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.
The code for CVPR21 paper "Deep Animation Video Interpolation in the Wild"
Source code for AAAI 2020 paper "Channel Attention Is All You Need for Video Frame Interpolation"
[ICCV 2021, Oral 3%] Official repository of XVFI
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)
FluidFrames.RIFE | video AI frame-generation app
Official PyTorch implementation of "Deep Slow Motion Video Reconstruction with Hybrid Imaging System" (TPAMI)
Source code for CVPR 2020 paper "Scene-Adaptive Video Frame Interpolation via Meta-Learning"
[AAAI 2020] Official repository of FISR.
[ECCV2022] Animation from Blur: Multi-modal Blur Decomposition with Motion Guidance
Tensorflow 2 implementation of Super SloMo paper
Official MegEngine Implementation of Real-Time Intermediate Flow Estimation for Video Frame Interpolation
A clumsy video auto duplication remove and frame interpolate script (mainly for 24fps cfr animation with dup-frames)
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.
Frame Interpolation Refined with Stable Diffusion via Control Net
Video frame interpolation using RIFE