PadmanabanVarma - Revision history

imported>Student2016: /* Quantitative Results */

2016-12-16T00:58:17Z

Quantitative Results

← Older revision		Revision as of 00:58, 16 December 2016
Line 75:		Line 75:

	=== Quantitative Results ===		=== Quantitative Results ===
	First, we looked at a numerical comparison of how the different methods we tried performed on images on the test set. The two metrics we used to perform this comparison were the peak signal to noise ratio (PSNR) and visual signal to noise ratio (VSNR) values. Note that PSNR compares two images while VSNR is set up to only look at the noise content of a single image. In our project, we looked at the difference in VSNR of the denoised and original clean image, which led to very small values. This can be interpreted as how much the VSNR improved after the denoising techniques were applied.		First, we looked at a numerical comparison of how the different methods we tried performed on images on the test set. The two metrics we used to perform this comparison were the peak signal to noise ratio (PSNR) and visual signal to noise ratio (VSNR) values. Note that PSNR compares two images while VSNR is set up to only look at the noise content of a single image. To account for this difference, in our project, we looked at the difference in VSNR of the denoised and original clean image, which led to very small values. This can be interpreted as how much the VSNR improved after the denoising techniques were applied.

	Note that the numbers are the averages across entire images in the test set, while the linear regression algorithm was performed over individual patches in the image. Higher PSNR corresponds to a lower MSE, which is what the machine learning algorithm was optimized for. Therefore, as expected, the linear regression performs the best in terms of high PSNR. Moreover, even in terms of VSNR improvement, the algorithms perform the same relative to each other as with PSNR. This means that even though we did not optimize for VSNR, our algorithm performs well even in terms of that metric.		Note that the numbers are the averages across entire images in the test set, while the linear regression algorithm was performed over individual patches in the image. Higher PSNR corresponds to a lower MSE, which is what the machine learning algorithm was optimized for. Therefore, as expected, the linear regression performs the best in terms of high PSNR. Moreover, even in terms of VSNR improvement, the algorithms perform the same relative to each other as with PSNR. This means that even though we did not optimize for VSNR, our algorithm performs well even in terms of that metric.

imported>Student2016: /* Quantitative Results */

2016-12-16T00:52:56Z

Quantitative Results

← Older revision		Revision as of 00:52, 16 December 2016
Line 75:		Line 75:

	=== Quantitative Results ===		=== Quantitative Results ===
	First ,we looked at a numerical comparison of how the different methods we tried performed on images on the test set. The two metrics we used to perform this comparison were the peak signal to noise ratio (PSNR) and visual signal to noise ratio (VSNR) values. Note that PSNR compares two images while VSNR is set up to only look at the noise content of a single image. For the conversion to Lab, the white point corresponds to that of the nighttime illuminant used when generating the dataset. The calculation for VSNR first applies a spatial low pass filter based on optics of the visual system and viewing distance (assumed to be 0.5 m from the screen), then converts the image to Lab. The VSNR is then calculated as the square root of the sum of the variances of each Lab color channel. In our project, we looked at the difference in VSNR of the denoised and original clean image, which led to very small values. This can be interpreted as how much the VSNR improved after the denoising techniques were applied.		First, we looked at a numerical comparison of how the different methods we tried performed on images on the test set. The two metrics we used to perform this comparison were the peak signal to noise ratio (PSNR) and visual signal to noise ratio (VSNR) values. Note that PSNR compares two images while VSNR is set up to only look at the noise content of a single image. In our project, we looked at the difference in VSNR of the denoised and original clean image, which led to very small values. This can be interpreted as how much the VSNR improved after the denoising techniques were applied.

	Note that the numbers are the averages across entire images in the test set, while the linear regression algorithm was performed over individual patches in the image. Higher PSNR corresponds to a lower MSE, which is what the machine learning algorithm was optimized for. Therefore, as expected, the linear regression performs the best in terms of high PSNR. Moreover, even in terms of VSNR improvement, the algorithms perform ~~relatively~~ the same to each other as with PSNR. This means that even though we did not optimize for VSNR, our algorithm performs well even in terms of that metric.		Note that the numbers are the averages across entire images in the test set, while the linear regression algorithm was performed over individual patches in the image. Higher PSNR corresponds to a lower MSE, which is what the machine learning algorithm was optimized for. Therefore, as expected, the linear regression performs the best in terms of high PSNR. Moreover, even in terms of VSNR improvement, the algorithms perform the same relative to each other as with PSNR. This means that even though we did not optimize for VSNR, our algorithm performs well even in terms of that metric.

	Another interesting observation is that the noisy image has more of a VSNR improvement than the denoised methods. This could mean that the artifacts the denoising methods introduce are more noticeable in the dark images than the noise, therefore leading to a better VSNR value for the noisy dark image than the denoised dark image.		Another interesting observation is that the noisy image has more of a VSNR improvement than the denoised methods. This could mean that the artifacts the denoising methods introduce are more noticeable in the dark images than the noise, therefore leading to a better VSNR value for the noisy dark image than the denoised dark image.

imported>Student2016 at 00:47, 16 December 2016

2016-12-16T00:47:28Z

← Older revision		Revision as of 00:47, 16 December 2016
Line 16:		Line 16:
	For the base images of our dataset, we start with the Berkeley Segmentation Data Set [https://www2.eecs.berkeley.edu/Research/Projects/CS/vision/grouping/resources.html]. This dataset consists mostly of outdoor images, but includes people, nature and monuments. This ensured that we had a good variety of images to learn from and the learned parameter was not biased towards certain colors or spatial frequencies.		For the base images of our dataset, we start with the Berkeley Segmentation Data Set [https://www2.eecs.berkeley.edu/Research/Projects/CS/vision/grouping/resources.html]. This dataset consists mostly of outdoor images, but includes people, nature and monuments. This ensured that we had a good variety of images to learn from and the learned parameter was not biased towards certain colors or spatial frequencies.

	We processed these daytime images to simulate nighttime low-light image captures of the same scenes. We do this using the Image Systems Engineering Toolbox. The data set does not provide camera information metadata, and so we convert the RGB image to a scene using our monitors (Apple LCD) as the display calibration SPDs. Then we use sceneAdjustIlluminant to normalize the illuminant in all the images to D65. Next, we set the peak photon count in the images to 10 photons because this visually created a reasonable amount of Poisson noise in testing. This is done using the sceneAdjustLuminance function and by querying sceneGet for the photon count. Next, we use scenePhotonNoise to manually change the photon counts in the scene according to the Poisson distribution, and we modify the scenePhotonNoise function to remove the Gaussian approximation. Lastly, when saving the scene as an RGB image using sceneSaveImage, we modify the code such that it produces a dark RGB output (instead of the default, which rescales the XYZ values so that the RGB image is bright). Earlier, we assumed that the daylight is ~~6500~K~~ blackbody radiation. We justify this choice because it matches a sunny day well, and images taken taken in outdoor night settings can look almost exactly like daylight photos with a long exposure, which then informs our decision to create low light images by simply scaling down the photon count.		We processed these daytime images to simulate nighttime low-light image captures of the same scenes. We do this using the Image Systems Engineering Toolbox. The data set does not provide camera information metadata, and so we convert the RGB image to a scene using our monitors (Apple LCD) as the display calibration SPDs. Then we use sceneAdjustIlluminant to normalize the illuminant in all the images to D65. Next, we set the peak photon count in the images to 10 photons because this visually created a reasonable amount of Poisson noise in testing. This is done using the sceneAdjustLuminance function and by querying sceneGet for the photon count. Next, we use scenePhotonNoise to manually change the photon counts in the scene according to the Poisson distribution, and we modify the scenePhotonNoise function to remove the Gaussian approximation. Lastly, when saving the scene as an RGB image using sceneSaveImage, we modify the code such that it produces a dark RGB output (instead of the default, which rescales the XYZ values so that the RGB image is bright). Earlier, we assumed that the daylight is 6500K blackbody radiation. We justify this choice because it matches a sunny day well, and images taken taken in outdoor night settings can look almost exactly like daylight photos with a long exposure, which then informs our decision to create low light images by simply scaling down the photon count.

	The above procedure details how to create the noisy training examples. The noise-free values corresponding to these will be generated in much the same way, but excluding the Poisson noise addition step. These noise-free values are used as ground truth for the linear regression algorithm.		The above procedure details how to create the noisy training examples. The noise-free values corresponding to these will be generated in much the same way, but excluding the Poisson noise addition step. These noise-free values are used as ground truth for the linear regression algorithm.
Line 75:		Line 75:

	=== Quantitative Results ===		=== Quantitative Results ===
	First ,we looked at a numerical comparison of how the different methods we tried performed on images on the test set. The two metrics we used to perform this comparison were the peak signal to noise ratio (PSNR) and visual signal to noise ratio (VSNR) values. Note that PSNR compares two images while VSNR is set up to only look at the noise content of a single image. For the conversion to ~~LAB~~, the white point corresponds to that of the nighttime illuminant used when generating the dataset. The calculation for VSNR first applies a spatial low pass filter based on optics of the visual system and viewing distance (assumed to be 0.5~m from the screen), then converts the image to ~~LAB~~. The VSNR is then calculated as the square root of the sum of the variances of each ~~LAB~~ color channel. In our project, we looked at the difference in VSNR of the denoised and original clean image, which led to very small values. This can be interpreted as how much the VSNR improved after the denoising techniques were applied.		First ,we looked at a numerical comparison of how the different methods we tried performed on images on the test set. The two metrics we used to perform this comparison were the peak signal to noise ratio (PSNR) and visual signal to noise ratio (VSNR) values. Note that PSNR compares two images while VSNR is set up to only look at the noise content of a single image. For the conversion to Lab, the white point corresponds to that of the nighttime illuminant used when generating the dataset. The calculation for VSNR first applies a spatial low pass filter based on optics of the visual system and viewing distance (assumed to be 0.5 m from the screen), then converts the image to Lab. The VSNR is then calculated as the square root of the sum of the variances of each Lab color channel. In our project, we looked at the difference in VSNR of the denoised and original clean image, which led to very small values. This can be interpreted as how much the VSNR improved after the denoising techniques were applied.

	Note that the numbers are the averages across entire images in the test set, while the linear regression algorithm was performed over individual patches in the image. Higher PSNR corresponds to a lower MSE, which is what the machine learning algorithm was optimized for. Therefore, as expected, the linear regression performs the best in terms of high PSNR. Moreover, even in terms of VSNR improvement, the algorithms perform relatively the same to each other as with PSNR. This means that even though we did not optimize for VSNR, our algorithm performs well even in terms of that metric.		Note that the numbers are the averages across entire images in the test set, while the linear regression algorithm was performed over individual patches in the image. Higher PSNR corresponds to a lower MSE, which is what the machine learning algorithm was optimized for. Therefore, as expected, the linear regression performs the best in terms of high PSNR. Moreover, even in terms of VSNR improvement, the algorithms perform relatively the same to each other as with PSNR. This means that even though we did not optimize for VSNR, our algorithm performs well even in terms of that metric.

imported>Student2016: /* References */

2016-12-16T00:16:46Z

References

← Older revision		Revision as of 00:16, 16 December 2016
Line 104:		Line 104:
	Farrell, Joyce, Okincha, Mike, Parmar, Manu, and Wan- dell, Brian. Using visible snr (vsnr) to compare the image quality of pixel binning and digital resizing. In IS&T/SPIE Electronic Imaging, pp. 75370C–75370C. International Society for Optics and Photonics, 2010.		Farrell, Joyce, Okincha, Mike, Parmar, Manu, and Wan- dell, Brian. Using visible snr (vsnr) to compare the image quality of pixel binning and digital resizing. In IS&T/SPIE Electronic Imaging, pp. 75370C–75370C. International Society for Optics and Photonics, 2010.

	Hunt, R.W.G. The Reproduction of Colour. The Wiley-IS&T Series in Imaging Science and Tech- nology. Wiley, 2005. ISBN 9780470024263. https://books.google.com/books?id=~~Cd_ FVeuO10gC~~.		Hunt, R.W.G. The Reproduction of Colour. The Wiley-IS&T Series in Imaging Science and Tech- nology. Wiley, 2005. ISBN 9780470024263. [https://books.google.com/books?id=Cd_FVeuO10gC].

	Hyvärinen, Aapo, Hoyer, Patrik, and Oja, Erkki. Image denoising by sparse code shrinkage. In Intelligent Signal Processing. Citeseer, 1999.		Hyvärinen, Aapo, Hoyer, Patrik, and Oja, Erkki. Image denoising by sparse code shrinkage. In Intelligent Signal Processing. Citeseer, 1999.

imported>Student2016: /* References */

2016-12-16T00:16:23Z

References

← Older revision		Revision as of 00:16, 16 December 2016
Line 104:		Line 104:
	Farrell, Joyce, Okincha, Mike, Parmar, Manu, and Wan- dell, Brian. Using visible snr (vsnr) to compare the image quality of pixel binning and digital resizing. In IS&T/SPIE Electronic Imaging, pp. 75370C–75370C. International Society for Optics and Photonics, 2010.		Farrell, Joyce, Okincha, Mike, Parmar, Manu, and Wan- dell, Brian. Using visible snr (vsnr) to compare the image quality of pixel binning and digital resizing. In IS&T/SPIE Electronic Imaging, pp. 75370C–75370C. International Society for Optics and Photonics, 2010.

	Hunt, R.W.G. The Reproduction of Colour. The Wiley-IS&T Series in Imaging Science and Tech- nology. Wiley, 2005. ISBN 9780470024263. [https://books.google.com/books?id=Cd_ FVeuO10gC].		Hunt, R.W.G. The Reproduction of Colour. The Wiley-IS&T Series in Imaging Science and Tech- nology. Wiley, 2005. ISBN 9780470024263. https://books.google.com/books?id=Cd_ FVeuO10gC.

	Hyvärinen, Aapo, Hoyer, Patrik, and Oja, Erkki. Image denoising by sparse code shrinkage. In Intelligent Signal Processing. Citeseer, 1999.		Hyvärinen, Aapo, Hoyer, Patrik, and Oja, Erkki. Image denoising by sparse code shrinkage. In Intelligent Signal Processing. Citeseer, 1999.

imported>Student2016: /* Quantitative Results */

2016-12-16T00:15:56Z

Quantitative Results

← Older revision		Revision as of 00:15, 16 December 2016
Line 78:		Line 78:

	Note that the numbers are the averages across entire images in the test set, while the linear regression algorithm was performed over individual patches in the image. Higher PSNR corresponds to a lower MSE, which is what the machine learning algorithm was optimized for. Therefore, as expected, the linear regression performs the best in terms of high PSNR. Moreover, even in terms of VSNR improvement, the algorithms perform relatively the same to each other as with PSNR. This means that even though we did not optimize for VSNR, our algorithm performs well even in terms of that metric.		Note that the numbers are the averages across entire images in the test set, while the linear regression algorithm was performed over individual patches in the image. Higher PSNR corresponds to a lower MSE, which is what the machine learning algorithm was optimized for. Therefore, as expected, the linear regression performs the best in terms of high PSNR. Moreover, even in terms of VSNR improvement, the algorithms perform relatively the same to each other as with PSNR. This means that even though we did not optimize for VSNR, our algorithm performs well even in terms of that metric.

			Another interesting observation is that the noisy image has more of a VSNR improvement than the denoised methods. This could mean that the artifacts the denoising methods introduce are more noticeable in the dark images than the noise, therefore leading to a better VSNR value for the noisy dark image than the denoised dark image.

	[[File:Nitishparoma_patches.png\|150px\|right\|thumb\|caption\|Selected patches from a sample image. We compare all the denoising methods implemented to the noisy and original (noise-free) patch.]]		[[File:Nitishparoma_patches.png\|150px\|right\|thumb\|caption\|Selected patches from a sample image. We compare all the denoising methods implemented to the noisy and original (noise-free) patch.]]

imported>Student2016: /* Dataset */

2016-12-16T00:15:33Z

Dataset

← Older revision		Revision as of 00:15, 16 December 2016
Line 16:		Line 16:
	For the base images of our dataset, we start with the Berkeley Segmentation Data Set [https://www2.eecs.berkeley.edu/Research/Projects/CS/vision/grouping/resources.html]. This dataset consists mostly of outdoor images, but includes people, nature and monuments. This ensured that we had a good variety of images to learn from and the learned parameter was not biased towards certain colors or spatial frequencies.		For the base images of our dataset, we start with the Berkeley Segmentation Data Set [https://www2.eecs.berkeley.edu/Research/Projects/CS/vision/grouping/resources.html]. This dataset consists mostly of outdoor images, but includes people, nature and monuments. This ensured that we had a good variety of images to learn from and the learned parameter was not biased towards certain colors or spatial frequencies.

	We processed these daytime images to simulate nighttime low-light image captures of the same scenes. We do this using the Image Systems Engineering Toolbox~~~\cite{iset}~~. The data set does not provide camera information metadata, and so we convert the RGB image to a scene using our monitors (Apple LCD) as the display calibration SPDs. Then we use sceneAdjustIlluminant to normalize the illuminant in all the images to D65. Next, we set the peak photon count in the images to 10 photons because this visually created a reasonable amount of Poisson noise in testing. This is done using the sceneAdjustLuminance function and by querying sceneGet for the photon count. Next, we use scenePhotonNoise to manually change the photon counts in the scene according to the Poisson distribution, and we modify the scenePhotonNoise function to remove the Gaussian approximation. Lastly, when saving the scene as an RGB image using sceneSaveImage, we modify the code such that it produces a dark RGB output (instead of the default, which rescales the XYZ values so that the RGB image is bright). Earlier, we assumed that the daylight is 6500~K blackbody radiation. We justify this choice because it matches a sunny day well, and images taken taken in outdoor night settings can look almost exactly like daylight photos with a long exposure~~~\cite{moonlight}~~, which then informs our decision to create low light images by simply scaling down the photon count.		We processed these daytime images to simulate nighttime low-light image captures of the same scenes. We do this using the Image Systems Engineering Toolbox. The data set does not provide camera information metadata, and so we convert the RGB image to a scene using our monitors (Apple LCD) as the display calibration SPDs. Then we use sceneAdjustIlluminant to normalize the illuminant in all the images to D65. Next, we set the peak photon count in the images to 10 photons because this visually created a reasonable amount of Poisson noise in testing. This is done using the sceneAdjustLuminance function and by querying sceneGet for the photon count. Next, we use scenePhotonNoise to manually change the photon counts in the scene according to the Poisson distribution, and we modify the scenePhotonNoise function to remove the Gaussian approximation. Lastly, when saving the scene as an RGB image using sceneSaveImage, we modify the code such that it produces a dark RGB output (instead of the default, which rescales the XYZ values so that the RGB image is bright). Earlier, we assumed that the daylight is 6500~K blackbody radiation. We justify this choice because it matches a sunny day well, and images taken taken in outdoor night settings can look almost exactly like daylight photos with a long exposure, which then informs our decision to create low light images by simply scaling down the photon count.

	The above procedure details how to create the noisy training examples. The noise-free values corresponding to these will be generated in much the same way, but excluding the Poisson noise addition step. These noise-free values are used as ground truth for the linear regression algorithm.		The above procedure details how to create the noisy training examples. The noise-free values corresponding to these will be generated in much the same way, but excluding the Poisson noise addition step. These noise-free values are used as ground truth for the linear regression algorithm.

imported>Student2016: /* References */

2016-12-16T00:12:48Z

References

← Older revision		Revision as of 00:12, 16 December 2016
Line 104:		Line 104:
	Hunt, R.W.G. The Reproduction of Colour. The Wiley-IS&T Series in Imaging Science and Tech- nology. Wiley, 2005. ISBN 9780470024263. [https://books.google.com/books?id=Cd_ FVeuO10gC].		Hunt, R.W.G. The Reproduction of Colour. The Wiley-IS&T Series in Imaging Science and Tech- nology. Wiley, 2005. ISBN 9780470024263. [https://books.google.com/books?id=Cd_ FVeuO10gC].

	~~Hyva ̈rinen~~, Aapo, Hoyer, Patrik, and Oja, Erkki. Image denoising by sparse code shrinkage. In Intelligent Signal Processing. Citeseer, 1999.		Hyvärinen, Aapo, Hoyer, Patrik, and Oja, Erkki. Image denoising by sparse code shrinkage. In Intelligent Signal Processing. Citeseer, 1999.

	Jin, Fu, Fieguth, Paul, Winger, Lowell, and Jernigan, Ed- ward. Adaptive wiener filtering of noisy images and image sequences. In Image Processing, 2003. ICIP 2003. Proceedings. 2003 International Conference on, volume 3, pp. III–349. IEEE, 2003.		Jin, Fu, Fieguth, Paul, Winger, Lowell, and Jernigan, Ed- ward. Adaptive wiener filtering of noisy images and image sequences. In Image Processing, 2003. ICIP 2003. Proceedings. 2003 International Conference on, volume 3, pp. III–349. IEEE, 2003.

imported>Student2016: /* References */

2016-12-16T00:09:32Z

References

← Older revision		Revision as of 00:09, 16 December 2016
Line 99:		Line 99:

	== References ==		== References ==

			Farrell, Joyce, Okincha, Mike, Parmar, Manu, and Wan- dell, Brian. Using visible snr (vsnr) to compare the image quality of pixel binning and digital resizing. In IS&T/SPIE Electronic Imaging, pp. 75370C–75370C. International Society for Optics and Photonics, 2010.

			Hunt, R.W.G. The Reproduction of Colour. The Wiley-IS&T Series in Imaging Science and Tech- nology. Wiley, 2005. ISBN 9780470024263. [https://books.google.com/books?id=Cd_ FVeuO10gC].

			Hyva ̈rinen, Aapo, Hoyer, Patrik, and Oja, Erkki. Image denoising by sparse code shrinkage. In Intelligent Signal Processing. Citeseer, 1999.

			Jin, Fu, Fieguth, Paul, Winger, Lowell, and Jernigan, Ed- ward. Adaptive wiener filtering of noisy images and image sequences. In Image Processing, 2003. ICIP 2003. Proceedings. 2003 International Conference on, volume 3, pp. III–349. IEEE, 2003.

			Kingsbury, Nick. Complex wavelets for shift invariant analysis and filtering of signals. Applied and computational harmonic analysis, 10(3):234–253, 2001.

			Luo, Enming, Chan, Stanley H, and Nguyen, Truong Q. Adaptive image denoising by mixture adaptation. arXiv preprint arXiv:1601.04770, 2016.

			Martin, D., Fowlkes, C., Tal, D., and Malik, J. A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics. In Proc. 8th Int’l Conf. Computer Vision, volume 2, pp. 416–423, July 2001.

			Ren, Jimmy SJ and Xu, Li. On vectorization of deep convolutional neural networks for vision tasks. arXiv preprint arXiv:1501.07338, 2015.

			Wandell, Brian and Farrell, Joyce. Image systems engineer- ing toolbox (iset) [http://www.imageval.com/aboutiset/].

	== Appendix I ==		== Appendix I ==

imported>Student2016: /* Dataset */

2016-12-16T00:04:01Z

Dataset

← Older revision		Revision as of 00:04, 16 December 2016
Line 21:		Line 21:

	[[File:Nitishparoma_eg_original.jpg\|200px\|left\|thumb\|caption\|Sample image in its original form from the Berkeley Image Segmentation Data Set.]]		[[File:Nitishparoma_eg_original.jpg\|200px\|left\|thumb\|caption\|Sample image in its original form from the Berkeley Image Segmentation Data Set.]]
	[[File:Nitishparoma_eg_bright.~~png200px~~\|right\|thumb\|caption\|Sample noisy image after brightening so the noise is easier to see.]]		[[File:Nitishparoma_eg_bright.png\|200px\|right\|thumb\|caption\|Sample noisy image after brightening so the noise is easier to see.]]
	[[File:Nitishparoma_eg.png\|200px\|center\|thumb\|caption\|Sample low light image generated for our dataset, with Poisson noise.]]		[[File:Nitishparoma_eg.png\|200px\|center\|thumb\|caption\|Sample low light image generated for our dataset, with Poisson noise.]]

← Older revision		Revision as of 00:04, 16 December 2016
Line 21:		Line 21:

	[[File:Nitishparoma_eg_original.jpg\|200px\|left\|thumb\|caption\|Sample image in its original form from the Berkeley Image Segmentation Data Set.]]		[[File:Nitishparoma_eg_original.jpg\|200px\|left\|thumb\|caption\|Sample image in its original form from the Berkeley Image Segmentation Data Set.]]
	[[File:Nitishparoma_eg_bright.~~png200px~~\|right\|thumb\|caption\|Sample noisy image after brightening so the noise is easier to see.]]		[[File:Nitishparoma_eg_bright.png\|200px\|right\|thumb\|caption\|Sample noisy image after brightening so the noise is easier to see.]]
	[[File:Nitishparoma_eg.png\|200px\|center\|thumb\|caption\|Sample low light image generated for our dataset, with Poisson noise.]]		[[File:Nitishparoma_eg.png\|200px\|center\|thumb\|caption\|Sample low light image generated for our dataset, with Poisson noise.]]