YeTI：仅需两张噪声图像即可生成真实世界的sRGB噪声
YeTI: You Only Need Two Noisy Images for Real-World sRGB Noise Generation
浏览论文内容
中文总结 AI 辅助
针对真实世界sRGB图像去噪难题，提出YeTI框架，仅从同一场景两张噪声图像学习，利用重构自编码器和条件扩散Transformer分离场景与噪声特征，生成逼真噪声，经实验验证其有效性及在下游去噪任务中的实用价值。
中文摘要 AI 辅助
由于传感器噪声的非线性特性以及获取对齐的干净-噪声图像对的困难，真实世界的sRGB图像去噪仍然具有挑战性。有监督的去噪器往往过度拟合有限的配对数据集，而自监督方法仍依赖于足够多样的噪声观测。我们提出YeTI，一个仅从同一场景的两张噪声观测中学习的真实世界sRGB噪声生成框架。它使用重构自编码器分离场景结构和噪声特征，并用基于一致性目标训练的单步条件扩散Transformer对潜在噪声分布进行建模。实验证明YeTI在真实世界基准测试中的有效性，还展示了用其合成图像训练的去噪器在下游去噪任务中的强大性能。
英文摘要
Real-world sRGB image denoising remains challenging due to the nonlinear characteristics of sensor noise and the difficulty of acquiring aligned clean-noisy image pairs. Supervised denoisers often overfit to limited paired datasets, while self-supervised methods still depend on sufficiently diverse noisy observations. These limitations motivate scalable noise synthesis methods that can model real-world noise without clean ground truth or camera metadata. We propose YeTI, a real-world sRGB noise generation framework that learns from only two noisy observations of the same scene. YeTI uses a Reconstruction Autoencoder to disentangle scene structure and noise characteristics, and models the latent noise distribution with a one-step Conditional Diffusion Transformer trained using consistency objectives. Given a single noisy input at inference time, YeTI generates realistic, signal-dependent noise while preserving the underlying scene content. Extensive experiments demonstrate the effectiveness of YeTI across real-world benchmarks. We evaluate noise generation on SIDD and further assess generalization on SIDD+, MAI2021, and SID, covering smartphone and diverse consumer-camera sensors. Downstream denoising results on DND further show that denoisers trained with YeTI-synthesized images achieve strong real-world performance, highlighting the practical value of clean-image-free and metadata-free noise generation.
发表机构
- Department of Computer Science, Hanyang University（汉阳大学计算机科学系）
- Mobile Experience (MX) Division, Samsung Electronics（三星电子移动体验部门）
机构由 AI 辅助整理，请以论文原文为准。
