Deep Polarization Cues for Single-shot Shape and Subsurface Scattering Estimation
This work addresses a novel application of polarization for subsurface scattering estimation, which is incremental as it builds on prior polarization-based methods but targets a new domain.
The authors tackled the problem of jointly estimating shape and subsurface scattering parameters of translucent objects by using polarization cues, achieving superior performance over existing baselines on both synthetic and real data.
In this work, we propose a novel learning-based method to jointly estimate the shape and subsurface scattering (SSS) parameters of translucent objects by utilizing polarization cues. Although polarization cues have been used in various applications, such as shape from polarization (SfP), BRDF estimation, and reflection removal, their application in SSS estimation has not yet been explored. Our observations indicate that the SSS affects not only the light intensity but also the polarization signal. Hence, the polarization signal can provide additional cues for SSS estimation. We also introduce the first large-scale synthetic dataset of polarized translucent objects for training our model. Our method outperforms several baselines from the SfP and inverse rendering realms on both synthetic and real data, as demonstrated by qualitative and quantitative results.