Photo2Relief: Let Human in the Photograph Stand Out
This provides a solution for creating digital 2.5D artwork from photographs, which is incremental as it extends relief generation from faces to whole bodies.
The paper tackles the problem of generating whole-body relief art from single photographs, overcoming challenges like lack of ground-truth data and varying lighting conditions, and demonstrates high effectiveness in experiments.
In this paper, we propose a technique for making humans in photographs protrude like reliefs. Unlike previous methods which mostly focus on the face and head, our method aims to generate art works that describe the whole body activity of the character. One challenge is that there is no ground-truth for supervised deep learning. We introduce a sigmoid variant function to manipulate gradients tactfully and train our neural networks by equipping with a loss function defined in gradient domain. The second challenge is that actual photographs often across different light conditions. We used image-based rendering technique to address this challenge and acquire rendering images and depth data under different lighting conditions. To make a clear division of labor in network modules, a two-scale architecture is proposed to create high-quality relief from a single photograph. Extensive experimental results on a variety of scenes show that our method is a highly effective solution for generating digital 2.5D artwork from photographs.