English

Materials for Masses: SVBRDF Acquisition with a Single Mobile Phone Image

Computer Vision and Pattern Recognition 2018-04-17 v1

Abstract

We propose a material acquisition approach to recover the spatially-varying BRDF and normal map of a near-planar surface from a single image captured by a handheld mobile phone camera. Our method images the surface under arbitrary environment lighting with the flash turned on, thereby avoiding shadows while simultaneously capturing high-frequency specular highlights. We train a CNN to regress an SVBRDF and surface normals from this image. Our network is trained using a large-scale SVBRDF dataset and designed to incorporate physical insights for material estimation, including an in-network rendering layer to model appearance and a material classifier to provide additional supervision during training. We refine the results from the network using a dense CRF module whose terms are designed specifically for our task. The framework is trained end-to-end and produces high quality results for a variety of materials. We provide extensive ablation studies to evaluate our network on both synthetic and real data, while demonstrating significant improvements in comparisons with prior works.

Keywords

Cite

@article{arxiv.1804.05790,
  title  = {Materials for Masses: SVBRDF Acquisition with a Single Mobile Phone Image},
  author = {Zhengqin Li and Kalyan Sunkavalli and Manmohan Chandraker},
  journal= {arXiv preprint arXiv:1804.05790},
  year   = {2018}
}

Comments

submitted to European Conference on Computer Vision