STS-GAN: Can We Synthesize Solid Texture with High Fidelity from Arbitrary 2D Exemplar?
This work provides a method for generating realistic 3D solid textures from 2D images, which is beneficial for computational photography applications.
This paper addresses the challenge of synthesizing high-fidelity 3D solid textures from arbitrary 2D exemplars, a task where existing methods often fall short. The proposed STS-GAN framework successfully extends 2D exemplars to 3D solid textures, demonstrating the ability to generate realistic solid textures with visual characteristics similar to the input.
Solid texture synthesis (STS), an effective way to extend a 2D exemplar to a 3D solid volume, exhibits advantages in computational photography. However, existing methods generally fail to accurately learn arbitrary textures, which may result in the failure to synthesize solid textures with high fidelity. In this paper, we propose a novel generative adversarial nets-based framework (STS-GAN) to extend the given 2D exemplar to arbitrary 3D solid textures. In STS-GAN, multi-scale 2D texture discriminators evaluate the similarity between the given 2D exemplar and slices from the generated 3D texture, promoting the 3D texture generator synthesizing realistic solid textures. Finally, experiments demonstrate that the proposed method can generate high-fidelity solid textures with similar visual characteristics to the 2D exemplar.