Upcoming SlideShare
×

Gpgpu presentation final

959
-1

Published on

The final presentation of gpu project.

0 Likes
Statistics
Notes
• Full Name
Comment goes here.

Are you sure you want to Yes No
• Be the first to comment

• Be the first to like this

Views
Total Views
959
On Slideshare
0
From Embeds
0
Number of Embeds
0
Actions
Shares
0
12
0
Likes
0
Embeds 0
No embeds

No notes for slide

Gpgpu presentation final

1. 1. 薛健鑫, 蔡昆修, 何星翰 1
2. 2.  Introduction  Work progress  SR Algorithm  Evaluation  SR video player demo  Conclusion 2
3. 3.  Super-resolution are techniques that improve image quality from low-resolution. 3
4. 4.  Multiple neighboring frames of video each provide a rich amount of information about scene details.  Super-resolution on video can analyze multiple frames to reconstruct a enhance frame with detail 4
5. 5.  Retrieving image stream  From OpenCV  Super-resolution processing  Algorithm : FGSR, FRSR  GPU speedup investigation  Video player 5
6. 6.  Fast General Super-Resolution (FGSR)  For general video use  Fast, cheap, bad result  Fast & Robust Super-Resolution(FRSR)  Only appropriate for translational motion  Slow, better result 6
7. 7.  Predict HR = bicubic( Gi )  Iterative fix Predict HR : In’ = optcial_flow( bicubic(Gi+n ) ) Predict HR += α * ( Predict HR – In’ ) * 7
8. 8. Processing time 500 450 400 350 300 time (ms) 250 cpu 200 gpu 150 100 50 0 64 128 256 512 1024 2048 Image size 8
9. 9. Bilinear interpolation FGSR 9
10. 10.  Predicted HR= Median( shift(LR0~n) )  Iterative improve Predicted HR : Gback = FastGradientBackProject(HR); Greg = GradientRegularization(HR); HR = HR - β*(Gback + α* Greg); 10
11. 11. Bilinear interpolation FRSR 11
12. 12.  PSNR (Peak Signal to Noise Ratio): Ground truth Bilinear interpolation Bicubic interpolation image PSNR ∞ 14.450087 15.79615 (dB) 12
13. 13.  PSNR (Peak Signal to Noise Ratio): Ground truth FGSR FRSR algorithm algorithm image PSNR ∞ 14.642818 15.150817 (dB) 13
14. 14. 14
15. 15.  Problem on super-resolution:  Optical flow  Occlusion/ disocclusion  Insufficient information from neighboring frames  Still have much space to improve 15
16. 16.  Sina Farsiu, Dirk Robinson, Michael Elad, Peyman Milanfar. Fast and Robust Multi-Frame Super-Resolution. In IEEE Transactions on Image Processing2003.  Zhongding Jiang, Tien-tsin Wong, Hujun Bao. Practical Super-Resolution from Dynamic Video Sequences. In Proc. of IEEE CVPR2003. 16
17. 17. THE END 17
1. A particular slide catching your eye?

Clipping is a handy way to collect important slides you want to go back to later.