Omniscient Video Super-Resolution

This is the official code of OVSR (Omniscient Video Super-Resolution, ICCV 2021). This work is based on PFNL.

Datasets

Please refer to PFNL for the datasets (train, eval and test). Please modify the datapath in ./data/*.txt according to your machine.

Pre-Trained Models

Download the pre-trained models from mainland China with password: inub, or elsewhere.

Code

It should be easy to use train.sh or main.py for training or testing, note to change the hyper-parameters in options/ovsr.yml .

Environment

Python >= 3.6
PyTorch, tested on 1.9, but should be fine when >=1.6

Citation

If you find our code or datasets helpful, please consider citing our related works.

@InProceedings{Yi_2021_ICCV_OVSR,
    author    = {Yi, Peng and Wang, Zhongyuan and Jiang, Kui and Jiang, Junjun and Lu, Tao and Tian, Xin and Ma, Jiayi},
    title     = {Omniscient Video Super-Resolution},
    booktitle = {IEEE/CVF International Conference on Computer Vision (ICCV)},
    month     = {October},
    year      = {2021},
    pages     = {4429-4438}
}

@ARTICLE{MSHPFNL,
  author={Yi, Peng and Wang, Zhongyuan and Jiang, Kui and Jiang, Junjun and Lu, Tao and Ma, Jiayi},
  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence}, 
  title={A Progressive Fusion Generative Adversarial Network for Realistic and Consistent Video Super-Resolution}, 
  year={2020},
  volume={},
  number={},
  pages={},
  doi={10.1109/TPAMI.2020.3042298}
}

Contact

If you have questions or suggestions, please open an issue here or send an email to [email protected].

Omniscient Video Super-Resolution

Related tags

Overview

Omniscient Video Super-Resolution

Datasets

Pre-Trained Models

Code

Environment

Citation

Contact

Owner

Rethinking Transformer-based Set Prediction for Object Detection

[ICLR 2021] Heteroskedastic and Imbalanced Deep Learning with Adaptive Regularization

Flow is a computational framework for deep RL and control experiments for traffic microsimulation.

A naive ROS interface for visualDet3D.

Official implementation of UTNet: A Hybrid Transformer Architecture for Medical Image Segmentation

Kaggle Ultrasound Nerve Segmentation competition [Keras]

NeuralTalk is a Python+numpy project for learning Multimodal Recurrent Neural Networks that describe images with sentences.

DPT: Deformable Patch-based Transformer for Visual Recognition (ACM MM2021)

NeurIPS-2021: Neural Auto-Curricula in Two-Player Zero-Sum Games.

Adversarial Autoencoders

Open source Python module for computer vision

Symbolic Parallel Adaptive Importance Sampling for Probabilistic Program Analysis in JAX

Single/multi view image(s) to voxel reconstruction using a recurrent neural network

A universal framework for learning timestamp-level representations of time series

Y. Zhang, Q. Yao, W. Dai, L. Chen. AutoSF: Searching Scoring Functions for Knowledge Graph Embedding. IEEE International Conference on Data Engineering (ICDE). 2020

[CVPR 2021] Few-shot 3D Point Cloud Semantic Segmentation

Example scripts for the detection of lanes using the ultra fast lane detection model in ONNX.

Deep Illuminator is a data augmentation tool designed for image relighting. It can be used to easily and efficiently generate a wide range of illumination variants of a single image.

PyTorch code of my ICDAR 2021 paper Vision Transformer for Fast and Efficient Scene Text Recognition (ViTSTR)

A collection of resources on GAN Inversion.