Burst Image Quality Assessment: A New Benchmark and Unified Framework for Multiple Downstream Tasks

2025-11-11

AI Summary

To address the substantial storage overhead, low transmission efficiency, and degraded downstream task performance caused by redundancy in burst image sequences, this paper introduces, for the first time, a task-driven Burst Image Quality Assessment (BuIQA) problem. We construct the first large-scale benchmark dataset—comprising 45,000 images spanning ten diverse downstream tasks—and propose a unified evaluation framework. This framework jointly optimizes a task-aware prompt generation network and a quality assessment network via heterogeneous knowledge distillation, enabling cross-scenario adaptation. Our method accurately models frame-level, task-relevant quality, effectively selecting high-quality frames for applications such as denoising and super-resolution. Experimental results demonstrate a PSNR improvement of 0.33 dB over state-of-the-art methods, validating both the efficacy and practical utility of the proposed approach.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Search and Optimization: Distributed Search
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Web Mining and Content Analysis: Web data quality in the era of algorithmically-generated content

Abstract

In recent years, the development of burst imaging technology has improved the capture and processing capabilities of visual data, enabling a wide range of applications. However, the redundancy in burst images leads to the increased storage and transmission demands, as well as reduced efficiency of downstream tasks. To address this, we propose a new task of Burst Image Quality Assessment (BuIQA), to evaluate the task-driven quality of each frame within a burst sequence, providing reasonable cues for burst image selection. Specifically, we establish the first benchmark dataset for BuIQA, consisting of $7,346$ burst sequences with $45,827$ images and $191,572$ annotated quality scores for multiple downstream scenarios. Inspired by the data analysis, a unified BuIQA framework is proposed to achieve an efficient adaption for BuIQA under diverse downstream scenarios. Specifically, a task-driven prompt generation network is developed with heterogeneous knowledge distillation, to learn the priors of the downstream task. Then, the task-aware quality assessment network is introduced to assess the burst image quality based on the task prompt. Extensive experiments across 10 downstream scenarios demonstrate the impressive BuIQA performance of the proposed approach, outperforming the state-of-the-art. Furthermore, it can achieve $0.33$ dB PSNR improvement in the downstream tasks of denoising and super-resolution, by applying our approach to select the high-quality burst frames.

Problem

• Assessing task-driven quality in burst image sequences
• Reducing storage demands from redundant burst imaging
• Improving efficiency of downstream visual processing tasks

Innovation

• Task-driven prompt generation with knowledge distillation
• Task-aware quality assessment network for burst images
• Unified framework adapting to multiple downstream scenarios