Exemplar-based Pattern Synthesis with Implicit Periodic Field Network

TL;DR

This paper introduces the Implicit Periodic Field Network (IPFN), a scalable, diverse, and authentic exemplar-based pattern synthesis method using GANs and periodic encoding, applicable to 2D textures and 3D shapes.

Contribution

The paper proposes IPFN, a novel implicit network with periodic encoding for scalable, diverse, and high-quality pattern synthesis, advancing the state of the art in visual pattern generation.

Findings

Synthesizes tileable patterns with smooth transitions.

Produces high-quality, high-frequency details.

Effective in 2D texture and 3D shape synthesis.

Abstract

Synthesis of ergodic, stationary visual patterns is widely applicable in texturing, shape modeling, and digital content creation. The wide applicability of this technique thus requires the pattern synthesis approaches to be scalable, diverse, and authentic. In this paper, we propose an exemplar-based visual pattern synthesis framework that aims to model the inner statistics of visual patterns and generate new, versatile patterns that meet the aforementioned requirements. To this end, we propose an implicit network based on generative adversarial network (GAN) and periodic encoding, thus calling our network the Implicit Periodic Field Network (IPFN). The design of IPFN ensures scalability: the implicit formulation directly maps the input coordinates to features, which enables synthesis of arbitrary size and is computationally efficient for 3D shape synthesis. Learning with a periodic encoding scheme encourages diversity: the network is constrained to model the inner statistics of the exemplar based on spatial latent codes in a periodic field. Coupled with continuously designed GAN training procedures, IPFN is shown to synthesize tileable patterns with smooth transitions and local variations. Last but not least, thanks to both the adversarial training technique and the encoded Fourier features, IPFN learns high-frequency functions that produce authentic, high-quality results. To validate our approach, we present novel experimental results on various applications in 2D texture synthesis and 3D shape synthesis.