A Lightweight Approach for On-the-Fly Reflectance Estimation
Authors:
- Kihwan KimKKKihwan Kim
- Jinwei GuJGJinwei Gu
- Stephen TyreeSTStephen Tyree
- Pavlo MolchanovPMPavlo Molchanov
- Matthias NieBnerMNMatthias NieBner
- Jan KautzJKJan Kautz
- 1 October 2017
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 33, 20-28
Abstract
Estimating surface reflectance (BRDF) is one key component for complete 3D scene capture, with wide applications in virtual reality, augmented reality, and human computer interaction. Prior work is either limited to controlled environments (e.g., gonioreflectometers, light stages, or multi-camera domes), or requires the joint optimization of shape, illumination, and reflectance, which is often computationally too expensive (e.g., hours of running time) for real-time applications. Moreover, most prior work requires HDR images as input which further complicates the capture process. In this paper, we propose a lightweight approach for surface reflectance estimation directly from 8-bit RGB images in real-time, which can be easily plugged into any 3D scanning-and-fusion system with a commodity RGBD sensor. Our method is learning-based, with an inference time of less than 90ms per scene and a model size of less than 340K bytes. We propose two novel network architectures, HemiCNN and Grouplet, to deal with the unstructured input data from multiple viewpoints under unknown illumination. We further design a loss function to resolve the color-constancy and scale ambiguity. In addition, we have created a large synthetic dataset, SynBRDF, which comprises a total of 500K RGBD images rendered with a physically-based ray tracer under a variety of natural illumination, covering 5000 materials and 5000 shapes. SynBRDF is the first large-scale benchmark dataset for reflectance estimation. Experiments on both synthetic data and real data show that the proposed method effectively recovers surface reflectance, and outperforms prior work for reflectance estimation in uncontrolled environments.Keywords
All Related Versions
This publication has 27 references indexed in Scilit:
- Shape, Illumination, and Reflectance from ShadingIEEE Transactions on Pattern Analysis and Machine Intelligence, 2014
- Appearance-from-motionACM Transactions on Graphics, 2014
- Intrinsic images in the wildACM Transactions on Graphics, 2014
- OpenSurfacesACM Transactions on Graphics, 2013
- Reflectance and Natural Illumination from a Single Image2012
- Blind Reflectometry2010
- Toward a perceptual space for glossACM Transactions on Graphics, 2009
- Real-world illumination and the perception of surface reflectance propertiesJournal of Vision, 2003
- Image-Based Reconstruction of Spatially Varying Materials2001
- The rendering equationACM SIGGRAPH Computer Graphics, 1986