Deep Spectral Reflectance and Illuminant Estimation from Self-Interreflections
This addresses the challenge of accurate spectral estimation in computer vision for applications like material analysis, but it is incremental as it builds on existing interreflection and deep learning techniques.
The paper tackles the problem of estimating spectral reflectance and illuminant from a single RGB image using a CNN trained on simulated data from a physics-based interreflection model, showing it outperforms state-of-the-art learning-based approaches on simulated data and gives better results on real data compared to other interreflection-based methods.
In this work, we propose a CNN-based approach to estimate the spectral reflectance of a surface and the spectral power distribution of the light from a single RGB image of a V-shaped surface. Interreflections happening in a concave surface lead to gradients of RGB values over its area. These gradients carry a lot of information concerning the physical properties of the surface and the illuminant. Our network is trained with only simulated data constructed using a physics-based interreflection model. Coupling interreflection effects with deep learning helps to retrieve the spectral reflectance under an unknown light and to estimate the spectral power distribution of this light as well. In addition, it is more robust to the presence of image noise than the classical approaches. Our results show that the proposed approach outperforms the state of the art learning-based approaches on simulated data. In addition, it gives better results on real data compared to other interreflection-based approaches.