Add "RENOIR" dataset

[FedericoCalandra]

1. Smartphone Image Denoising Dataset (SIDD)

160 image pairs (noisy and ground-truth) representing 160 scene instances. These images can be used for training/learning purposes.

For each image, the following is provided:

Noisy Raw-RGB image (.MAT). Ground truth Raw-RGB image (.MAT). Noisy sRGB image (.PNG). Ground truth sRGB image (.PNG). Metadata extracted from the DNG file (.MAT).

SIDD dataset available at this link

---

2. Real Low-Light Image Noise Reduction Dataset (RENOIR)

Dataset of images corrupted by real low-light noise together with pixel and intensity aligned clean images. It contains about 500 images of 120 scenes that have been collected in low-light setting using three cameras: Cannon T3i, Cannon S90 and a Xiaomi MI3 mobile phone. The dataset is quite large since the images have the original sensor resolution, so each image has about 10 megapixels.

RENOIR dataset available at this link

[FedericoCalandra]

I datasets sono molto grandi (circa 12 GB). Meglio importare solo SIDD in versione ridotta (160 immagini). In questo caso siamo sui 6,2 GB.

[peiva-git]

I due link sono esattamente uguali, probabilmente un errore?

[FedericoCalandra]

Ho sostituito il link con quello corretto

[FedericoCalandra]

Opto per il dataset RENOIR perché SIDD viene usato per addestrare diversi modelli reali (CBDNet, NBNet) e non potremmo quindi utilizzarlo per la fase di test