Two-shot Spatially-varying BRDF and Shape Estimation
This addresses the challenge of efficient 3D capture for computer vision and graphics applications, offering a practical mobile solution, though it is incremental as it builds on existing deep learning approaches.
The paper tackles the problem of estimating shape and spatially-varying appearance (SVBRDF) from images, proposing a deep learning architecture that uses two-shot flash and no-flash images to achieve high-quality reconstructions comparable to optimization-based methods, with experiments showing superior performance on synthetic and real-world datasets.
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.