CVIVApr 14, 2025

The Tenth NTIRE 2025 Efficient Super-Resolution Challenge Report

arXiv:2504.10686v132 citationsh-index: 982025 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
Originality Synthesis-oriented
AI Analysis

This challenge advances efficient super-resolution techniques for image processing applications, but it is incremental as it builds on existing benchmarks and methods.

The paper reviews the NTIRE 2025 Efficient Super-Resolution Challenge, which aimed to develop deep models optimizing runtime, parameters, and FLOPs while achieving PSNR targets of at least 26.90 dB and 26.99 dB on validation and test datasets, with 43 teams submitting valid entries.

This paper presents a comprehensive review of the NTIRE 2025 Challenge on Single-Image Efficient Super-Resolution (ESR). The challenge aimed to advance the development of deep models that optimize key computational metrics, i.e., runtime, parameters, and FLOPs, while achieving a PSNR of at least 26.90 dB on the $\operatorname{DIV2K\_LSDIR\_valid}$ dataset and 26.99 dB on the $\operatorname{DIV2K\_LSDIR\_test}$ dataset. A robust participation saw \textbf{244} registered entrants, with \textbf{43} teams submitting valid entries. This report meticulously analyzes these methods and results, emphasizing groundbreaking advancements in state-of-the-art single-image ESR techniques. The analysis highlights innovative approaches and establishes benchmarks for future research in the field.

Code Implementations3 repos
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes