Real-time Image Smoothing via Iterative Least Squares

TL;DR

This paper introduces an efficient iterative least squares method for real-time, edge-preserving image smoothing that balances high quality with low computational cost, suitable for GPU acceleration.

Contribution

The paper presents a novel global optimization approach, ILS, enabling high-quality image smoothing with significantly reduced computational complexity and high parallelizability.

Findings

Produces high-quality smoothing with minimal artifacts

Achieves real-time processing at 20fps for 1080p color images on GPU

Flexible method adaptable to various smoothing applications

Abstract

Edge-preserving image smoothing is a fundamental procedure for many computer vision and graphic applications. There is a tradeoff between the smoothing quality and the processing speed: the high smoothing quality usually requires a high computational cost which leads to the low processing speed. In this paper, we propose a new global optimization based method, named iterative least squares (ILS), for efficient edge-preserving image smoothing. Our approach can produce high-quality results but at a much lower computational cost. Comprehensive experiments demonstrate that the propose method can produce results with little visible artifacts. Moreover, the computation of ILS can be highly parallel, which can be easily accelerated through either multi-thread computing or the GPU hardware. With the acceleration of a GTX 1080 GPU, it is able to process images of 1080p resolution ($1920\times1080$) at the rate of 20fps for color images and 47fps for gray images. In addition, the ILS is flexible and can be modified to handle more applications that require different smoothing properties. Experimental results of several applications show the effectiveness and efficiency of the proposed method. The code is available at \url{https://github.com/wliusjtu/Real-time-Image-Smoothing-via-Iterative-Least-Squares}