Search papers, labs, and topics across Lattice.
The NTIRE 2026 image super-resolution challenge benchmarked methods for 4x upsampling using two tracks: restoration (PSNR-focused) and perceptual quality. A total of 31 teams competed, submitting solutions evaluated on a unified dataset and protocol. The challenge results highlight the state-of-the-art in image super-resolution and provide a comparative analysis of different approaches.
A unified benchmark reveals the trade-offs between pixel-wise accuracy and perceptual realism in state-of-the-art image super-resolution techniques.
This paper presents the NTIRE 2026 image super-resolution ($\times$4) challenge, one of the associated competitions of the NTIRE 2026 Workshop at CVPR 2026. The challenge aims to reconstruct high-resolution (HR) images from low-resolution (LR) inputs generated through bicubic downsampling with a $\times$4 scaling factor. The objective is to develop effective super-resolution solutions and analyze recent advances in the field. To reflect the evolving objectives of image super-resolution, the challenge includes two tracks: (1) a restoration track, which emphasizes pixel-wise fidelity and ranks submissions based on PSNR; and (2) a perceptual track, which focuses on visual realism and evaluates results using a perceptual score. A total of 194 participants registered for the challenge, with 31 teams submitting valid entries. This report summarizes the challenge design, datasets, evaluation protocol, main results, and methods of participating teams. The challenge provides a unified benchmark and offers insights into current progress and future directions in image super-resolution.
