MaterialMVP: Illumination-Invariant Material Generation via Multi-view PBR Diffusion
This addresses material synthesis for 3D graphics, enabling more realistic and controllable texture generation, though it appears incremental with novel components like Reference Attention and Consistency-Regularized Training.
The paper tackles the problem of generating physically-based rendering (PBR) textures from 3D meshes and image prompts, achieving illumination-invariant and geometrically consistent results that outperform existing methods in consistency and quality for scalable 3D asset creation.
Physically-based rendering (PBR) has become a cornerstone in modern computer graphics, enabling realistic material representation and lighting interactions in 3D scenes. In this paper, we present MaterialMVP, a novel end-to-end model for generating PBR textures from 3D meshes and image prompts, addressing key challenges in multi-view material synthesis. Our approach leverages Reference Attention to extract and encode informative latent from the input reference images, enabling intuitive and controllable texture generation. We also introduce a Consistency-Regularized Training strategy to enforce stability across varying viewpoints and illumination conditions, ensuring illumination-invariant and geometrically consistent results. Additionally, we propose Dual-Channel Material Generation, which separately optimizes albedo and metallic-roughness (MR) textures while maintaining precise spatial alignment with the input images through Multi-Channel Aligned Attention. Learnable material embeddings are further integrated to capture the distinct properties of albedo and MR. Experimental results demonstrate that our model generates PBR textures with realistic behavior across diverse lighting scenarios, outperforming existing methods in both consistency and quality for scalable 3D asset creation.