MatFusion: A Generative Diffusion Model for SVBRDF Capture

TL;DR

MatFusion introduces a diffusion-based approach for SVBRDF estimation from photographs, enabling flexible, high-quality material synthesis and refinement under various lighting conditions, with competitive accuracy.

Contribution

The paper presents a novel diffusion model backbone for SVBRDF estimation trained on synthetic data, allowing flexible refinement and multiple plausible outputs from a single photograph.

Findings

Achieves equal or better accuracy than existing methods under flash lighting.

Enables synthesis of multiple SVBRDF estimates for user selection.

Refinement with rendering methods does not require backpropagation during training.

Abstract

We formulate SVBRDF estimation from photographs as a diffusion task. To model the distribution of spatially varying materials, we first train a novel unconditional SVBRDF diffusion backbone model on a large set of 312,165 synthetic spatially varying material exemplars. This SVBRDF diffusion backbone model, named MatFusion, can then serve as a basis for refining a conditional diffusion model to estimate the material properties from a photograph under controlled or uncontrolled lighting. Our backbone MatFusion model is trained using only a loss on the reflectance properties, and therefore refinement can be paired with more expensive rendering methods without the need for backpropagation during training. Because the conditional SVBRDF diffusion models are generative, we can synthesize multiple SVBRDF estimates from the same input photograph from which the user can select the one that best matches the users' expectation. We demonstrate the flexibility of our method by refining different SVBRDF diffusion models conditioned on different types of incident lighting, and show that for a single photograph under colocated flash lighting our method achieves equal or better accuracy than existing SVBRDF estimation methods.