Cited time in webofscience Cited time in scopus

ABCD : Arbitrary Bitwise Coefficient for De-quantization

Title
ABCD : Arbitrary Bitwise Coefficient for De-quantization
Author(s)
Han, Woo KyoungLee, ByeonghunPark, Sang HyunJin, Kyong Hwan
Issued Date
2023-06-20
Citation
Computer Vision and Pattern recognition, pp.5876 - 5885
Type
Conference Paper
ISBN
9798350301298
ISSN
2575-7075
Abstract
Modern displays and contents support more than 8bits image and video. However, bit-starving situations such as compression codecs make low bit-depth (LBD) images (<8bits), occurring banding and blurry artifacts. Previous bit depth expansion (BDE) methods still produce unsatisfactory high bit-depth (HBD) images. To this end, we propose an implicit neural function with a bit query to recover de-quantized images from arbitrarily quantized inputs. We develop a phasor estimator to exploit the information of the nearest pixels. Our method shows superior performance against prior BDE methods on natural and animation images. We also demonstrate our model on YouTube UGC datasets for de-banding. Our source code is available at https://github.com/WooKyoungHan/ABCD
URI
http://hdl.handle.net/20.500.11750/47924
DOI
10.1109/CVPR52729.2023.00569
Publisher
IEEE Computer Society, The Computer Vision Foundation
Related Researcher
  • 박상현 Park, Sang Hyun 로봇및기계전자공학과
  • Research Interests 컴퓨터비전; 인공지능; 의료영상처리
Files in This Item:

There are no files associated with this item.

Appears in Collections:
Department of Robotics and Mechatronics Engineering Medical Image & Signal Processing Lab 2. Conference Papers
Department of Electrical Engineering and Computer Science Image Processing Laboratory 2. Conference Papers

qrcode

  • twitter
  • facebook
  • mendeley

Items in Repository are protected by copyright, with all rights reserved, unless otherwise indicated.

BROWSE