用历史数据预测缺失帧段，实现网络受限下的视频完整重建
FrameCorr: Adaptive, Autoencoder-based Neural Compression for Video Reconstruction in Resource and Timing Constrained Network Settings
- 基于自编码器的自适应压缩，利用已接收数据预测丢失帧段
- 在部分数据丢失条件下仍可完成高质量视频帧重建
- 适合带宽受限、实时性要求高的物联网视频传输场景
尽管物联网（IoT）设备因成本低而被广泛用于视频处理，但将捕获的数据传送到附近服务器时，常面临网络带宽稀缺和时间约束不一的问题。现有视频压缩方法在数据不完整时难以恢复。本文提出FrameCorr，一种基于深度学习的解决方案，利用先前接收到的数据预测缺失帧段，从而实现从部分接收数据中重建完整帧。该方法通过自编码器架构自适应地处理不同丢包情况，显著提升在资源与时间受限网络环境中的视频重建质量。
原文摘要 · Abstract (English)
Despite the growing adoption of video processing via Internet of Things (IoT) devices due to their cost-effectiveness, transmitting captured data to nearby servers poses challenges due to varying timing constraints and scarcity of network bandwidth. Existing video compression methods face difficulties in recovering compressed data when incomplete data is provided. Here, we introduce FrameCorr, a deep-learning based solution that utilizes previously received data to predict the missing segments of a frame, enabling the reconstruction of a frame from partially received data.
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。