The DIV2K Dataset is a comprehensive collection of high-resolution RGB images used for NTIRE and PIRM challenges, designed to support image super-resolution research and development. It includes a diverse range of contents with the following divisions:
Download Dataset
Train Data:
800 high-definition images
Corresponding low-resolution images with downscaling factors of 2, 3, and 4
Validation Data:
100 high-definition images
Corresponding low-resolution images available from the beginning of the challenge
High-resolution images released at the final challenge phase
Test Data:
100 diverse images
Low-resolution images provided for final evaluation
Results announced post-challenge
Contact Us
Quality Data Creation
Guaranteed TAT
ISO 9001:2015, ISO/IEC 27001:2013 Certified
HIPAA Compliance
GDPR Compliance
Compliance and Security
Let's Discuss your Data collection
Requirement With Us
To get a detailed estimation of requirements please reach us.