Abstract
Poster presented at AI4CC at CVPR 2022 and BMVA Symposium 2022, for the paper "SaiNet: Stereo aware inpainting behind objects with generative networks" (https://doi.org/10.48550/arXiv.2205.07014). In this work, we present an end-to-end network for stereo-consistent image inpainting with the objective of inpainting large missing regions behind objects. The proposed model consists of an edge-guided UNet-like network using Partial Convolutions. We enforce multi-view stereo consistency by introducing a disparity loss. More importantly, we develop a training scheme where the model is learned from realistic stereo masks representing object occlusions, instead of the more common random masks. The technique is trained in a supervised way. Our evaluation shows competitive results compared to previous state-of-the-art techniques.