NTIRE 2025 Challenge on Efficient Burst HDR and Restoration: Datasets, Methods, and Results

TL;DR

This paper presents the NTIRE 2025 challenge focused on developing efficient multi-frame HDR and restoration methods using a new RAW dataset, highlighting innovative solutions that balance performance and computational constraints.

Contribution

It introduces a novel RAW multi-frame dataset and benchmarks multiple solutions, setting new standards for efficiency and quality in burst HDR and restoration tasks.

Findings

Top method achieved 43.22 dB PSNR

217 participants registered, 6 solutions submitted

Demonstrates potential of efficient multi-frame HDR techniques

Abstract

This paper reviews the NTIRE 2025 Efficient Burst HDR and Restoration Challenge, which aims to advance efficient multi-frame high dynamic range (HDR) and restoration techniques. The challenge is based on a novel RAW multi-frame fusion dataset, comprising nine noisy and misaligned RAW frames with various exposure levels per scene. Participants were tasked with developing solutions capable of effectively fusing these frames while adhering to strict efficiency constraints: fewer than 30 million model parameters and a computational budget under 4.0 trillion FLOPs. A total of 217 participants registered, with six teams finally submitting valid solutions. The top-performing approach achieved a PSNR of 43.22 dB, showcasing the potential of novel methods in this domain. This paper provides a comprehensive overview of the challenge, compares the proposed solutions, and serves as a valuable reference for researchers and practitioners in efficient burst HDR and restoration.