Recent advances in deep learning have shown excellent performance in various scene
understanding tasks. However, in some complex environments or under challenging …

Polarization imaging can retrieve inaccurate objects' 3D shapes with fine textures, whereas
coarse but accurate depths can be provided by binocular stereo vision. To take full …

Segmentation of transparent objects is a hard, open problem in computer vision.
Transparent objects lack texture of their own, adopting instead the texture of scene …

We present a new data-driven approach with physics-based priors to scene-level normal
estimation from a single polarization image. Existing shape from polarization (SfP) works …

In the field of industrial metrology, there is a rising need for 3D information at a very high
resolution for micro-measurements and quality control of transparent objects such as glass …

Stereo depth estimation usually struggles to deal with textureless scenes for both traditional
and learning-based methods due to the inherent dependence on image correspondence …

This paper makes a first attempt to bring the Shape from Polarization (SfP) problem to the
realm of deep learning. The previous state-of-the-art methods for SfP have been purely …

State-of-the-art solutions for Shape-from-Polarization (SfP) suffer from a speed-resolution
tradeoff: they either sacrifice the number of polarization angles measured or necessitate …

Ellipsometry techniques allow to measure polarization information of materials, requiring
precise rotations of optical components with different configurations of lights and sensors …

Highly reflective surfaces are notorious in the field of depth sensing and three-dimensional
(3D) imaging because they can cause severe errors in perception of the depth. Despite …