Simple Image Signal Processing using Global Context Guidance
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866929514194403328 |
|---|---|
| author | Elezabi, Omar Conde, Marcos V. Timofte, Radu |
| author_facet | Elezabi, Omar Conde, Marcos V. Timofte, Radu |
| contents | In modern smartphone cameras, the Image Signal Processor (ISP) is the core element that converts the RAW readings from the sensor into perceptually pleasant RGB images for the end users. The ISP is typically proprietary and handcrafted and consists of several blocks such as white balance, color correction, and tone mapping. Deep learning-based ISPs aim to transform RAW images into DSLR-like RGB images using deep neural networks. However, most learned ISPs are trained using patches (small regions) due to computational limitations. Such methods lack global context, which limits their efficacy on full-resolution images and harms their ability to capture global properties such as color constancy or illumination. First, we propose a novel module that can be integrated into any neural ISP to capture the global context information from the full RAW images. Second, we propose an efficient and simple neural ISP that utilizes our proposed module. Our model achieves state-of-the-art results on different benchmarks using diverse and real smartphone images. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_11569 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Simple Image Signal Processing using Global Context Guidance Elezabi, Omar Conde, Marcos V. Timofte, Radu Computer Vision and Pattern Recognition Machine Learning Image and Video Processing In modern smartphone cameras, the Image Signal Processor (ISP) is the core element that converts the RAW readings from the sensor into perceptually pleasant RGB images for the end users. The ISP is typically proprietary and handcrafted and consists of several blocks such as white balance, color correction, and tone mapping. Deep learning-based ISPs aim to transform RAW images into DSLR-like RGB images using deep neural networks. However, most learned ISPs are trained using patches (small regions) due to computational limitations. Such methods lack global context, which limits their efficacy on full-resolution images and harms their ability to capture global properties such as color constancy or illumination. First, we propose a novel module that can be integrated into any neural ISP to capture the global context information from the full RAW images. Second, we propose an efficient and simple neural ISP that utilizes our proposed module. Our model achieves state-of-the-art results on different benchmarks using diverse and real smartphone images. |
| title | Simple Image Signal Processing using Global Context Guidance |
| topic | Computer Vision and Pattern Recognition Machine Learning Image and Video Processing |
| url | https://arxiv.org/abs/2404.11569 |