# 视频插帧--Video Frame Interpolation via Adaptive Convolution

Given two video frames I1and I2, our method aims to interpolate a frame ˆI temporally in the middle of the two input frames

3 Video Frame Interpolation 传统的帧插值方法是 two-step approach： first estimates motion between two frames and then interpolates the pixel color based on the motion 但是光流的计算很容易不稳定 optical flow is not reliable due to occlusion, motion blur, and lack of texture

3.1. Convolution kernel estimation 卷积核估计 这里我们使用一个 CNN 网络来 estimate a proper convolutional kernel to synthesize each output pixel in the interpolated images.

In our implementation, the default receptive field size is 79 × 79 pixels. The convolution patch size is 41×41 and the kernel size is 41 × 82 as it is used to convolve with two patches

Loss function 这里我们分别设计了 color loss 和 gradient loss，最终的损失函数是 combine the above color and gradient loss as our final loss

4 Experiments Qualitative evaluation on blurry videos

Evaluation on the Middlebury testing set

Qualitative evaluation on video with abrupt brightness change

Qualitative evaluation with respect to occlusion

On a single Nvidia Titan X, this implementation takes about 2.8 seconds with 3.5 gigabytes of memory for a 640 × 480 image, and 9.1 seconds with 4.7 gigabytes for 1280×720, and 21.6 seconds with 6.8 gigabytes for 1920 × 1080.

0 条评论

## 相关文章

### 【干货】Lossless Triplet Loss: 一种高效的Siamese网络损失函数

【导读】本文是数据科学家Marc-Olivier Arsenault撰写的一篇博文，主要讲解了在Siamese网络中使用Lossless Triplet Los...

6356

4055

### TensorFlow 深度学习笔记 从线性分类器到深度神经网络

Limit of Linear Model 实际要调整的参数很多 ? 如果有N个Class，K个Label，需要调整的参数就有(N+1)K个 Linear...

2669

### CS231n 课后作业第二讲 : Assignment 2（含代码实现）| 分享总结

CS231n 是斯坦福大学开设的计算机视觉与深度学习的入门课程，授课内容在国内外颇受好评。其配套的课后作业质量也颇高，因此雷锋网 AI 研习社在近期的线上公开...

44010

7744

6009

3506

### 2.3 模型相关

covariance stationary：一个时间序列，均值，方差，协方差不随时间而变化 上面的模型都和两维度有关： 1. 数据相互关联的程度 2. 稳定性

1572

1163

4449