Why Low-Light Cameras Go Color Blind: Removing Color Bias in Raw Denoising

• URL: http://arxiv.org/abs/2607.11090v1
• Date: Mon, 13 Jul 2026 04:58:14 GMT
• Title: Why Low-Light Cameras Go Color Blind: Removing Color Bias in Raw Denoising
• Abstract summary: We propose a camera-agnostic, calibration-free paradigm for low-light raw denoising.<n>We identify that color bias from black-level error is a primary source of performance degradation.<n>We evaluate our approach across the ELD, SID, and LRID datasets, demonstrating superior performance among blind denoisers.
• Score: 42.231128978265005
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Raw images inherently suffer from noise due to the stochastic nature of light and sensor hardware imperfections. As real photon counts fall, the ratio of this noise to the signal degrades; consequently, for low-light conditions, robust denoising is especially vital for high-quality results. While recent data-driven methods achieve strong performance, they typically rely on large-scale noisy-clean image pairs that are costly and difficult to collect. Alternatively, parametric noise models can generate synthetic training data, but this necessitates precise camera calibration, which is often impractical for unknown devices. In this work, we propose a camera-agnostic, calibration-free paradigm for low-light raw denoising. We identify that color bias from black-level error is a primary source of performance degradation and causes severe color shifts. To mitigate this, we introduce a bias estimator network that predicts the black-level error as a global feature of the noisy input. We evaluate our approach across the ELD, SID, and LRID datasets, demonstrating superior performance among blind denoisers, particularly in terms of color correction. In many cases, we are competitive with-or can even surpass-methods with stronger supervision. Furthermore, we reveal that the widely used SIDD dataset contains significant color bias in its ground-truth images, which yields unrealistic color reproduction in trained models. We introduce a new ground-truth extraction framework to resolve this issue and provide a benchmark of existing methods on the corrected dataset.

Related papers

• NIR-Assisted Image Denoising: A Selective Fusion Approach and A Real-World Benchmark Dataset [53.79524776100983]
  Leveraging near-infrared (NIR) images to assist visible RGB image denoising shows the potential to address this issue.<n>Existing works still struggle with taking advantage of NIR information effectively for real-world image denoising.<n>We propose an efficient Selective Fusion Module (SFM), which can be plug-and-played into the advanced denoising networks.
  arXiv  Detail & Related papers  (2024-04-12T14:54:26Z)
• Make Explicit Calibration Implicit: Calibrate Denoiser Instead of the Noise Model [83.9497193551511]
  We introduce Lighting Every Darkness (LED), which is effective regardless of the digital gain or the camera sensor. LED eliminates the need for explicit noise model calibration, instead utilizing an implicit fine-tuning process that allows quick deployment and requires minimal data. LED also allows researchers to focus more on deep learning advancements while still utilizing sensor engineering benefits.
  arXiv  Detail & Related papers  (2023-08-07T10:09:11Z)
• 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)
• Instance Segmentation in the Dark [43.85818645776587]
  We take a deep look at instance segmentation in the dark and introduce several techniques that substantially boost the low-light inference accuracy. We propose a novel learning method that relies on an adaptive weighted downsampling layer, a smooth-oriented convolutional block, and disturbance suppression learning. We capture a real-world low-light instance segmentation dataset comprising over two thousand paired low/normal-light images with instance-level pixel-wise annotations.
  arXiv  Detail & Related papers  (2023-04-27T16:02:29Z)
• Rawgment: Noise-Accounted RAW Augmentation Enables Recognition in a Wide Variety of Environments [1.0323063834827415]
  We propose a noise-accounted RAW image augmentation method for image recognition in challenging environments. In essence, color jitter and blur augmentation are applied to a RAW image before applying non-linear ISP, resulting in realistic intensity. We show that our proposed noise-accounted RAW augmentation method doubles the image recognition accuracy in challenging environments only with simple training data.
  arXiv  Detail & Related papers  (2022-10-28T10:33:45Z)
• Modeling sRGB Camera Noise with Normalizing Flows [35.29066692454865]
  We propose a new sRGB-domain noise model based on normalizing flows that is capable of learning the complex noise distribution found in sRGB images under various ISO levels. Our normalizing flows-based approach outperforms other models by a large margin in noise modeling and synthesis tasks.
  arXiv  Detail & Related papers  (2022-06-02T00:56:34Z)
• Low-light Image Enhancement via Breaking Down the Darkness [8.707025631892202]
  This paper presents a novel framework inspired by the divide-and-rule principle. We propose to convert an image from the RGB space into a luminance-chrominance one. An adjustable noise suppression network is designed to eliminate noise in the brightened luminance. The enhanced luminance further serves as guidance for the chrominance mapper to generate realistic colors.
  arXiv  Detail & Related papers  (2021-11-30T16:50:59Z)
• 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)
• CycleISP: Real Image Restoration via Improved Data Synthesis [166.17296369600774]
  We present a framework that models camera imaging pipeline in forward and reverse directions. By training a new image denoising network on realistic synthetic data, we achieve the state-of-the-art performance on real camera benchmark datasets.
  arXiv  Detail & Related papers  (2020-03-17T15:20:25Z)

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.