CTGAN: Semantic-guided Conditional Texture Generator for 3D Shapes
This addresses the need for efficient and high-quality texture generation in the entertainment industry, representing a domain-specific advancement.
The paper tackles the problem of generating high-fidelity textures for 3D shapes, which is time-consuming with traditional methods, by proposing CTGAN, a semantic-guided conditional texture generator that outperforms existing methods and achieves state-of-the-art performance on quality metrics.
The entertainment industry relies on 3D visual content to create immersive experiences, but traditional methods for creating textured 3D models can be time-consuming and subjective. Generative networks such as StyleGAN have advanced image synthesis, but generating 3D objects with high-fidelity textures is still not well explored, and existing methods have limitations. We propose the Semantic-guided Conditional Texture Generator (CTGAN), producing high-quality textures for 3D shapes that are consistent with the viewing angle while respecting shape semantics. CTGAN utilizes the disentangled nature of StyleGAN to finely manipulate the input latent codes, enabling explicit control over both the style and structure of the generated textures. A coarse-to-fine encoder architecture is introduced to enhance control over the structure of the resulting textures via input segmentation. Experimental results show that CTGAN outperforms existing methods on multiple quality metrics and achieves state-of-the-art performance on texture generation in both conditional and unconditional settings.