Physics-Guided ISO-Dependent Sensor Noise Modeling for Extreme Low-Light Photography

CVPR 2023  ยท  Yue Cao, Ming Liu, Shuai Liu, Xiaotao Wang, Lei Lei, WangMeng Zuo ยท

Although deep neural networks have achieved astonishing performance in many vision tasks, existing learning-based methods are far inferior to the physical model-based solutions in extreme low-light sensor noise modeling. To tap the potential of learning-based sensor noise modeling, we investigate the noise formation in a typical imaging process and propose a novel physics-guided ISO-dependent sensor noise modeling approach. Specifically, we build a normalizing flow-based framework to represent the complex noise characteristics of CMOS camera sensors. Each component of the noise model is dedicated to a particular kind of noise under the guidance of physical models. Moreover, we take into consideration of the ISO dependence in the noise model, which is not completely considered by the existing learning-based methods. For training the proposed noise model, a new dataset is further collected with paired noisy-clean images, as well as flat-field and bias frames covering a wide range of ISO settings. Compared to existing methods, the proposed noise model benefits from the flexible structure and accurate modeling capabilities, which can help achieve better denoising performance in extreme low-light scenes. The source code and collected dataset will be publicly available.

PDF Abstract
No code implementations yet. Submit your code now

Datasets


Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Benchmark
Image Denoising ELD SonyA7S2 x100 LLD* PSNR (Raw) 46.74 # 1
SSIM (Raw) 0.986 # 1
Image Denoising ELD SonyA7S2 x100 LLD PSNR (Raw) 45.61 # 4
SSIM (Raw) 0.977 # 4
Image Denoising ELD SonyA7S2 x200 LLD* PSNR (Raw) 44.95 # 1
SSIM (Raw) 0.977 # 1
Image Denoising ELD SonyA7S2 x200 LLD PSNR (Raw) 43.84 # 4
SSIM (Raw) 0.959 # 5
Image Denoising SID SonyA7S2 x250 LLD PSNR (Raw) 39.76 # 4
SSIM (Raw) 0.933 # 5
Image Denoising SID SonyA7S2 x250 LLD* PSNR (Raw) 41.02 # 1
SSIM (Raw) 0.948 # 1
Image Denoising SID x100 LLD* PSNR (Raw) 43.36 # 1
SSIM 0.961 # 2
Image Denoising SID x100 LLD PSNR (Raw) 42.10 # 4
SSIM 0.955 # 4
Image Denoising SID x300 LLD* PSNR (Raw) 37.80 # 1
SSIM 0.935 # 1
Image Denoising SID x300 LLD PSNR (Raw) 36.76 # 5
SSIM 0.912 # 5

Methods


No methods listed for this paper. Add relevant methods here