BVI-RLV：一个完全配准的低光视频增强数据集
BVI-RLV: A Fully Registered Dataset for Low-Light Video Enhancement
AI总结：
针对低光视频增强中缺乏像素对齐训练数据的问题，提出了BVI-RLV数据集，通过电动滑轨和图像优化实现亚像素配准，并基于CNN、Transformer、Mamba和扩散模型提供基线，实验证明配准对监督学习至关重要。
摘要：
低光视频通常表现出时空不连贯的噪声，损害可见性并降低计算机视觉应用的性能。使用深度学习增强此类内容的一个主要挑战在于缺乏像素对齐的高质量训练数据。我们引入了BVI-RLV，一个完全配准的低光视频数据集，包含来自40个不同场景的超过3万对帧，在两种低光条件下，每个帧都与正常光照的真实值对齐。与依赖中性密度（ND）滤波器或存在未对齐问题的现有数据集不同，BVI-RLV通过使用电动滑轨和基于图像的优化，在动态运动场景下实现了全高清分辨率下99.24%数据的亚像素配准。该数据集涵盖了广泛的运动类型和真实的时间噪声。我们还提供了使用四种代表性架构的基线实现：卷积神经网络（CNN）、Transformer、状态空间模型（Mamba）和扩散模型（DM）。实验表明，配准对于监督学习至关重要，与未配准训练相比，PSNR提升高达5.85 dB。在跨数据集评估中，基于BVI-RLV训练的模型优于基于现有数据集训练的模型，即使在真实户外场景中也取得了优越性能。我们的数据集公开于https://doi.org/10.21227/mzny-8c77。
英文摘要：
Low-light videos often exhibit spatiotemporally incoherent noise, compromising visibility and degrading performance in computer vision applications. A major challenge for enhancing such content using deep learning lies in the scarcity of pixel-aligned, high-quality training data. We introduce BVI-RLV, a fully registered low-light video dataset comprising over 30k paired frames from 40 diverse scenes under two low-light conditions, each aligned with normal-light ground truth. Unlike existing datasets that rely on neutral density (ND) filters or suffer from misalignment issues, BVI-RLV achieves sub-pixel registration for 99.24% of data at full HD resolution across dynamic motion scenarios using a motorized dolly and image-based refinement. The dataset covers a wide range of motion types and realistic temporal noise. We also provide baseline implementations using four representative architectures: Convolutional Neural Network (CNN), Transformer, State Space Model (Mamba), and Diffusion Model (DM). Experiments demonstrate that registration is crucial for supervised learning, yielding up to 5.85 dB PSNR improvement compared to unregistered training. Models trained on BVI-RLV outperform those trained on existing datasets in cross-dataset evaluations, achieving superior performance even in real-world outdoor scenes. Our dataset is publicly available at https://doi.org/10.21227/mzny-8c77.
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。
