针对神经网络图像压缩的视觉伪影，提出检测与量化方法并构建验证数据集。
JPEG AI Image Compression Visual Artifacts: Detection Methods and Dataset
- 分离检测三类伪影：纹理边界退化、颜色变化、文字扭曲
- 从35万张图中筛选出4.6万例经人工评估验证的伪影样本
- 适合测试神经编码器缺陷、优化压缩算法的研究者使用
近年来学习型图像压缩方法显著进步，已开始超越传统编码器。然而，基于神经网络的方法在部分图像中会意外引入视觉伪影。为此，我们提出方法以分别检测三类伪影（纹理与边界退化、颜色变化、文字扭曲），定位受影响区域，并量化伪影强度。仅考虑那些因神经压缩导致失真、但传统编码器在相近码率下可成功恢复的区域。我们利用该方法对JPEG AI验证模型在HM-18.0（H.265参考软件）下的表现进行评估，处理了约35万张来自Open Images的数据集图像，采用不同压缩质量参数，最终获得46,440个经众包主观评估验证的伪影样本。所提出的检测方法与数据集对测试神经网络图像编码器、发现其缺陷及提升性能具有重要价值。相关源代码与数据集已公开。
原文摘要 · Abstract (English)
Learning-based image compression methods have improved in recent years and started to outperform traditional codecs. However, neural-network approaches can unexpectedly introduce visual artifacts in some images. We therefore propose methods to separately detect three types of artifacts (texture and boundary degradation, color change, and text corruption), to localize the affected regions, and to quantify the artifact strength. We consider only those regions that exhibit distortion due solely to the neural compression but that a traditional codec recovers successfully at a comparable bitrate. We employed our methods to collect artifacts for the JPEG AI verification model with respect to HM-18.0, the H.265 reference software. We processed about 350,000 unique images from the Open Images dataset using different compression-quality parameters; the result is a dataset of 46,440 artifacts validated through crowd-sourced subjective assessment. Our proposed dataset and methods are valuable for testing neural-network-based image codecs, identifying bugs in these codecs, and enhancing their performance. We make source code of the methods and the dataset publicly available.
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。