Deep Interactive Surface Creation from 3D Sketch Strokes

Abstract

Creating art is often viewed as a uniquely human endeavor. In this paper, we introduce a multi-conditional Generative Adversarial Network (GAN) approach trained on large amounts of human paintings to synthesize realistic-looking paintings that emulate human art. Our approach is based on the StyleGAN neural network architecture, but incorporates a custom multi-conditional control mechanism that provides fine-granular control over characteristics of the generated paintings, e.g., with regard to the perceived emotion evoked in a spectator. We also investigate several evaluation techniques tailored to multi-conditional generation.

Use Cases for a Hybrid Augmented Reality Computer Workstation in Cad Workflows

“…Here, implicit modelling gestures allow for quick and intuitive realization of user's ideas. Existing approaches create parametric surface patches from mid-air gesturing (Fuge et al, 2012) or spatial line sketches (Bhattacharjee and Chaudhuri, 2022). Researchers also developed an approach for 3D shape modelling from hand poses without predefined gestures (Vinayak and Ramani, 2015).…”