Efficient HDR Reconstruction from Real-World Raw Images
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918328981782528 |
|---|---|
| author | Yang, Qirui Liu, Yihao Cheng, Qihua Yue, Huanjing Li, Kun Yang, Jingyu |
| author_facet | Yang, Qirui Liu, Yihao Cheng, Qihua Yue, Huanjing Li, Kun Yang, Jingyu |
| contents | The growing prevalence of high-resolution displays on edge devices has created a pressing need for efficient high dynamic range (HDR) imaging algorithms. However, most existing HDR methods either struggle to deliver satisfactory visual quality or incur high computational and memory costs, limiting their applicability to high-resolution inputs (typically exceeding 12 megapixels). Furthermore, current HDR dataset collection approaches are often labor-intensive and inefficient. In this work, we explore a novel and practical solution for HDR reconstruction directly from raw sensor data, aiming to enhance both performance and deployability on mobile platforms. Our key insights are threefold: (1) we propose RepUNet, a lightweight and efficient HDR network leveraging structural re-parameterization for fast and robust inference; (2) we design a new computational raw HDR data formation pipeline and construct a new raw HDR dataset, RealRaw-HDR; (3) we design a plug-and-play motion alignment loss to suppress ghosting artifacts under constrained bandwidth conditions effectively. Our model contains fewer than 830K parameters and takes less than 3 ms to process an image of 4K resolution using one RTX 3090 GPU. While being highly efficient, our model also achieves comparable performance to state-of-the-art HDR methods in terms of PSNR, SSIM, and a color difference metric. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2306_10311 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Efficient HDR Reconstruction from Real-World Raw Images Yang, Qirui Liu, Yihao Cheng, Qihua Yue, Huanjing Li, Kun Yang, Jingyu Image and Video Processing Computer Vision and Pattern Recognition The growing prevalence of high-resolution displays on edge devices has created a pressing need for efficient high dynamic range (HDR) imaging algorithms. However, most existing HDR methods either struggle to deliver satisfactory visual quality or incur high computational and memory costs, limiting their applicability to high-resolution inputs (typically exceeding 12 megapixels). Furthermore, current HDR dataset collection approaches are often labor-intensive and inefficient. In this work, we explore a novel and practical solution for HDR reconstruction directly from raw sensor data, aiming to enhance both performance and deployability on mobile platforms. Our key insights are threefold: (1) we propose RepUNet, a lightweight and efficient HDR network leveraging structural re-parameterization for fast and robust inference; (2) we design a new computational raw HDR data formation pipeline and construct a new raw HDR dataset, RealRaw-HDR; (3) we design a plug-and-play motion alignment loss to suppress ghosting artifacts under constrained bandwidth conditions effectively. Our model contains fewer than 830K parameters and takes less than 3 ms to process an image of 4K resolution using one RTX 3090 GPU. While being highly efficient, our model also achieves comparable performance to state-of-the-art HDR methods in terms of PSNR, SSIM, and a color difference metric. |
| title | Efficient HDR Reconstruction from Real-World Raw Images |
| topic | Image and Video Processing Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2306.10311 |