TY - GEN
T1 - CNN Based Multi-view Image Quality Enhancement
AU - Jeon, Gyu Lee
AU - Kim, Hee Jae
AU - Yeo, Eun
AU - Kang, Je Won
N1 - Funding Information:
ACKNOWLEDGMENT This work was supported by Institute of Information communications Technology Planning Evaluation (IITP) grant funded by the Korea government(MSIT) (No. 2020-0-00920, Development of Ultra High Resolution Unstructured Plenoptic 9ideo Storage Compression Streaming Technology for Medium to Large Space). This work was supported by the National Research Foundation of Korea(NRF) grant funded by the Korea government(MSIT) (No. 2022R1A2C4002052).
Publisher Copyright:
© 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - We propose a CNN-based multi-view image quality enhancement (MVIQE) to improve the quality of a target image using adjacent multi-view images. Differing from the conventional single frame quality enhancement, our approach aims to improve the quality by transferring a higher quality of other input views in multi-view images as references. Our network contains an optical flow estimation module, warping layers, and image synthesis module to enhance the quality of a target image with quantization noise. Experimental results show that our method outperforms previous studies on image quality enhancement in terms of peak signal-to-noise ratio performance.
AB - We propose a CNN-based multi-view image quality enhancement (MVIQE) to improve the quality of a target image using adjacent multi-view images. Differing from the conventional single frame quality enhancement, our approach aims to improve the quality by transferring a higher quality of other input views in multi-view images as references. Our network contains an optical flow estimation module, warping layers, and image synthesis module to enhance the quality of a target image with quantization noise. Experimental results show that our method outperforms previous studies on image quality enhancement in terms of peak signal-to-noise ratio performance.
KW - Convolutional Neural Networks(CNN)
KW - Image quality enhancement
KW - Keywords
KW - multi-view images
UR - http://www.scopus.com/inward/record.url?scp=85135237816&partnerID=8YFLogxK
U2 - 10.1109/ICUFN55119.2022.9829639
DO - 10.1109/ICUFN55119.2022.9829639
M3 - Conference contribution
AN - SCOPUS:85135237816
T3 - International Conference on Ubiquitous and Future Networks, ICUFN
SP - 372
EP - 375
BT - ICUFN 2022 - 13th International Conference on Ubiquitous and Future Networks
PB - IEEE Computer Society
T2 - 13th International Conference on Ubiquitous and Future Networks, ICUFN 2022
Y2 - 5 July 2022 through 8 July 2022
ER -