YeTI: You Only Need Two Noisy Images for Real-World sRGB Noise Generation

• URL: http://arxiv.org/abs/2607.09193v1
• Date: Fri, 10 Jul 2026 08:33:57 GMT
• Title: YeTI: You Only Need Two Noisy Images for Real-World sRGB Noise Generation
• Abstract summary: We propose YeTI, a real-world sRGB noise generation framework that learns from only two noisy observations of the same scene.<n>Given a single noisy input at inference time, YeTI generates realistic, signal-dependent noise while preserving the underlying scene content.
• Score: 11.302699058366388
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: 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.

Related papers

• sRGB Real Noise Modeling via Noise-Aware Sampling with Normalizing Flows [27.338824932164417]
  We introduce a new NF framework that allows us to both classify noise based on camera settings and generate various noisy images.<n>Our model demonstrates exceptional noise quality and leads in denoising performance on benchmark datasets.
  arXiv  Detail & Related papers  (2026-08-29T04:16:07Z)
• Diffusion-Based sRGB Real Noise Generation via Prompt-Driven Noise Representation Learning [16.09820578603153]
  We propose a novel framework called Prompt-Driven Noise Generation (PNG)<n>This model is capable of acquiring high-dimensional prompt features that capture the characteristics of real-world input noise.<n>By eliminating the dependency on explicit camera metadata, our approach significantly enhances the generalizability and applicability of noise synthesis.
  arXiv  Detail & Related papers  (2026-03-05T06:54:38Z)
• Realistic Noise Synthesis with Diffusion Models [44.404059914652194]
  Deep denoising models require extensive real-world training data, which is challenging to acquire.<n>We propose a novel Realistic Noise Synthesis Diffusor (RNSD) method using diffusion models to address these challenges.
  arXiv  Detail & Related papers  (2023-05-23T12:56:01Z)
• Advancing Unsupervised Low-light Image Enhancement: Noise Estimation, Illumination Interpolation, and Self-Regulation [55.07472635587852]
  Low-Light Image Enhancement (LLIE) techniques have made notable advancements in preserving image details and enhancing contrast. These approaches encounter persistent challenges in efficiently mitigating dynamic noise and accommodating diverse low-light scenarios. We first propose a method for estimating the noise level in low light images in a quick and accurate way. We then devise a Learnable Illumination Interpolator (LII) to satisfy general constraints between illumination and input.
  arXiv  Detail & Related papers  (2023-05-17T13:56:48Z)
• Noise2NoiseFlow: Realistic Camera Noise Modeling without Clean Images [35.29066692454865]
  This paper proposes a framework for training a noise model and a denoiser simultaneously. It relies on pairs of noisy images rather than noisy/clean paired image data. The trained denoiser is shown to significantly improve upon both supervised and weakly supervised baseline denoising approaches.
  arXiv  Detail & Related papers  (2022-06-02T15:31:40Z)
• Learning to Generate Realistic Noisy Images via Pixel-level Noise-aware Adversarial Training [50.018580462619425]
  We propose a novel framework, namely Pixel-level Noise-aware Generative Adrial Network (PNGAN) PNGAN employs a pre-trained real denoiser to map the fake and real noisy images into a nearly noise-free solution space. For better noise fitting, we present an efficient architecture Simple Multi-versa-scale Network (SMNet) as the generator.
  arXiv  Detail & Related papers  (2022-04-06T14:09:02Z)
• C2N: Practical Generative Noise Modeling for Real-World Denoising [53.96391787869974]
  We introduce a Clean-to-Noisy image generation framework, namely C2N, to imitate complex real-world noise without using paired examples. We construct the noise generator in C2N accordingly with each component of real-world noise characteristics to express a wide range of noise accurately.
  arXiv  Detail & Related papers  (2022-02-19T05:53:46Z)
• Rethinking Noise Synthesis and Modeling in Raw Denoising [75.55136662685341]
  We introduce a new perspective to synthesize noise by directly sampling from the sensor's real noise. It inherently generates accurate raw image noise for different camera sensors.
  arXiv  Detail & Related papers  (2021-10-10T10:45:24Z)
• Physics-based Noise Modeling for Extreme Low-light Photography [63.65570751728917]
  We study the noise statistics in the imaging pipeline of CMOS photosensors. We formulate a comprehensive noise model that can accurately characterize the real noise structures. Our noise model can be used to synthesize realistic training data for learning-based low-light denoising algorithms.
  arXiv  Detail & Related papers  (2021-08-04T16:36:29Z)
• Adaptive noise imitation for image denoising [58.21456707617451]
  We develop a new textbfadaptive noise imitation (ADANI) algorithm that can synthesize noisy data from naturally noisy images. To produce realistic noise, a noise generator takes unpaired noisy/clean images as input, where the noisy image is a guide for noise generation. Coupling the noisy data output from ADANI with the corresponding ground-truth, a denoising CNN is then trained in a fully-supervised manner.
  arXiv  Detail & Related papers  (2020-11-30T02:49:36Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.