Abstract We present a novel method to synthesize novel view selfies from a mobile phone captured video. This is challenging…
Abstract Single-view depth estimation using CNNs trained from unlabelled videos has shown significant promise. However, the excellent results have mostly…
Notice: this post presents the NeurIPS version. Please see more information in our IJCV paper [pdf]. Abstract Recent work has…
Abstract Matching two images while estimating their relative geometry is a key step in many computer vision applications. For decades,…
Abstract This paper attempts to separate true correspondences from false ones at high speed. We term the proposed method…