Two-shot Spatially-varying BRDF and Shape Estimation

Overview of the network architecture The proposed cascaded network architectures.


Capturing the shape and spatially-varying appearance (SVBRDF) of an object from images is a challenging task that has applications in both computer vision and graphics. Traditional optimization-based approaches often need a large number of images taken from multiple views in a controlled environment. Newer deep learning-based approaches require only a few input images, but the reconstruction quality is not on par with optimization techniques. We propose a novel deep learning architecture with a stage-wise estimation of shape and SVBRDF. The previous predictions guide each estimation, and a joint refinement network later refines both SVBRDF and shape. We follow a practical mobile image capture setting and use unaligned two-shot flash and no-flash images as input. Both our two-shot image capture and network inference can run on mobile hardware. We also create a large-scale synthetic training dataset with domain-randomized geometry and realistic materials. Extensive experiments on both synthetic and real-world datasets show that our network trained on a synthetic dataset can generalize well to real-world images. Comparisons with recent approaches demonstrate the superior performance of the proposed approach.

In IEEE Conference on Computer Vision and Pattern Recognition


Click the images for an interactive 3D visualization.

Aksoy et al. - A Dataset of Flash and Ambient Illumination Pairs from the Crowd

Real-world Examples
Synthetic Examples

This material is posted here with permission of the IEEE. Internal or personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution must be obtained from the IEEE by writing to

Mark Boss
Mark Boss
Ph.D. Student

I’m a Ph.D. student at the University of Tübingen with research interests in the intersection of machine learning and computer graphics.