ABCD : Arbitrary Bitwise Coefficient for De-Quantization
Authors:
- 1 June 2023
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 5876-5885
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/ABCDKeywords
Funding Information
- DGIST R&D Program of the Ministry of Science and ICT of Korea (22-KUJoint-02,21-IJRP-01)
- Korean National Police Agency(KNPA) (230222M01)
- Korea Government (MSIT) (2021-0-02068)
This publication has 36 references indexed in Scilit:
- Perceptual quality evaluation of synthetic pictures distorted by compression and transmissionSignal Processing: Image Communication, 2018
- Enhanced Deep Residual Networks for Single Image Super-Resolution2017
- Image Bit-Depth Enhancement via Maximum A Posteriori Estimation of AC SignalIEEE Transactions on Image Processing, 2016
- TESTIMAGES: A Large Data Archive For Display and Algorithm TestingJournal of Graphics Tools, 2013
- N-Dimensional Binary Vector SpacesFormalized Mathematics, 2013
- Bit-depth expansion using Minimum Risk Based Classification2012
- From 2D Extrapolation to 1D Interpolation: Content Adaptive Image Bit-Depth Expansion2012
- Bit-depth expansion by contour region reconstruction2009
- High dynamic range display systems2004
- Pixel bit-depth increase by bit replication1998