用AI分析胶片颗粒，压缩时保留艺术效果。
FGA-NN: Film Grain Analysis Neural Network
- 基于学习的方法分析胶片颗粒参数，兼容传统合成技术。
- 在压缩后能高保真还原颗粒，且计算复杂度低。
- 适合影视制作与视频压缩领域使用。
胶片颗粒曾是模拟胶片的副产物，如今多用于电影内容的艺术表达。然而，在中低码率压缩时，由于其随机性，胶片颗粒容易丢失。为在高效压缩的同时保留艺术意图，本文在编码前对胶片颗粒进行分析建模，并在解码后重建。提出 FGA-NN，首个基于学习的胶片颗粒分析方法，可估计与传统合成兼容的胶片颗粒参数。定量与定性结果表明，FGA-NN 在分析精度与合成复杂度之间具有更优平衡，具备强鲁棒性与实际应用价值。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。