Light-VQA：面向低光视频增强的多维质量评估模型
Light-VQA: A Multi-Dimensional Quality Assessment Model for Low-Light Video Enhancement
AI总结：
本文针对低光视频增强质量评估缺失问题，构建LLVE-QA数据集并提出Light-VQA模型，通过融合手工设计的亮度、噪声、帧间亮度一致性特征与深度学习时空特征，在多个数据集上取得最优性能。
摘要：
近年来，用户生成内容（UGC）视频在我们的日常生活中变得无处不在。然而，由于拍摄设备和技术的限制，UGC视频往往包含各种退化，其中视觉上最不利的影响之一是曝光不足。因此，人们提出了相应的视频增强算法，如低光视频增强（LLVE），以处理这种特定的退化。然而，与视频增强算法不同，几乎所有现有的视频质量评估（VQA）模型都是通用构建的，而非专门构建的，它们从综合角度衡量视频质量。据我们所知，目前还没有专门为LLVE算法增强的视频设计的VQA模型。为此，我们首先构建了一个低光视频增强质量评估（LLVE-QA）数据集，其中收集了254个原始低光视频，然后利用8种LLVE算法进行增强，共获得2060个视频。此外，我们提出了一个专门用于LLVE的质量评估模型，名为Light-VQA。更具体地说，由于亮度和噪声对低光增强VQA的影响最大，我们手工设计了相应的特征，并将其与基于深度学习的语义特征整合为整体空间信息。对于时间信息，除了基于深度学习的运动特征外，我们还研究了视频帧之间手工设计的亮度一致性，整体时间信息是它们的拼接。随后，空间和时间信息被融合以获得视频的质量感知表示。大量实验结果表明，我们的Light-VQA在LLVE-QA和公共数据集上相对于当前最先进（SOTA）方法取得了最佳性能。数据集和代码可在https://github.com/wenzhouyidu/Light-VQA找到。
英文摘要：
Recently, Users Generated Content (UGC) videos becomes ubiquitous in our daily lives. However, due to the limitations of photographic equipments and techniques, UGC videos often contain various degradations, in which one of the most visually unfavorable effects is the underexposure. Therefore, corresponding video enhancement algorithms such as Low-Light Video Enhancement (LLVE) have been proposed to deal with the specific degradation. However, different from video enhancement algorithms, almost all existing Video Quality Assessment (VQA) models are built generally rather than specifically, which measure the quality of a video from a comprehensive perspective. To the best of our knowledge, there is no VQA model specially designed for videos enhanced by LLVE algorithms. To this end, we first construct a Low-Light Video Enhancement Quality Assessment (LLVE-QA) dataset in which 254 original low-light videos are collected and then enhanced by leveraging 8 LLVE algorithms to obtain 2,060 videos in total. Moreover, we propose a quality assessment model specialized in LLVE, named Light-VQA. More concretely, since the brightness and noise have the most impact on low-light enhanced VQA, we handcraft corresponding features and integrate them with deep-learning-based semantic features as the overall spatial information. As for temporal information, in addition to deep-learning-based motion features, we also investigate the handcrafted brightness consistency among video frames, and the overall temporal information is their concatenation. Subsequently, spatial and temporal information is fused to obtain the quality-aware representation of a video. Extensive experimental results show that our Light-VQA achieves the best performance against the current State-Of-The-Art (SOTA) on LLVE-QA and public dataset. Dataset and Codes can be found at https://github.com/wenzhouyidu/Light-VQA.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
