From left to right: input photo (4096x4096 pixels), SVBRDF maps (albedo, normal, roughness, height, ambient occlusion) reconstructed with our method, rendering of the reconstructed material and rendering with a constant albedo to visualize the extracted geometry.

Abstract

We propose a hybrid method to reconstruct a physically-based spatially varying BRDF from a single high resolution picture of an outdoor surface captured under natural lighting conditions with any kind of camera device. Relying on both deep learning and explicit processing, our PBR material acquisition handles the removal of shades, projected shadows and specular highlights present when capturing a highly irregular surface and enables to properly retrieve the underlying geometry. To achieve this, we train two cascaded U-Nets on physically-based materials, rendered under various lighting conditions, to infer the spatially-varying albedo and normal maps. Our network processes relatively small image tiles (512x512 pixels) and we propose a solution to handle larger image resolutions by solving a Poisson system across these tiles. We complete this pipeline with analytical solutions to reconstruct height, roughness and ambient occlusion.

Downloads

• Manuscript: high resolution PDF (240Mb), low resolution PDF (9.1Mb)

Bibtex

@article{MRRKB:2022:MaterIA, 
  title = "MaterIA: Single Image High-Resolution Material Capture in the Wild", 
  author = "Rosalie Martin and Arthur Roullier and Romain Rouffet and Adrien Kaiser and Tamy Boubekeur", 
  year = "2022", 
  journal = "Computer Graphics Forum (Proc. EUROGRAPHICS 2022)",
  number = "to appear",
  volume = "to appear",
  pages  = "to appear",
}