Regularised Diffusion-Shock Inpainting

TL;DR

The paper presents regularised diffusion-shock inpainting, combining diffusion and shock filtering to achieve sharp edge propagation and efficient filling, with reduced parameters and applicability to vector data.

Contribution

It introduces a regularised version of diffusion-shock inpainting that reduces parameters while maintaining quality and extends the method to vector-valued data.

Findings

Performance is comparable or superior to existing PDE-based inpainting methods.

The method effectively propagates edges with high sharpness and directional accuracy.

Regularisation enables parameter reduction without quality loss.

Abstract

We introduce regularised diffusion--shock (RDS) inpainting as a modification of diffusion--shock inpainting from our SSVM 2023 conference paper. RDS inpainting combines two carefully chosen components: homogeneous diffusion and coherence-enhancing shock filtering. It benefits from the complementary synergy of its building blocks: The shock term propagates edge data with perfect sharpness and directional accuracy over large distances due to its high degree of anisotropy. Homogeneous diffusion fills large areas efficiently. The second order equation underlying RDS inpainting inherits a maximum--minimum principle from its components, which is also fulfilled in the discrete case, in contrast to competing anisotropic methods. The regularisation addresses the largest drawback of the original model: It allows a drastic reduction in model parameters without any loss in quality. Furthermore, we extend RDS inpainting to vector-valued data. Our experiments show a performance that is comparable to or better than many inpainting methods based on partial differential equations and related integrodifferential models