Image Inpainting Based On Coherence Transport With Adapted Distance Functions

TL;DR

This paper extends a coherence transport-based image inpainting method by employing adaptive distance functions for serialization, improving results in challenging inpainting scenarios.

Contribution

It introduces the use of alternative distance functions for serialization in coherence transport inpainting, addressing limitations of the boundary distance approach.

Findings

Adaptive distance functions improve inpainting quality in difficult cases

The method effectively resolves serialization issues in coherence transport

Enhanced inpainting results demonstrate the method's robustness

Abstract

We discuss an extension of our method Image Inpainting Based on Coherence Transport. For the latter method the pixels of the inpainting domain have to be serialized into an ordered list. Up till now, to induce the serialization we have used the distance to boundary map. But there are inpainting problems where the distance to boundary serialization causes unsatisfactory inpainting results. In the present work we demonstrate cases where we can resolve the difficulties by employing other distance functions which better suit the problem at hand.