DEVICE AND METHOD FOR GENERATING SUPER-RESOLUTION IMAGE CAPABLE OF ADJUSTING EDGE SHARPNESS
The present invention relates to a device and method for generating a super-resolution image capable of adjusting edge sharpness. The device comprises: an image receiving unit that receives a source image of a first resolution; an up-scaling unit that generates an up-scaled image having a second res...
Gespeichert in:
Hauptverfasser: | , , |
---|---|
Format: | Patent |
Sprache: | eng ; fre ; kor |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | The present invention relates to a device and method for generating a super-resolution image capable of adjusting edge sharpness. The device comprises: an image receiving unit that receives a source image of a first resolution; an up-scaling unit that generates an up-scaled image having a second resolution by up-scaling the source image; and an image generation unit that generates a resultant image having enhanced sharpness compared to the upscaled image by weighting a difference between an input and an output of a convolutional neural network (CNN) to which the upscaled image is applied.
La présente invention concerne un dispositif et un procédé de génération d'une image super-résolution permettant d'ajuster la netteté des bords. Le dispositif comprend : une unité de réception d'image qui reçoit une image source d'une première résolution ; une unité d'interpolation qui génère une image interpolée ayant une seconde résolution par interpolation de l'image source ; et une unité de génération d'image qui génère une image résultante ayant une netteté améliorée comparativement à l'image interpolée par pondération d'une différence entre une entrée et une sortie d'un réseau neuronal convolutif (CNN) auquel l'image interpolée est appliquée.
본 발명은 에지 선명도의 조정이 가능한 초해상화 이미지 생성 장치 및 방법에 관한 것으로, 상기 장치는 제1 해상도의 소스 이미지를 수신하는 이미지 수신부; 상기 소스 이미지를 업 스케일링(up scaling) 하여 제2 해상도를 갖는 업 스케일된 이미지를 생성하는 업 스케일링부; 및 상기 업 스케일된 이미지가 적용된 합성곱 모델(CNN, Convolution Neural Network)의 입력 및 출력 사이의 차이를 가중화 하여 상기 업 스케일된 이미지보다 선명도가 향상된 결과 이미지를 생성하는 이미지 생성부;를 포함한다. |
---|