Trainable Nonlinear Reaction Diffusion: A Flexible Framework for Fast and Effective Image Restoration

TL;DR

This paper introduces TNRD, a trainable nonlinear reaction diffusion framework that learns parameters from data for fast, effective image restoration across tasks like denoising, super-resolution, and deblocking, achieving state-of-the-art results.

Contribution

It proposes a novel, fully trainable nonlinear diffusion model with time-dependent parameters, optimized via a loss function, for versatile and efficient image restoration.

Findings

Achieves top performance on standard datasets for denoising, super-resolution, and deblocking.

Models are computationally efficient, requiring few diffusion steps and suitable for GPU acceleration.

Demonstrates the effectiveness of learning all parameters simultaneously in diffusion models.

Abstract

Image restoration is a long-standing problem in low-level computer vision with many interesting applications. We describe a flexible learning framework based on the concept of nonlinear reaction diffusion models for various image restoration problems. By embodying recent improvements in nonlinear diffusion models, we propose a dynamic nonlinear reaction diffusion model with time-dependent parameters (\ie, linear filters and influence functions). In contrast to previous nonlinear diffusion models, all the parameters, including the filters and the influence functions, are simultaneously learned from training data through a loss based approach. We call this approach TNRD -- \textit{Trainable Nonlinear Reaction Diffusion}. The TNRD approach is applicable for a variety of image restoration tasks by incorporating appropriate reaction force. We demonstrate its capabilities with three representative applications, Gaussian image denoising, single image super resolution and JPEG deblocking. Experiments show that our trained nonlinear diffusion models largely benefit from the training of the parameters and finally lead to the best reported performance on common test datasets for the tested applications. Our trained models preserve the structural simplicity of diffusion models and take only a small number of diffusion steps, thus are highly efficient. Moreover, they are also well-suited for parallel computation on GPUs, which makes the inference procedure extremely fast.