HiMat: DiT-based Ultra-High Resolution SVBRDF Generation
Researchers have developed HiMat, a new framework for generating ultra-high-resolution (4K) spatially varying bidirectional reflectance functions (SVBRDFs). This method addresses the computational and memory challenges of creating detailed 3D content by operating in a compressed latent space and using a diffusion transformer with linear attention for efficiency. HiMat also incorporates a novel convolutional module called CrossStitch to ensure consistency across different reflectance maps without the overhead of global attention, outperforming prior methods in fidelity, efficiency, and diversity. AI
IMPACT Enables more efficient and detailed 3D content creation, potentially impacting real-time rendering and virtual environments.