用单向多映射实现低数据量图像处理，提升画质与个性化
SemiISP/SemiIE: Semi-Supervised Image Signal Processor and Image Enhancement Leveraging One-to-Many Mapping sRGB-to-RAW
- 基于sRGB-to-RAW重建生成伪RAW数据，支持半监督学习
- 新方法显著提升图像信号处理任务的画质表现
- 适合小样本定制化图像增强，如个人偏好或特定场景
基于深度神经网络的方法在图像信号处理（ISP）和图像增强（IE）任务中已取得成功，但这些任务训练数据的构建成本远高于其他任务，难以建立大规模数据集。此外，以极少量数据实现个性化ISP与IE可开辟新价值流，因不同用户对图像质量偏好各异。尽管半监督学习在此类场景中具有潜力，但尚未被广泛采用。本文提出一种基于伪RAW图像重建（sRGB-to-RAW）的半监督学习框架，用于ISP与IE。现有sRGB-to-RAW方法虽能生成伪RAW数据并提升目标检测等高层视觉任务性能，但其图像质量仍不足以满足需要精确画质定义的ISP与IE任务。为此，本文提出一种更高质量的sRGB-to-RAW方法。结合该方法的半监督学习在多个模型与数据集上均有效提升了图像质量。
原文摘要 · Abstract (English)
DNN-based methods have been successful in Image Signal Processor (ISP) and image enhancement (IE) tasks. However, the cost of creating training data for these tasks is considerably higher than for other tasks, making it difficult to prepare large-scale datasets. Also, creating personalized ISP and IE with minimal training data can lead to new value streams since preferred image quality varies depending on the person and use case. While semi-supervised learning could be a potential solution in such cases, it has rarely been utilized for these tasks. In this paper, we realize semi-supervised learning for ISP and IE leveraging a RAW image reconstruction (sRGB-to-RAW) method. Although existing sRGB-to-RAW methods can generate pseudo-RAW image datasets that improve the accuracy of RAW-based high-level computer vision tasks such as object detection, their quality is not sufficient for ISP and IE tasks that require precise image quality definition. Therefore, we also propose a sRGB-to-RAW method that can improve the image quality of these tasks. The proposed semi-supervised learning with the proposed sRGB-to-RAW method successfully improves the image quality of various models on various datasets.
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。