Video Frame Interpolation
94 papers with code • 20 benchmarks • 12 datasets
The goal of Video Frame Interpolation is to synthesize several frames in the middle of two adjacent frames of the original video. Video Frame Interpolation can be applied to generate slow motion video, increase video frame rate, and frame recovery in video streaming.
Benchmarks
These leaderboards are used to track progress in Video Frame Interpolation
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
Libraries
Use these libraries to find Video Frame Interpolation models and implementationsDatasets
UCF101
DAVIS
GoPro
Middlebury
Vimeo90K
X4K1000FPS
MSU Video Frame Interpolation
Inter4K
SlowFlow
ATD-12K
Subtasks
Most implemented papers
MEMC-Net: Motion Estimation and Motion Compensation Driven Neural Network for Video Interpolation and Enhancement
Recently, a number of data-driven frame interpolation methods based on convolutional neural networks have been proposed.
MEMC-Net: Motion Estimation and Motion Compensation Driven Neural Network for Video Frame Interpolation and Enhancement
baowenbo/MEMC-Net
•
•
arXiv 2018
In this work, we propose a motion estimation and motion compensation driven neural network for video frame interpolation.
Variational Approach for Capsule Video Frame Interpolation
The main objective of the paper is to increase the frame rate to be closer to that of the colonoscopy.
Deep Video Frame Interpolation using Cyclic Frame Generation
alex04072000/CyclicGen
•
•
AAAI 2019
In addition to the cycle consistency loss, we propose two extensions: motion linearity loss and edge-guided training.
Event-driven Video Frame Synthesis
Temporal Video Frame Synthesis (TVFS) aims at synthesizing novel frames at timestamps different from existing frames, which has wide applications in video codec, editing and analysis.
Unsupervised Video Interpolation Using Cycle Consistency
NVIDIA/unsupervised-video-interpolation
•
•
ICCV 2019
We further introduce a pseudo supervised loss term that enforces the interpolated frames to be consistent with predictions of a pre-trained interpolation model.
AdaCoF: Adaptive Collaboration of Flows for Video Frame Interpolation
HyeongminLEE/AdaCoF-pytorch
•
•
CVPR 2020
Video frame interpolation is one of the most challenging tasks in video processing research.
FISR: Deep Joint Frame Interpolation and Super-Resolution with a Multi-scale Temporal Loss
JihyongOh/FISR
•
•
In this paper, we first propose a joint VFI-SR framework for up-scaling the spatio-temporal resolution of videos from 2K 30 fps to 4K 60 fps.
Blurry Video Frame Interpolation
laomao0/BIN
•
•
CVPR 2020
Existing works reduce motion blur and up-convert frame rate through two separate ways, including frame deblurring and frame interpolation.
Deep Slow Motion Video Reconstruction with Hybrid Imaging System
In this paper, we address this problem using two video streams as input; an auxiliary video with high frame rate and low spatial resolution, providing temporal information, in addition to the standard main video with low frame rate and high spatial resolution.
