An evaluation of SVBRDF Prediction from Generative Image Models for Appearance Modeling of 3D Scenes
This work addresses appearance modeling for digital content creation, offering an incremental improvement by evaluating methods to enhance consistency in fast pipelines.
The paper tackles the problem of generating consistent SVBRDF texture atlases for 3D scenes by combining generative image models with SVBRDF prediction networks, finding that a standard UNet architecture achieves competitive accuracy and coherence compared to more complex designs.
Digital content creation is experiencing a profound change with the advent of deep generative models. For texturing, conditional image generators now allow the synthesis of realistic RGB images of a 3D scene that align with the geometry of that scene. For appearance modeling, SVBRDF prediction networks recover material parameters from RGB images. Combining these technologies allows us to quickly generate SVBRDF maps for multiple views of a 3D scene, which can be merged to form a SVBRDF texture atlas of that scene. In this paper, we analyze the challenges and opportunities for SVBRDF prediction in the context of such a fast appearance modeling pipeline. On the one hand, single-view SVBRDF predictions might suffer from multiview incoherence and yield inconsistent texture atlases. On the other hand, generated RGB images, and the different modalities on which they are conditioned, can provide additional information for SVBRDF estimation compared to photographs. We compare neural architectures and conditions to identify designs that achieve high accuracy and coherence. We find that, surprisingly, a standard UNet is competitive with more complex designs. Project page: http://repo-sam.inria.fr/nerphys/svbrdf-evaluation