RAFT
RAFT (Recurrent All-Pairs Field Transforms) is a deep learning-based optical flow estimation model. It constructs all-pairs correlation volumes between feature maps and iteratively updates flow fields using a recurrent unit, achieving high accuracy on standard optical flow benchmarks.
Timeline (last 90 days)
Deep learning-based optical flow estimation methods such as RAFT and FlowNet have achieved significant breakthroughs in accuracy and speed, making real-time optical flow frame interpolation possible.
光流估计（通过 RAFT、GMFlow 等算法）用于量化视频运动信息，光流均值接近零表示静态场景，方差过大意味着剧烈场景切换或抖动，这类数据不适合训练
光流计算连续两帧之间每个像素的位移向量形成稠密运动场，经典算法包括Lucas-Kanade和Horn-Schunck，RAFT等深度学习方法提升了精度
经典光流算法Lucas-Kanade基于局部约束，Horn-Schunck基于全局约束，都依赖亮度恒定假设；FlowNet（2015）首次用CNN端到端估计光流，RAFT（2020）通过全对相关体积改进
FlowNet于2015年首次用卷积神经网络端到端估计光流，RAFT于2020年通过全对相关体积并迭代优化大幅提升光流估计精度
All Facts (5)
Deep learning-based optical flow estimation methods such as RAFT and FlowNet have achieved significant breakthroughs in accuracy and speed, making real-time optical flow frame interpolation possible.
50%Unverified光流估计（通过 RAFT、GMFlow 等算法）用于量化视频运动信息，光流均值接近零表示静态场景，方差过大意味着剧烈场景切换或抖动，这类数据不适合训练
50%Unverified光流计算连续两帧之间每个像素的位移向量形成稠密运动场，经典算法包括Lucas-Kanade和Horn-Schunck，RAFT等深度学习方法提升了精度
50%Unverified经典光流算法Lucas-Kanade基于局部约束，Horn-Schunck基于全局约束，都依赖亮度恒定假设；FlowNet（2015）首次用CNN端到端估计光流，RAFT（2020）通过全对相关体积改进
50%UnverifiedFlowNet于2015年首次用卷积神经网络端到端估计光流，RAFT于2020年通过全对相关体积并迭代优化大幅提升光流估计精度
50%