High-Quality Correspondence and Segmentation Estimation for Dual-Lens Smart-Phone Portraits
This addresses the challenge of improving image processing for dual-lens smartphones, but it is incremental as it builds on existing CRF methods.
The paper tackled the joint problems of estimating correspondence between two images and extracting foreground objects in dual-lens smartphone portraits by proposing a joint fully connected conditional random field framework, achieving promising results on 2,000 new image pairs.
Estimating correspondence between two images and extracting the foreground object are two challenges in computer vision. With dual-lens smart phones, such as iPhone 7Plus and Huawei P9, coming into the market, two images of slightly different views provide us new information to unify the two topics. We propose a joint method to tackle them simultaneously via a joint fully connected conditional random field (CRF) framework. The regional correspondence is used to handle textureless regions in matching and make our CRF system computationally efficient. Our method is evaluated over 2,000 new image pairs, and produces promising results on challenging portrait images.