Spatially-Varying Super-Resolution for HDTV, ISCAS2013.

  • C.-T. Shen, H.-H. Liu, M.-S. Lee, Y.-P. Hung, and S.-C. Pei, “Spatially-Varying Super-Resolution for HDTV", in Proc. of IEEE International Symposium on Circuits and Systems (ISCAS), pp. 1195-1198, 2013.
  • Talk Slides: ISCAS2013_v5
  • System:

system

  •  Results #1 chip_merge
  •  Results #2koala_merge
  • Results #3 girl_merge
  •  Results #4kitchen_merge
  •  Results #5 on Video Frames suzie_merge
  • Results #6 on Video Framesforeman_merge
  •  Results #7 on Video FramesDT2800_merge
  •  Results #8 on Video FramesDT3000_merge
  • Results #9 on Video FramesH4800_merge
  •  Results #10 on Video FramesH5000_merge

Visual Enhancement using Constrained L0 Gradient Image Decomposition for Low Backlight Displays, IEEE SPL 2012.

S.-C. Pei, C.-T. Shen, and T.-Y. Lee, “Visual Enhancement using Constrained L0 Gradient Image Decomposition for Low Backlight Displays", IEEE Signal Processing Letters, Vol. 19, No. 12, pp. 813-816, 2012.

  • System:system
  • Results #1: Original Input, Linear-Scaled, Ours
  • Results #2: Original Input, Linear-Scaled, Ours
  • Results #3: Original Input, Linear-Scaled, Ours
  • Results #4: Original Input, Linear-Scaled, Ours

Spatially-Varying Out-Of-Focus Image Deblurring with L1-2 Optimization and a Guided Blur Map, ICASSP2012.

  • C.-T. Shen, W.-L. Hwang, and S.-C. Pei, “Spatially-Varying Out-Of-Focus Image Deblurring with L1-2 Optimization and a Guided Blur Map", in Proc. of 37th IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pp. 1069-1072, 2012.
  • System:system
  • L1-2 Deblurring:L12
  • Results #1 (Blurry Input, Ours, Blur Map): The data is downloaded from Zhuo et al’s webpage. Please notice the regions within different depth.demo_building
  • Results #2 (Blurry Input, Ours, Blur Map): The data is downloaded from Zhuo et al’s webpage. We remove the out-of-focus while extend the depth-of-field. demo_pumpkin
  • Results #3 (Blurry Input, Ours, Blur Map): The data is captured using Camera Control Pro 2 with a tripod. Since two men stand at the different depth, the input image suffers spatially-varying out-of-focus blur. As we can see, we reconstruct the blurry faces.demo_face
  • Results #4 (Blurry Input, Ours, Blur Map): The data is captured using Camera Control Pro 2 with a tripod and focus on the ball.
    Since two men stand at the different depth, the input image suffers spatially-varying out-of-focus blur. As we can see, we reconstruct the blurry faces while keep the ball latent.demo_face2
  • Results #5 (Blurry Input, Ours, Blur Map) : The data is captured using a camera phone, and it is out-of-focus. We remove the blur while enhance the chinese characters and texture parts. demo_China
  • Results #6 (Blurry Input, Ours, Blur Map) : The data is captured using a camera phone, and it is out-of-focus. We remove the blur while enhance the lady’s face and texture parts. The lady is a Traditional Chinese Doctor. She is observing the patient’s movement.demo_Ho
  • Results #7 (Blurry Input, Ours, Blur Map): The data is captured using a digital still camera(DSC), and it is out-of-focus. We remove the blur in the background while enhance the lady’s face and texture parts. demo_JCY01
  • Results #8 (Blurry Input, Ours, Blur Map): The data is part of the image captured using a DSLR, and it is out-of-focus. We remove the blur in the background while keep the hair latent. demo_JCY02
  • Results #9 (Blurry Input, Ours, Blur Map): The data is downloaded from Xu et al.’s webpage. Although the data suffers from motion-blur, our method still gives a certain result and extends the depth of field. Since our method is not for depth estimation, we set the smooth regions as in-focus regions so as to suppress the ringing artifacts. demo_sculpture
  • Results #10 (Blurry Input, Ours, Blur Map): The data is downloaded from Xu et al.’s webpage. Although the data suffers from motion-blur, our method still gives a certain result and extends the depth of field.demo_stone
  • Results #11 (Blurry Input, Ours, Blur Map): The data is downloaded from Xu et al.’s webpage. Although the data suffers from motion-blur, our method still gives a certain result and extends the depth of field. Since our method is not for depth estimation, we set the smooth regions as in-focus regions so as to suppress the ringing artifacts. demo_car
  • Results #12 (Blurry Input, Ours, Blur Map): The data is downloaded from Xu et al.’s webpage. Although the data suffers from motion-blur, our method still gives a certain result and extends the depth of field.demo_wheel