and relative proportions. Locally, we employ semantic part auto-encoders to construct part-level shape spaces, which are useful for refining the geometry of an input pre-segmented hand-drawn sketch. To encode complicated body shapes under various poses, we take a local-to-global approach. In this work, we present DeepPortraitDrawing, a deep generative framework for converting roughly drawn sketches to realistic human body images. It is, first because of the sensitivity to human shapes, second because of the complexity of human images caused by body shape and pose changes, and third because of the domain gap between realistic images and freehand sketches.
STANDALONE PHOTOSKETCHER HOW TO
However, how to generate realistic human body images from sketches is still a challenging problem.
Researchers have explored various ways to generate realistic images from freehand sketches, e.g., for objects and human faces.
0 kommentar(er)
