Learning Weighting Map for Bit-Depth Expansion within a Rational Range

Liu, Yuqing; Jia, Qiong; Zhang, Jian; Fan, Xiaohui; Wang, Shiqi; Ma, Siwei; Gao, Wen

doi:10.48550/arxiv.2204.12039

Cited by 1 publication

(1 citation statement)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Byun et al [7] proposed a method to identify the bit-depth of input images by providing the network with bit-depth information concatenated with the input image. Liu et al [8] learned a unified representation for different bit-depth degradation by concatenating the theoretical upper bound of the missing information as bit-depth information to the input. Punnappurath et al [9] progressively recovered each missing bitplane from the bit-depth of the input image to the desired bit-depth by training an independent multiple networks on a bitplane wise.…”

Section: Introductionmentioning

confidence: 99%

Frequency domain-based bit-depth enhancement method and dealing with different bit-depth degradation

Iriyama

Aomori

Otake

2023

NOLTA

View full text Add to dashboard Cite

In this paper, we present the effectiveness of a frequency domain-based loss function using the discrete cosine transform (DCT) for the bit-depth enhancement (BDE) problem that recovers high-bit-depth images from low-bit-depth images. By minimizing the loss between the DCT coefficients, it is expected to recover smooth luminance changes by suppressing extra frequency components caused by the weak gradients contained in the false contour artifacts. Moreover, we proposed a frequency domain-based multi-level BDE method to deal with different bit-depth degradation. The proposed multi-level BDE method identifies the bit-depth of the input image by embedding the bit-depth information in the frequency domain, and it recovered the missing lower bits appropriately. Experimental results show that the model optimized with frequency-based loss outperforms the model optimized with other losses in the comparison considering the objective and subjective results. Furthermore, we show that the proposed multi-level BDE method is effective for more severe bit-depth degradation on a specific benchmark dataset.

show abstract

Section: Introductionmentioning

confidence: 99%