SSGP: Sparse Spatial Guided Propagation for Robust and Generic Interpolation

Abstract

Interpolation of sparse pixel information towards a dense target resolution finds its application across multiple disciplines in computer vision. State-of-the-art interpolation of motion fields applies model-based interpolation that makes use of edge information extracted from the target image. For depth completion, data-driven learning approaches are widespread. Our work is inspired by latest trends in depth completion that tackle the problem of dense guidance for sparse information. We extend these ideas and create a generic cross-domain architecture that can be applied for a multitude of interpolation problems like optical flow, scene flow, or depth completion. In our experiments, we show that our proposed concept of Sparse Spatial Guided Propagation (SSGP) achieves improvements to robustness, accuracy, or speed compared to specialized algorithms.

Deep Learning based Monocular Depth Prediction: Datasets, Methods and Applications

“…Then the scaffolding is refined along with image through skip-connections in multi-scale manner in refinement network. Schuster et al[160] design a sparse spatial guided propagation method. They predict two affinity matrix from multi-scale information of the RGB images for each scale of the sparse depth map.…”