Show simple item record

dc.contributor.authorLi, Rui
dc.contributor.authorQiu, Simeng
dc.contributor.authorZang, Guangming
dc.contributor.authorHeidrich, Wolfgang
dc.date.accessioned2020-09-09T14:15:06Z
dc.date.available2020-09-09T14:15:06Z
dc.date.issued2020-08-23
dc.identifier.urihttp://hdl.handle.net/10754/665049
dc.description.abstractReflection removal from photographs is an important task in computational photography, but also for computer vision tasks that involve imaging through windows and similar settings. Traditionally, the problem is approached as a single reflection removal problem under very controlled scenarios. In this paper we aim to generalize the reflection removal to real-world scenarios with more complicated light interactions. To this end, we propose a simple yet efficient learning framework for supervised image reflection separation with a polarization-guided raytracing model and loss function design. Instead of a conventional image sensor, we use a polarization sensor that instantaneously captures four linearly polarized photos of the scene in the same image. Through a combination of a new polarization-guided image formation model and a novel supervised learning framework for the interpretation of a raytracing image formation model, a general method is obtained to tackle general image reflection removal problems. We demonstrate our method with extensive experiments on both real and synthetic data and demonstrate the unprecedented quality of image reconstructions.
dc.relation.urlhttps://vccimaging.org/Publications/Rui2020Reflection/
dc.titleDataset for Reflection Separation via Multi-bounce Polarization State Tracing
dc.typeDataset
dc.contributor.departmentComputational Imaging Group
dc.contributor.departmentComputer Science Program
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
dc.contributor.departmentElectrical Engineering
dc.contributor.departmentElectrical Engineering Program
dc.contributor.departmentVisual Computing Center (VCC)
kaust.personLi, Rui
kaust.personQiu, Simeng
kaust.personZang, Guangming
kaust.personHeidrich, Wolfgang
dc.relation.issupplementtoDOI:10.1007/978-3-030-58601-0_46
refterms.dateFOA2020-08-23T00:00:00Z
display.relations<b>Is Supplement To:</b><br/> <ul><li><i>[Conference Paper]</i> <br/> Li, R., Qiu, S., Zang, G., & Heidrich, W. (2020). Reflection Separation via Multi-bounce Polarization State Tracing. Lecture Notes in Computer Science, 781–796. doi:10.1007/978-3-030-58601-0_46. DOI: <a href="https://doi.org/10.1007/978-3-030-58601-0_46" >10.1007/978-3-030-58601-0_46</a> Handle: <a href="http://hdl.handle.net/10754/667925" >10754/667925</a></a></li></ul>


Files in this item

Thumbnail
Name:
dataset.zip
Size:
2.033Gb
Format:
application/zip
Description:
Polarization image dataset

This item appears in the following Collection(s)

Show simple item record