Towards Efficient SDRTV-to-HDRTV by Learning from Image Formation
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2023
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910612902117376 |
|---|---|
| author | Chen, Xiangyu Li, Zheyuan Zhang, Zhengwen Ren, Jimmy S. Liu, Yihao He, Jingwen Qiao, Yu Zhou, Jiantao Dong, Chao |
| author_facet | Chen, Xiangyu Li, Zheyuan Zhang, Zhengwen Ren, Jimmy S. Liu, Yihao He, Jingwen Qiao, Yu Zhou, Jiantao Dong, Chao |
| contents | Modern displays can render video content with high dynamic range (HDR) and wide color gamut (WCG). However, most resources are still in standard dynamic range (SDR). Therefore, transforming existing SDR content into the HDRTV standard holds significant value. This paper defines and analyzes the SDRTV-to-HDRTV task by modeling the formation of SDRTV/HDRTV content. Our findings reveal that a naive endto-end supervised training approach suffers from severe gamut transition errors. To address this, we propose a new three-step solution called HDRTVNet++, which includes adaptive global color mapping, local enhancement, and highlight refinement. The adaptive global color mapping step utilizes global statistics for image-adaptive color adjustments. A local enhancement network further enhances details, and the two sub-networks are combined as a generator to achieve highlight consistency through GANbased joint training. Designed for ultra-high-definition TV content, our method is both effective and lightweight for processing 4K resolution images. We also constructed a dataset using HDR videos in the HDR10 standard, named HDRTV1K, containing 1235 training and 117 testing images, all in 4K resolution. Additionally, we employ five metrics to evaluate SDRTV-to-HDRTV performance. Our results demonstrate state-of-the-art performance both quantitatively and visually. The codes and models are available at https://github.com/xiaom233/HDRTVNet-plus. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2309_04084 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Towards Efficient SDRTV-to-HDRTV by Learning from Image Formation Chen, Xiangyu Li, Zheyuan Zhang, Zhengwen Ren, Jimmy S. Liu, Yihao He, Jingwen Qiao, Yu Zhou, Jiantao Dong, Chao Computer Vision and Pattern Recognition Multimedia Image and Video Processing Modern displays can render video content with high dynamic range (HDR) and wide color gamut (WCG). However, most resources are still in standard dynamic range (SDR). Therefore, transforming existing SDR content into the HDRTV standard holds significant value. This paper defines and analyzes the SDRTV-to-HDRTV task by modeling the formation of SDRTV/HDRTV content. Our findings reveal that a naive endto-end supervised training approach suffers from severe gamut transition errors. To address this, we propose a new three-step solution called HDRTVNet++, which includes adaptive global color mapping, local enhancement, and highlight refinement. The adaptive global color mapping step utilizes global statistics for image-adaptive color adjustments. A local enhancement network further enhances details, and the two sub-networks are combined as a generator to achieve highlight consistency through GANbased joint training. Designed for ultra-high-definition TV content, our method is both effective and lightweight for processing 4K resolution images. We also constructed a dataset using HDR videos in the HDR10 standard, named HDRTV1K, containing 1235 training and 117 testing images, all in 4K resolution. Additionally, we employ five metrics to evaluate SDRTV-to-HDRTV performance. Our results demonstrate state-of-the-art performance both quantitatively and visually. The codes and models are available at https://github.com/xiaom233/HDRTVNet-plus. |
| title | Towards Efficient SDRTV-to-HDRTV by Learning from Image Formation |
| topic | Computer Vision and Pattern Recognition Multimedia Image and Video Processing |
| url | https://arxiv.org/abs/2309.04084 |