混合模型提升视频帧预测，3D CNN与ConvLSTM表现最佳
Benefits of Feature Extraction and Temporal Sequence Analysis for Video Frame Prediction: An Evaluation of Hybrid Deep Learning Models
- 用自编码器提取特征，结合RNN、3D CNN等建模时间序列
- SSIM从0.69升至0.82，真实灰度视频预测最易
- 适合做视频压缩、自动驾驶等场景的算法研发者
近年来，人工智能在计算机视觉领域取得显著进展，推动了视频帧预测等复杂问题的解决。该任务在气象预报、自动驾驶中具有重要应用，并可提升视频压缩与流媒体技术。本文评估了多种融合自编码器特征提取与循环神经网络（RNN）、3D卷积神经网络（3D CNN）及类似结构的混合深度学习模型。在三个不同数据集上进行了严格测试，涵盖合成与真实场景、灰度与彩色图像。结果表明，结合3D CNN与ConvLSTM的混合模型效果最优，整体结构相似性（SSIM）从0.69提升至0.82；真实世界灰度视频的预测难度最低。
原文摘要 · Abstract (English)
In recent years, advances in Artificial Intelligence have significantly impacted computer science, particularly in the field of computer vision, enabling solutions to complex problems such as video frame prediction. Video frame prediction has critical applications in weather forecasting or autonomous systems and can provide technical improvements, such as video compression and streaming. Among Artificial Intelligence methods, Deep Learning has emerged as highly effective for solving vision-related tasks, although current frame prediction models still have room for enhancement. This paper evaluates several hybrid deep learning approaches that combine the feature extraction capabilities of autoencoders with temporal sequence modelling using Recurrent Neural Networks (RNNs), 3D Convolutional Neural Networks (3D CNNs), and related architectures. The proposed solutions were rigorously evaluated on three datasets that differ in terms of synthetic versus real-world scenarios and grayscale versus color imagery. Results demonstrate that the approaches perform well, with SSIM metrics increasing from 0.69 to 0.82, indicating that hybrid models utilizing 3DCNNs and ConvLSTMs are the most effective, and greyscale videos with real data are the easiest to predict.
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。