Photo2Relief: Let Human in the Photograph Stand Out
Zhongping Ji, Feifei Che, Hanshuo Liu, Ziyi Zhao, Yu-Wei Zhang and, Wenping Wang

TL;DR
Photo2Relief introduces a novel neural network approach that creates relief-like 3D effects of entire human figures in photographs, overcoming challenges of lack of ground-truth data and lighting variations.
Contribution
The paper presents a gradient domain loss function and a two-scale architecture for generating reliefs from single images without ground-truth supervision.
Findings
Effective relief generation across diverse scenes
Handles lighting variations with image-based rendering
Produces high-quality 2.5D artwork from photographs
Abstract
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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdvanced Vision and Imaging · 3D Surveying and Cultural Heritage · Generative Adversarial Networks and Image Synthesis
MethodsFocus
