Depth from a Light Field Image with Learning-Based Matching Costs
Depth from a Light Field Image with Learning-Based Matching Costs is a scholarly work by Hae-Gon Jeon, Yu-Wing Tai, and In So Kweon, published in 2018 in ''IEEE Transactions on Pattern Analysis and Machine Intelligence''. The main subjects of the publication include computer science, artificial intelligence, autofocus, software pipeline, digital image correlation, light field, semiconductor device reliability, consistency, computer vision, measure, vignetting, field, benchmark, and stereopsis. The authors introduce a pipeline that automatically determines the best configuration for photo-consistency measure, which leads to the most reliable depth label from the light field.