Variety decorative bas-relief generation based on normal prediction and transfer

As the generation of realistic bas-relief models from 2D images suffers from insufficient 3D depth information and severe under-constraint, in this article, we propose a new framework for bas-relief modeling based on 2D decorative images, which adopts conditional generative adversarial network to infer the normal information of the decorative bas-reliefs from the greyscale information extracted from the images. For the variety of models, we extract the internal structure information through the saliency detection method based on scene perception, and use the transfer process based on the optimized texture synthesis algorithm to complete the normal editing from the source normal map to the new one, which can diversify and control the structure and detailed information of existed normal map. Finally, we adopt a bas-relief reconstruction approach based on domain transfer recursive filter and surface from gradient to recover 2.5D information from predicted and transferred normal maps. Experiments on various model examples demonstrate the efficiency and diversity of the proposed method in reconstructing bas-relief models from a single decorative image.