Восстановление сжатого видео Моисейцев Алексей Video Group CS MSU Graphics & Media Lab
Only for Maxus Содержание Введение Простые модели Adaptive Fuzzy Post-Filtering DCT Re-application Классификация Support Vector Regression Modified Mean-Removed Classified Vector Quantization Регуляризация Заключение 2 CS MSU Graphics & Media Lab (Video Group)
Only for Maxus Введение 3 CS MSU Graphics & Media Lab (Video Group)
Only for Maxus Введение 4 CS MSU Graphics & Media Lab (Video Group)
Only for Maxus Содержание Введение Простые модели Adaptive Fuzzy Post-Filtering DCT Re-application Классификация Support Vector Regression Modified Mean-Removed Classified Vector Quantization Регуляризация Заключение 6 CS MSU Graphics & Media Lab (Video Group)
Only for Maxus Adaptive Fuzzy Post-Filtering N x ( x , x ) ~ j c j j x 1 c N ( x , x ) c j j 1 ( a , b ) e ( a b ) 2 / 2 2 сила фильтра , 2 зависит от типа блока ~ x новое значение пикселя c Adaptive Fuzzy Post-Filtering for Highly Compressed Video. Hao-Song Kong, Yao Nie, Anthony Vetro, Huifang Sun, Kenneth E. Barner. ICIP 2004. 7 CS MSU Graphics & Media Lab (Video Group)
Only for Maxus Adaptive Fuzzy Post-Filtering Adaptive Fuzzy Post-Filtering for Highly Compressed Video. Hao-Song Kong, Yao Nie, Anthony Vetro, Huifang Sun, Kenneth E. Barner. ICIP 2004. 8 CS MSU Graphics & Media Lab (Video Group)
Only for Maxus Adaptive Fuzzy Post-Filtering PSNR 30.93 dB PSNR 30.61 dB Adaptive Fuzzy Post-Filtering for Highly Compressed Video. Hao-Song Kong, Yao Nie, Anthony Vetro, Huifang Sun, Kenneth E. Barner. ICIP 2004. 9 CS MSU Graphics & Media Lab (Video Group)
Only for Maxus Adaptive Fuzzy Post-Filtering Преимущества Быстрая работа Простота в реализации Недостатки Просто маскировка артефактов Замыливание изображения 10 CS MSU Graphics & Media Lab (Video Group)
Only for Maxus Содержание Введение Простые модели Adaptive Fuzzy Post-Filtering DCT Re-application Классификация Support Vector Regression Modified Mean-Removed Classified Vector Quantization Регуляризация Заключение 11 11 11 CS MSU Graphics & Media Lab (Video Group)
Only for Maxus DCT Re-application 1. Сдвинуть изображение по вертикали и горизонтали на (i,j) 2. Сжать изображение 3. Вернуть изображение обратно, т.е. сдвинуть на (-i,-j) 4. Повторить для всех сдвигов из [-3, 4] x [-3, 4] 5. Усреднить результат Enhancement of JPEG-Compressed Images by Re-application of JPEG. Aria Nosratinia. Department of Electrical Engineering, University of Texas at Dallas, Richardson. 2002. 12 12 CS MSU Graphics & Media Lab (Video Group)
Only for Maxus DCT Re-application Enhancement of JPEG-Compressed Images by Re-application of JPEG. Aria 13 13 Nosratinia. Department of Electrical Engineering, University of Texas at Dallas, CS MSU Graphics & Media Lab (Video Group) Richardson. 2002.
Only for Maxus DCT Re-application Enhancement of JPEG-Compressed Images by Re-application of JPEG. Aria 14 14 Nosratinia. Department of Electrical Engineering, University of Texas at Dallas, CS MSU Graphics & Media Lab (Video Group) Richardson. 2002.
Only for Maxus DCT Re-application ( , ) , i j i j y D Q D x , i j , i j сжатое изображени е - x восстановл енное изображени е - y оператор сдвига - D оператор кодировани я и декодирова ния Q - i , j Enhancement of JPEG-Compressed Images by Re-application of JPEG. Aria 15 15 Nosratinia. Department of Electrical Engineering, University of Texas at Dallas, CS MSU Graphics & Media Lab (Video Group) Richardson. 2002.
Only for Maxus DCT Re-application Пример работы Enhancement of JPEG-Compressed Images by Re-application of JPEG. Aria Nosratinia. Department of Electrical Engineering, University of Texas at Dallas, Richardson. 2002. 16 16 CS MSU Graphics & Media Lab (Video Group)
Only for Maxus DCT Re-application Пример работы Enhancement of JPEG-Compressed Images by Re-application of JPEG. Aria Nosratinia. Department of Electrical Engineering, University of Texas at Dallas, Richardson. 2002. 17 17 CS MSU Graphics & Media Lab (Video Group)
Only for Maxus DCT Re-application Пример работы Enhancement of JPEG-Compressed Images by Re-application of JPEG. Aria Nosratinia. Department of Electrical Engineering, University of Texas at Dallas, Richardson. 2002. 18 18 CS MSU Graphics & Media Lab (Video Group)
Only for Maxus DCT Re-application Преимущества Заметное уменьшение артефактов Прост в реализации Недостатки Желательно знать параметры сжатия Ориентирован на изображения Невысокая скорость работы ( ~58 умножений на пиксель ) 19 CS MSU Graphics & Media Lab (Video Group)
Only for Maxus Содержание Введение Простые модели Adaptive Fuzzy Post-Filtering DCT Re-application Классификация Support Vector Regression Modified Mean-Removed Classified Vector Quantization Регуляризация Заключение 20 20 20 CS MSU Graphics & Media Lab (Video Group)
Only for Maxus Support Vector Regression Support Vector Machine 21 21 Compression Artifact Reduction Using Support Vector Regression. CS MSU Graphics & Media Lab (Video Group) Sanjeev Kumar, Truong Nguyen, Mainak Biswas. ICIP 2006
Only for Maxus Support Vector Regression y - моделируемая функция ( x ) f - тренировочные данные x , i y i - вид модели ( ), y w x b Минимизация l * 1 , w w C 2 i i 1 i при условии допустимое отклонение для всех элементов , ( ) y w x b i i i * отклонение для каждого элемента * , , ( ) w x b y i i i i i * , 0 i i 22 22 Compression Artifact Reduction Using Support Vector Regression. CS MSU Graphics & Media Lab (Video Group) Sanjeev Kumar, Truong Nguyen, Mainak Biswas. ICIP 2006
Only for Maxus Support Vector Regression 23 23 Compression Artifact Reduction Using Support Vector Regression. CS MSU Graphics & Media Lab (Video Group) Sanjeev Kumar, Truong Nguyen, Mainak Biswas. ICIP 2006
Only for Maxus Support Vector Regression 24 24 Compression Artifact Reduction Using Support Vector Regression. CS MSU Graphics & Media Lab (Video Group) Sanjeev Kumar, Truong Nguyen, Mainak Biswas. ICIP 2006
Only for Maxus Support Vector Regression 25 Compression Artifact Reduction Using Support Vector Regression. CS MSU Graphics & Media Lab (Video Group) Sanjeev Kumar, Truong Nguyen, Mainak Biswas. ICIP 2006
Only for Maxus Support Vector Regression Преимущества Визуальное улучшение на некоторых типах изображений Недостатки Зависимость от обучающей выборки Сложно прогнозируемое поведение 26 CS MSU Graphics & Media Lab (Video Group)
Only for Maxus Содержание Введение Простые модели Adaptive Fuzzy Post-Filtering DCT Re-application Классификация Support Vector Regression Modified Mean-Removed Classified Vector Quantization Регуляризация Заключение 27 27 27 CS MSU Graphics & Media Lab (Video Group)
Only for Maxus MMRCVQ (Modified Mean-Removed Classified Vector Quantization) Artifact reduction of compressed color images using modified mean-removed classified vector quantization. Jim Zone-Chang Lai, Yi-Ching Liaw, and Winston Lo. Journal of the Chinese Institute of Engineers, Vol. 27, No. 5, pp. 747-751 (2004) 28 28 CS MSU Graphics & Media Lab (Video Group)
Recommend
More recommend