Evaluation Pipeline for our ECCV2020: Journey Towards Tiny Perceptual Super-Resolution.

Royson

Last update: Mar 30, 2022

Related tags

Deep Learning tpsr

Overview

Journey Towards Tiny Perceptual Super-Resolution

Test code for our ECCV2020 paper: https://arxiv.org/abs/2007.04356

Our x4 upscaling pre-trained models, namely TPSR_NOGAN, TPSR_ESRGAN, and TPSR_D2, are in the folder 'pretrained'.

The evaluate.py script runs the evaluation pipeline on the images in 'input_images' ('Set5' by default) and evaluates the PSNR against the ground truth in 'ground_truth' folder.

Upsampled images are saved in 'output_images'.

Examples:

Evaluating PSNR using TPSR_D2 on Set5: python evaluate.py --model pretrained/TPSR_D2X4.pt
Getting output images using your own input images in the 'input_images' folder using TPSR_D2 (No evaluation) python evaluate.py --model pretrained/TPSR_D2X4.pt --ground_truth ''

Citation:

Please consider citing our paper if you find it helpful:

@article{Lee2020JourneyTT,
  title={Journey Towards Tiny Perceptual Super-Resolution},
  author={Royson Lee and L. Dudziak and M. Abdelfattah and Stylianos I. Venieris and H. Kim and Hongkai Wen and N. Lane},
  journal={ECCV},
  year={2020}
}

Comments

how to use my own data to evaluate your code

Hi, I am trying to use this code for my image with low resolution to enlarge high resolution. But, when I typed in python evaluate.py --model pretrained/TPSR_D2X4.pt --ground_truth 'my file name' it is not working. i changed png --> jpg in your code. and make same file name in input folder. Help me

Thanks,

opened by john09282922 6

Official implementation of "Not only Look, but also Listen: Learning Multimodal Violence Detection under Weak Supervision" ECCV2020

XDVioDet Official implementation of "Not only Look, but also Listen: Learning Multimodal Violence Detection under Weak Supervision" ECCV2020. The proj

64 Dec 12, 2022

PyTorch reimplementation of hand-biomechanical-constraints (ECCV2020)

Hand Biomechanical Constraints Pytorch Unofficial PyTorch reimplementation of Hand-Biomechanical-Constraints (ECCV2020). This project reimplement foll

59 Dec 20, 2022

Code for "Learning Canonical Representations for Scene Graph to Image Generation", Herzig & Bar et al., ECCV2020

Learning Canonical Representations for Scene Graph to Image Generation (ECCV 2020) Roei Herzig*, Amir Bar*, Huijuan Xu, Gal Chechik, Trevor Darrell, A

24 Jul 7, 2022

From Fidelity to Perceptual Quality: A Semi-Supervised Approach for Low-Light Image Enhancement (CVPR'2020)

Under-exposure introduces a series of visual degradation, i.e. decreased visibility, intensive noise, and biased color, etc. To address these problems, we propose a novel semi-supervised learning approach for low-light image enhancement.

117 Jan 3, 2023

This is the official repository for evaluation on the NoW Benchmark Dataset. The goal of the NoW benchmark is to introduce a standard evaluation metric to measure the accuracy and robustness of 3D face reconstruction methods from a single image under variations in viewing angle, lighting, and common occlusions.

NoW Evaluation This is the official repository for evaluation on the NoW Benchmark Dataset. The goal of the NoW benchmark is to introduce a standard e

71 Dec 30, 2022

ICCV2021 - A New Journey from SDRTV to HDRTV.

Evaluation Pipeline for our ECCV2020: Journey Towards Tiny Perceptual Super-Resolution.

Related tags

Overview

Journey Towards Tiny Perceptual Super-Resolution

Examples:

Citation:

You might also like...

Official implementation of "Not only Look, but also Listen: Learning Multimodal Violence Detection under Weak Supervision" ECCV2020

PyTorch reimplementation of hand-biomechanical-constraints (ECCV2020)

Code for "Learning Canonical Representations for Scene Graph to Image Generation", Herzig & Bar et al., ECCV2020

From Fidelity to Perceptual Quality: A Semi-Supervised Approach for Low-Light Image Enhancement (CVPR'2020)

ICCV2021 - A New Journey from SDRTV to HDRTV.

Towards Ultra-Resolution Neural Style Transfer via Thumbnail Instance Normalization

Super-Fast-Adversarial-Training - A PyTorch Implementation code for developing super fast adversarial training

A framework for joint super-resolution and image synthesis, without requiring real training data

Comments

how to use my own data to evaluate your code

Owner

Royson

The project covers common metrics for super-resolution performance evaluation.

Evaluation and Benchmarking of Speech Super-resolution Methods

Source code for our paper "Learning to Break Deep Perceptual Hashing: The Use Case NeuralHash"

PyTorch code for our paper "Attention in Attention Network for Image Super-Resolution"

PyTorch code for our paper "Image Super-Resolution with Non-Local Sparse Attention" (CVPR2021).

PyTorch code for our ECCV 2020 paper "Single Image Super-Resolution via a Holistic Attention Network"

PyTorch code for our ECCV 2018 paper "Image Super-Resolution Using Very Deep Residual Channel Attention Networks"

Implementation for our ICCV 2021 paper: Dual-Camera Super-Resolution with Aligned Attention Modules

Implementation for our ICCV 2021 paper: Dual-Camera Super-Resolution with Aligned Attention Modules

Code for the ECCV2020 paper "A Differentiable Recurrent Surface for Asynchronous Event-Based Data"