FGA-NN: Film Grain Analysis Neural Network

TL;DR

This paper presents FGA-NN, a novel neural network-based method for analyzing and modeling film grain to enable efficient compression and high-quality synthesis, preserving artistic intent in cinematographic content.

Contribution

FGA-NN is the first learning-based approach to analyze film grain parameters compatible with conventional synthesis methods.

Findings

FGA-NN achieves superior analysis accuracy and synthesis quality.

The method demonstrates robustness across different content types.

FGA-NN offers an efficient balance between complexity and performance.

Abstract

Film grain, once a by-product of analog film, is now present in most cinematographic content for aesthetic reasons. However, when such content is compressed at medium to low bitrates, film grain is lost due to its random nature. To preserve artistic intent while compressing efficiently, film grain is analyzed and modeled before encoding and synthesized after decoding. This paper introduces FGA-NN, the first learning-based film grain analysis method to estimate conventional film grain parameters compatible with conventional synthesis. Quantitative and qualitative results demonstrate FGA-NN's superior balance between analysis accuracy and synthesis complexity, along with its robustness and applicability.