Chord: Chain of Rendering Decomposition for PBR Material Estimation from Generated Texture Images
This addresses the challenge of efficient, high-quality material creation for computer graphics applications, though it appears to be an incremental improvement combining existing techniques in a novel way.
The paper tackles the problem of generating physically-based rendering (PBR) materials from user inputs, which traditionally requires significant artist expertise, by proposing a two-stage framework that synthesizes texture images and then estimates material channels sequentially. The method demonstrates superior performance over existing approaches and shows strong robustness on both generated textures and real photographs.
Material creation and reconstruction are crucial for appearance modeling but traditionally require significant time and expertise from artists. While recent methods leverage visual foundation models to synthesize PBR materials from user-provided inputs, they often fall short in quality, flexibility, and user control. We propose a novel two-stage generate-and-estimate framework for PBR material generation. In the generation stage, a fine-tuned diffusion model synthesizes shaded, tileable texture images aligned with user input. In the estimation stage, we introduce a chained decomposition scheme that sequentially predicts SVBRDF channels by passing previously extracted representation as input into a single-step image-conditional diffusion model. Our method is efficient, high quality, and enables flexible user control. We evaluate our approach against existing material generation and estimation methods, demonstrating superior performance. Our material estimation method shows strong robustness on both generated textures and in-the-wild photographs. Furthermore, we highlight the flexibility of our framework across diverse applications, including text-to-material, image-to-material, structure-guided generation, and material editing.