针对单光子传感器低帧率噪声视频，提出端到端恢复网络QUIVER。
Quanta Video Restoration
- 基于预滤波、光流估计、融合与精修的经典思路设计可训练网络
- 在2000帧/秒的高速数据集上显著优于现有方法
- 适合处理低光、高动态场景下的视频恢复任务
单光子图像传感器的普及推动了高速与低光成像应用的发展。然而，此类传感器采集的数据通常为1位或少数比特，且受噪声和强运动影响严重。传统视频修复方法不适用于此情况，而专用的量子脉冲算法在输入帧数较少时性能有限。本文提出Quanta Video Restoration（QUIVER），一个基于经典量子修复方法核心思想（预滤波、光流估计、融合与精修）的端到端可训练网络。同时，我们构建并发布了I2-2000FPS数据集，具有最高2000帧/秒的时间分辨率，用于训练与测试。在模拟与真实数据上，QUIVER显著优于现有量子恢复方法。代码与数据集见https://github.com/chennuriprateek/Quanta_Video_Restoration-QUIVER-
原文摘要 · Abstract (English)
The proliferation of single-photon image sensors has opened the door to a plethora of high-speed and low-light imaging applications. However, data collected by these sensors are often 1-bit or few-bit, and corrupted by noise and strong motion. Conventional video restoration methods are not designed to handle this situation, while specialized quanta burst algorithms have limited performance when the number of input frames is low. In this paper, we introduce Quanta Video Restoration (QUIVER), an end-to-end trainable network built on the core ideas of classical quanta restoration methods, i.e., pre-filtering, flow estimation, fusion, and refinement. We also collect and publish I2-2000FPS, a high-speed video dataset with the highest temporal resolution of 2000 frames-per-second, for training and testing. On simulated and real data, QUIVER outperforms existing quanta restoration methods by a significant margin. Code and dataset available at https://github.com/chennuriprateek/Quanta_Video_Restoration-QUIVER-
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。