The Eleventh NTIRE 2026 Efficient Super-Resolution Challenge Report
It benchmarks state-of-the-art methods for efficient super-resolution, which is important for researchers and practitioners in image processing, but is incremental as it reports on an existing challenge.
The paper reviews the NTIRE 2026 challenge on efficient single-image super-resolution, where participants aimed to reduce runtime, parameters, or FLOPs while maintaining PSNR around 26.90-26.99 dB on DIV2K datasets, with 95 registrants and 15 valid submissions.
This paper reviews the NTIRE 2026 challenge on efficient single-image super-resolution with a focus on the proposed solutions and results. The aim of this challenge is to devise a network that reduces one or several aspects, such as runtime, parameters, and FLOPs, while maintaining PSNR of around 26.90 dB on the DIV2K_LSDIR_valid dataset, and 26.99 dB on the DIV2K_LSDIR_test dataset. The challenge had 95 registered participants, and 15 teams made valid submissions. They gauge the state-of-the-art results for efficient single-image super-resolution.