SSGP: Sparse Spatial Guided Propagation for Robust and Generic Interpolation

TL;DR

This paper introduces SSGP, a versatile interpolation method that leverages sparse spatial guidance to improve robustness, accuracy, and speed across various computer vision tasks like optical flow and depth completion.

Contribution

The paper presents a novel generic architecture, SSGP, that extends depth completion ideas to multiple interpolation problems, outperforming specialized algorithms.

Findings

SSGP improves robustness over existing methods

SSGP enhances accuracy in interpolation tasks

SSGP offers faster processing times

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.