Transparent Shape from a Single View Polarization Image
This work addresses a domain-specific challenge in computer vision for transparent object reconstruction, representing an incremental improvement over prior shape from polarization methods.
The paper tackles the problem of estimating transparent surface shape from a single polarization image, where existing methods struggle due to transmission interference, and proposes a learning-based approach that achieves superior accuracy as demonstrated in experiments.
This paper presents a learning-based method for transparent surface estimation from a single view polarization image. Existing shape from polarization(SfP) methods have the difficulty in estimating transparent shape since the inherent transmission interference heavily reduces the reliability of physics-based prior. To address this challenge, we propose the concept of physics-based prior, which is inspired by the characteristic that the transmission component in the polarization image has more noise than reflection. The confidence is used to determine the contribution of the interfered physics-based prior. Then, we build a network(TransSfP) with multi-branch architecture to avoid the destruction of relationships between different hierarchical inputs. To train and test our method, we construct a dataset for transparent shape from polarization with paired polarization images and ground-truth normal maps. Extensive experiments and comparisons demonstrate the superior accuracy of our method.