PyTorch implementation of Super SloMo by Jiang et al.
-
Updated
Mar 9, 2023 - Python
Frame interpolation is used to increase the frame rate of a video, or to create a slow-motion video without lowering the frame rate.
PyTorch implementation of Super SloMo by Jiang et al.
FILM: Frame Interpolation for Large Motion, In ECCV 2022.
Source code for AAAI 2020 paper "Channel Attention Is All You Need for Video Frame Interpolation"
[ICCV 2021, Oral 3%] Official repository of XVFI
The code for CVPR21 paper "Deep Animation Video Interpolation in the Wild"
IFRNet: Intermediate Feature Refine Network for Efficient Frame Interpolation (CVPR 2022)
Official code for "AMT: All-Pairs Multi-Field Transforms for Efficient Frame Interpolation" (CVPR2023)
Source code for CVPR 2020 paper "Scene-Adaptive Video Frame Interpolation via Meta-Learning"
[AAAI 2020] Official repository of FISR.
FluidFrames.RIFE | video AI frame-generation app
Tensorflow 2 implementation of Super SloMo paper
Official PyTorch implementation of "Deep Slow Motion Video Reconstruction with Hybrid Imaging System" (TPAMI)
Frame Interpolation Refined with Stable Diffusion via Control Net
[ECCV2022] Animation from Blur: Multi-modal Blur Decomposition with Motion Guidance
In this repository, we deal with the task of video frame interpolation with estimated optical flow. To estimate the optical flow we use Lucas-Kanade algorithm, Multiscale Lucas-Kanade algorithm (with iterative tuning), and Discrete Horn-Schunk algorithm. We explore the interpolation performance on Spheres dataset and Corridor dataset.
PyTorch Implementation of "Robust Temporal Super-Resolution for Dynamic Motion Video", ICCVW, AIM2019
In this repository, we deal with the task of video frame interpolation with estimated optical flow. To estimate the optical flow we use pre-trained FlowNet2 deep learning model and experiment by fine-tuning it. We explore the interpolation performance on Spheres dataset and Corridor dataset.
Video frame interpolation using RIFE
A Novel Approach leveraging Auto-Encoders, LSTM Networks and Maximum Entropy Principle for Video Super-Resolution (Upscaling and Frame Interpolation)