TEXTRIX: Latent Attribute Grid for Native Texture Generation and Beyond
This addresses limitations in 3D texture generation for applications like 3D modeling and segmentation, representing a novel method rather than an incremental improvement.
The paper tackles the problem of inter-view inconsistencies and incomplete coverage in 3D texture generation by introducing TEXTRIX, a native 3D attribute generation framework that uses a latent grid and Diffusion Transformer to directly color 3D models, achieving state-of-the-art performance with seamless, high-fidelity textures and accurate 3D part segmentation.
Prevailing 3D texture generation methods, which often rely on multi-view fusion, are frequently hindered by inter-view inconsistencies and incomplete coverage of complex surfaces, limiting the fidelity and completeness of the generated content. To overcome these challenges, we introduce TEXTRIX, a native 3D attribute generation framework for high-fidelity texture synthesis and downstream applications such as precise 3D part segmentation. Our approach constructs a latent 3D attribute grid and leverages a Diffusion Transformer equipped with sparse attention, enabling direct coloring of 3D models in volumetric space and fundamentally avoiding the limitations of multi-view fusion. Built upon this native representation, the framework naturally extends to high-precision 3D segmentation by training the same architecture to predict semantic attributes on the grid. Extensive experiments demonstrate state-of-the-art performance on both tasks, producing seamless, high-fidelity textures and accurate 3D part segmentation with precise boundaries.