Test image 2

Blur kernel =        Noise level = 5%


Mouse over the following links to flip between images
By default, our result is shown
MAP estimate - fixed sparse gradient prior, PSNR : 25.008538, SSIM : 0.909876
MAP estimate - adjusted sparse gradient prior, PSNR : 25.034535, SSIM : 0.912597
Degraded image
Original image
Gradient distribution
User study result

Ours PSNR : 24.959475, SSIM : 0.912513

Mouse over the following links to flip between images
By default, our result is shown
MAP estimate - sparse gradient prior, PSNR : 25.008538, SSIM : 0.909876
MAP estimate - adjusted sparse gradient prior, PSNR : 25.034535, SSIM : 0.912597
Degraded image
Original image
Gradient distribution
User study result



Test image 8

Blur kernel =        Noise level = 5%


Mouse over the following links to flip between images
By default, our result is shown
MAP estimate - fixed sparse gradient prior, PSNR : 29.659139, SSIM : 0.919851
MAP estimate - adjusted sparse gradient prior, PSNR : 30.146984, SSIM : 0.923550
Degraded image
Original image
Gradient distribution
User study result

Ours PSNR : 29.459834, SSIM : 0.915032

Mouse over the following links to flip between images
By default, our result is shown
MAP estimate - sparse gradient prior, PSNR : 29.659139, SSIM : 0.919851
MAP estimate - adjusted sparse gradient prior, PSNR : 30.146984, SSIM : 0.923550
Degraded image
Original image
Gradient distribution
User study result