SIRA - An efficient method for retrieving stereo images from anaglyphs

作者：

Highlights：

• Time series can be applied to anaglyph reversion enabling fast matching algorithms.

• Proposed SIRA’s method consumes 26 times less computational resources, on average.

• SIRA allows for anaglyph visualization independency and viewing of legacy anaglyphs.

• SIRA introduces a new approach to find anaglyphic/stereo correspondences.

• SIRA presents a novel pixel descriptor which deals anaglyphic photometric differences.

摘要

•Time series can be applied to anaglyph reversion enabling fast matching algorithms.•Proposed SIRA’s method consumes 26 times less computational resources, on average.•SIRA allows for anaglyph visualization independency and viewing of legacy anaglyphs.•SIRA introduces a new approach to find anaglyphic/stereo correspondences.•SIRA presents a novel pixel descriptor which deals anaglyphic photometric differences.

论文关键词：Anaglyph reversion,Time series,Stereo images,Signal processing

论文评审过程：Received 16 July 2019, Revised 2 December 2019, Accepted 16 April 2020, Available online 22 April 2020, Version of Record 27 April 2020.

论文官网地址：https://doi.org/10.1016/j.image.2020.115866