Reflection Separation via Multi-bounce Polarization State Tracing

Rui Li, Simeng Qiu, Guangming Zang, Wolfgang Heidrich

Research output: Chapter in Book/Report/Conference proceedingConference contribution


Reflection 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 ray-tracing 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 ray-tracing 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.
Original languageEnglish (US)
Title of host publicationComputer Vision – ECCV 2020
PublisherSpringer International Publishing
Number of pages16
ISBN (Print)9783030586003
StatePublished - Nov 28 2020

ASJC Scopus subject areas

  • Theoretical Computer Science
  • Computer Science(all)

Fingerprint Dive into the research topics of 'Reflection Separation via Multi-bounce Polarization State Tracing'. Together they form a unique fingerprint.

Cite this