SDRTV-to-HDRTV via Hierarchical Dynamic Context Feature Mapping

He, Gang; Xu, Kepeng; Xu, Li; Wu, Chang; Sun, Ming; Wen, Xiaoqing; Tai, Yu-Wing

doi:10.1145/3503161.3548043

Cited by 19 publications

(9 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similarly, the SSIM is another crucial measure that evaluates the perceptual quality of images by comparing structural similarities. We compare the proposed method with state-of-the-art SDRTV-to-HDRTV methods (FMNet [ 43 ], HDRUNET [ 44 ], HDCFM [ 11 ], HyCondITM [ 45 ], etc.). For a fair comparison, each method was retrained on the same training set.…”

Section: Resultsmentioning

confidence: 99%

“…[ 10 ] proposed a global priors guided modulation network to extract color conformity priors and structural similarity priors that are beneficial for SDRTV-to-HDRTV and SR tasks, respectively. Similarly, the HDCFM framework [ 11 ] involves hierarchical dynamic context feature mapping to facilitate the learning of the mapping function from SDR frames to HDR frames. This is achieved through a hierarchical feature modulation module coupled with a dynamic context feature transformation module, providing a structured approach to understanding and transforming visual data from SDR to HDR and enhancing the visual output and potentially paving the way for better utilization of existing SDR video resources in the newer HDRTV format.…”

Section: Related Workmentioning

confidence: 99%

“…In a different vein, HDRTVNET [ 7 ] introduced a multi-stage mechanism to achieve SDRTV-to-HDRTV conversion, employing global tone mapping, local image enhancement, and image generation. Similarly, the HDCFM framework [ 11 ] involves hierarchical dynamic context feature mapping to facilitate the learning of the mapping function from the SDR frame to the HDR frame.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Multi-Frame Content-Aware Mapping Network for Standard-Dynamic-Range to High-Dynamic-Range Television Artifact Removal

Wang,

2024

Sensors

Self Cite

View full text Add to dashboard Cite

Recently, advancements in image sensor technology have paved the way for the proliferation of high-dynamic-range television (HDRTV). Consequently, there has been a surge in demand for the conversion of standard-dynamic-range television (SDRTV) to HDRTV, especially due to the dearth of native HDRTV content. However, since SDRTV often comes with video encoding artifacts, SDRTV to HDRTV conversion often amplifies these encoding artifacts, thereby reducing the visual quality of the output video. To solve this problem, this paper proposes a multi-frame content-aware mapping network (MCMN), aiming to improve the performance of conversion from low-quality SDRTV to high-quality HDRTV. Specifically, we utilize the temporal spatial characteristics of videos to design a content-aware temporal spatial alignment module for the initial alignment of video features. In the feature prior extraction stage, we innovatively propose a hybrid prior extraction module, including cross-temporal priors, local spatial priors, and global spatial prior extraction. Finally, we design a temporal spatial transformation module to generate an improved tone mapping result. From time to space, from local to global, our method makes full use of multi-frame information to perform inverse tone mapping of single-frame images, while it is also able to better repair coding artifacts.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Multi-Frame Content-Aware Mapping Network for Standard-Dynamic-Range to High-Dynamic-Range Television Artifact Removal

Wang,

2024

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…Following [3], several works have been proposed to address the task of SDRTV-to-HDRTV. For example, He et al [19] proposes HD-CFM, which introduces hierarchical global and local feature modulation to deal with this task. To enhance the contrast in a frequency-adaptive way for SDRTV-to-HDRTV conversion, Xu et al [18] introduces a Frequency-aware Modulation Network (FMNet) that reduces the structural distortions and artifacts.…”

Section: Sdrtv-to-hdrtvmentioning

confidence: 99%

“…A preliminary version of this work was presented at ICCV2021 [3]. Following the proposed settings of SDRTVto-HDRTV, several works have investigated this problem [18], [19], [20], [21], [22]. The present work significantly improves upon the initial version in several ways.…”

mentioning

confidence: 96%

A New Journey from SDRTV to HDRTV

Chen

Zhang

Ren

et al. 2021

2021 IEEE/CVF International Conference on Computer Vision (ICCV)

View full text Add to dashboard Cite

Modern displays are capable of rendering video content with high dynamic range (HDR) and wide color gamut (WCG). However, the majority of available resources are still in standard dynamic range (SDR). As a result, there is significant value in transforming existing SDR content into the HDRTV standard. In this paper, we define and analyze the SDRTV-to-HDRTV task by modeling the formation of SDRTV/HDRTV content. Our analysis and observations indicate that a naive end-to-end supervised training pipeline suffers from severe gamut transition errors. To address this issue, we propose a novel three-step solution pipeline called HDRTVNet++, which includes adaptive global color mapping, local enhancement, and highlight refinement. The adaptive global color mapping step uses global statistics as guidance to perform image-adaptive color mapping. A local enhancement network is then deployed to enhance local details. Finally, we combine the two sub-networks above as a generator and achieve highlight consistency through GAN-based joint training. Our method is primarily designed for ultra-high-definition TV content and is therefore effective and lightweight for processing 4K resolution images. We also construct a dataset using HDR videos in the HDR10 standard, named HDRTV1K that contains 1235 and 117 training images and 117 testing images, all in 4K resolution. Besides, we select five metrics to evaluate the results of SDRTV-to-HDRTV algorithms. Our final results demonstrate state-of-the-art performance both quantitatively and visually. The code, model and dataset are available at https://github.com/xiaom233/HDRTVNet-plus.

show abstract