Two layer coding of HDR images with noise bias compensation

Iwahashi, Masahiro; Hamzah, Fairoza Amira Binti; Yoshida, Taichi; Kiya, Hitoshi

doi:10.1109/apsipa.2015.7415309

Cited by 4 publications

(1 citation statement)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is also proved that the quantization algorithm can improve the performance on several existing two-layer encoding methods. Iwahashi et al [6] used noise bias compensation to reduce variance of the noise. They defined noise bias as the mean of the noise in the same observed pixel value from different original values, and compensated it according to an observed pixel value.…”

Section: Introductionmentioning

confidence: 99%

High dynamic range image compression based on visual saliency

Wang

Zhu

2020

SIP

View full text Add to dashboard Cite

With wider luminance range than conventional low dynamic range (LDR) images, high dynamic range (HDR) images are more consistent with human visual system (HVS). Recently, JPEG committee releases a new HDR image compression standard JPEG XT. It decomposes an input HDR image into base layer and extension layer. The base layer code stream provides JPEG (ISO/IEC 10918) backward compatibility, while the extension layer code stream helps to reconstruct the original HDR image. However, this method does not make full use of HVS, causing waste of bits on imperceptible regions to human eyes. In this paper, a visual saliency-based HDR image compression scheme is proposed. The saliency map of tone mapped HDR image is first extracted, then it is used to guide the encoding of extension layer. The compression quality is adaptive to the saliency of the coding region of the image. Extensive experimental results show that our method outperforms JPEG XT profile A, B, C and other state-of-the-art methods. Moreover, our proposed method offers the JPEG compatibility at the same time.

show abstract

Section: Introductionmentioning

confidence: 99%

High dynamic range image compression based on visual saliency

Wang

Zhu

2020

SIP

View full text Add to dashboard Cite

show abstract

High Dynamic Range Image Compression Based on Visual Saliency

Li¹,

Wang²,

Zhu³

2018

2018 Picture Coding Symposium (PCS)

View full text Add to dashboard Cite

In recent years, large visual language models (LVLMs) have shown impressive performance and promising generalization capability in multi-modal tasks, thus replacing humans as receivers of visual information in various application scenarios. In this paper, we pioneer to propose a variable bitrate image compression framework consisting of a pre-editing module and an end-to-end codec to achieve promising rate-accuracy performance for different LVLMs. In particular, instead of optimizing an adaptive pre-editing network towards a particular task or several representative tasks, we propose a new optimization strategy tailored for LVLMs, which is designed based on the representation and discrimination capability with token-level distortion and rank. The pre-editing module and the variable bitrate end-to-end image codec are jointly trained by the losses based on semantic tokens of the large model, which introduce enhanced generalization capability for various data and tasks. Experimental results demonstrate that the proposed framework could efficiently achieve much better rate-accuracy performance compared to the state-of-the-art coding standard, Versatile Video Coding. Meanwhile, experiments with multi-modal tasks have revealed the robustness and generalization capability of the proposed framework.

show abstract