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.
Abstract (translated)
胶片颗粒，过去是模拟胶片的副产品，现在由于美学原因出现在大多数电影内容中。然而，在以中低比特率压缩这种内容时，随机性质的胶片颗粒会丢失。为了在高效压缩的同时保留艺术意图，需要先对胶片颗粒进行分析和建模，然后再编码和解码过程中重新合成。本文介绍了FGA-NN，这是首个基于学习的方法，用于估计与传统合成兼容的传统胶片颗粒参数。定量和定性的结果表明，FGA-NN在分析准确性和合成复杂性之间具有优越的平衡，并且表现出其鲁棒性和适用性。
URL
https://arxiv.org/abs/2506.14350
