1 / 19

Noisy Video Super-Resolution

Feng Liu, JinjunWang,ShenghuoZhu (MM’08) University of Wisconsin-Madison, NEC Laboratories America, Inc. Noisy Video Super-Resolution. 第一組: 資訊四 B95902105 黃彥達 資訊碩一 R98922046 蔡旻光 網媒碩二 R97944012 鄒志鴻. Outline. Introduction Goal File Format Noise Reduced Image

terra
Download Presentation

Noisy Video Super-Resolution

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Feng Liu, JinjunWang,ShenghuoZhu (MM’08) University of Wisconsin-Madison, NEC Laboratories America, Inc. Noisy Video Super-Resolution 第一組: 資訊四 B95902105 黃彥達 資訊碩一 R98922046 蔡旻光 網媒碩二 R97944012 鄒志鴻

  2. Outline • Introduction • Goal • File Format • Noise Reduced Image • Proposed Approach • Motion Estimation & Estimated Super-Resolution Result • Implementation • Result • Conclusion

  3. Introduction • Low-quality videos often not only have limited resolution but also suffer from noise • In fact, the requirements of de-noising & super-resolution is quite similar • This paper present a unified framework which achieves simultaneous video de-noising and super-resolution algorithm by some measurements of visual quality

  4. Goal • Refine low-quality videos from YouTube, and make the video better effects, which has better quality by human eyes. • Input is low-quality and noise-included (block effects or somewhat noise) videos

  5. Noise-Reduced Image mv-SAD Gaussian-space Gaussian-time | p(I,j) – p(i’, j’) | > threshold

  6. Gaussian Space Set Mean = 0 Standard deviation Frame t Pixel(I,j)

  7. Motion Vector (mv_i, mv_j) Frame t+1 Pixel ( i , j , t) Frame t Pixel ( i + mv_i , j + mv_j , t+1)

  8. Gaussian Time Pixel(I,j) Frame t+2 Frame t - 2 Frame t - 1 Frame t Frame t+1 Frame t Time Gaussian Space Gaussian

  9. Noise-Reduced Image Before After

  10. Proposed Approach – 1 / 4 • Consider the visual quality with respect to the following 3 aspects: • Fidelity Preserving • To achieve similar high-resolution result • Detail Preserving • Enhanced details (edge) • Spatial-Temporal Smoothness • Remove undesirable high-frequency contents (e.g. jitter)

  11. Proposed Approach – 2 / 4 • Fidelity Preserving • Conventional metrics: • Measure fidelity by the difference between Ih & Il would be problematic & waste useful time-space information in video • Proposed metrics: • Estimate an approximation of super-resolution results from space-time neighboring pixels • The fidelity measurement: noised see next page for details

  12. Proposed Approach – 3 / 4 • Detail Preserving • Enhanced details (edge) • Contrast preserving • Human visual system is more sensitive to contrast than pixel values • Gradient fields of Ih & should be close ,where Wkis one or zero if the patchk with/o edges (canny detector)

  13. Proposed Approach – 4 / 4 • (Spatial-Temporal) Smoothness • Smooth results are often favored by the human system • Encourage to minimize: • A 2-D Laplace filter may be Spatial-temporal Laplacian OR

  14. An Optimization Problem • Proposed Measurements • A quadratic minimization problem to solve (AX = b): Similarity Contrast Detail Information(edge) Spatial-Temporal Smoothness

  15. Implementation – 1 / 2 Motion Estimation + Bilateral filter Inputlow Fidelity -1 0 1 … 1 -1 0 1 … 1 -1 0 1 … 1 Gradient = Minimize Edge 6 -1 … -1 -1 6 -1 … -1 -1 6 -1 … -1 Result (X) Laplacian

  16. Implementation – 2 / 2 • Adjustments for the weight terms • The measurement term is more emphasized if the weight is larger • By iteratively experiments for our test data, we took • However, we found that for different videos, the best weight sets may be also different

  17. Result • 352 x 288 Result

  18. Conclusion • The proposed framework formulates noisy video super-resolution as an optimization problem, aiming to maximize the visual quality of the result • The measurements of fidelity-preserving, detail-preserving and smoothness are considered to maximize the visual quality results

  19. Thank you!!

More Related