arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2609.21169eess.IVcs.CV

自适应色彩分级

Adaptive Color Grading

Trevor D. Canham, Abhijith Punnappurath, Michael S. Brown

首次发表
浏览论文内容

中文总结 AI 辅助

本文开发开源色彩分级工具并标注视频帧数据集,发现K近邻预测色调阈值优于端到端方法,证明聚焦核心参数建模创意风格化的有效性。

中文摘要 AI 辅助

对色调区域(如阴影、高光)进行独立控制对于画家、摄影师和电影摄影师来说至关重要,这能使二维图像栩栩如生。在图像处理软件中,这一需求最直接地通过色彩分级模块来实现,该模块使用强度阈值来分割不同的光照区域以进行局部调整。在这项工作中,我们开发了一个开源色彩分级工具,并利用它标注了一个大型视频帧数据集,其中包含色调区域阈值。利用这些阈值,我们基于从业者的传统经验和机器学习两种策略进行了建模实验。结果表明,K近邻是一种有效的预测策略,其性能优于最先进的端到端图像增强方法。这一结果证明了在建模创意风格化过程时,专注于一组紧凑的核心参数是有益的。我们的自适应色彩分级界面和数据可在以下网址获取:https URL。

英文摘要

Independent control of tonescale regions (e.g., shadows, highlights) is essential for painters, photographers and cinematographers to bring 2D images to life. In image manipulation software this is most directly addressed by color grading modules, which use intensity thresholds to segment distinct illumination regions for local manipulation. In this work we develop an open source color grading tool and use it to annotate a large dataset of video frames with tonescale region thresholds. Using these thresholds we conduct modeling experiments with strategies based on both practitioners' conventional wisdom and machine learning. Results show that K-nearest neighbors is an effective prediction strategy, outperforming state-of-the-art end-to-end methods for image enhancement. This outcome demonstrates the benefit of focusing on a compact set of core parameters when modeling creative stylization processes. Our adaptive color grading interface and data are available at https://github.com/SamsungLabs/adaptive-color-grading.

发表机构

  • Samsung AI Center-Toronto(三星多伦多人工智能中心)
  • Samsung Electronics(三星电子)
  • York University(约克大学)

机构由 AI 辅助整理,请以论文原文为准。

补充信息

↑