Skip to yearly menu bar Skip to main content


Poster

MatFuse: Controllable Material Generation with Diffusion Models

Giuseppe Vecchio · Renato Sortino · Simone Palazzo · Concetto Spampinato

Arch 4A-E Poster #415
[ ] [ Project Page ] [ Paper PDF ]
[ Poster
Wed 19 Jun 10:30 a.m. PDT — noon PDT

Abstract:

Creating high-quality materials in computer graphics is a challenging and time-consuming task, which requires great expertise. To simplify this process, we introduce MatFuse, a unified approach that harnesses the generative power of diffusion models for creation and editing of 3D materials.Our method integrates multiple sources of conditioning, including color palettes, sketches, text, and pictures, enhancing creative possibilities and granting fine-grained control over material synthesis.Additionally, MatFuse enables map-level material editing capabilities through latent manipulation by means of a multi-encoder compression model which learns a disentangled latent representation for each map.We demonstrate the effectiveness of MatFuse under multiple conditioning settings and explore the potential of material editing. Finally, we assess the quality of the generated materials both quantitatively in terms of CLIP-IQA and FID scores and qualitatively by conducting a user study.Source code for training MatFuse and supplemental materials are publicly available at https://gvecchio.com/matfuse.

Chat is not available.