An open API service indexing awesome lists of open source software.

https://github.com/prs-eth/thera

Thera: Aliasing-Free Arbitrary-Scale Super-Resolution with Neural Heat Fields
https://github.com/prs-eth/thera

Last synced: about 1 year ago
JSON representation

Thera: Aliasing-Free Arbitrary-Scale Super-Resolution with Neural Heat Fields

Awesome Lists containing this project

README

          



# Thera: Aliasing-Free Arbitrary-Scale Super-Resolution with Neural Heat Fields

**Alexander Becker❄️🔥, Rodrigo Daudt❄️🔥, Dominik Narnhofer🔥, Torben Peters🔥, Nando Metzger🔥, Jan Dirk Wegner🌶️, Konrad Schindler🔥**


❄️ Equal contribution
🔥 Photogrammetry and Remote Sensing, ETH Zurich
🌶️ Department of Mathematical Modeling and Machine Learning, University of Zurich

[![Paper](https://img.shields.io/badge/arXiv-PDF-b31b1b)](https://arxiv.org/abs/2311.17643)
[![Page](https://img.shields.io/badge/Project-Page-green)](https://therasr.github.io)
[![Hugging Face Space](https://img.shields.io/badge/🤗%20Hugging%20Face-Space-yellow)](https://huggingface.co/spaces/prs-eth/thera)
[![License](https://img.shields.io/badge/License-Apache--2.0-929292)](https://www.apache.org/licenses/LICENSE-2.0)


teaser
teaser



Thera is the first arbitrary-scale super-resolution method with a built-in physical observation model.

## News
**2025-03-15**: We are #1 on Hacker News 🎉

**2025-03-14**: Interactive Hugging Face Space is online

**2025-03-12**: Pre-trained checkpoints are released

## Setup environment
You need a Python 3.10 environment (e.g., installed via conda) on Linux as well as an NVIDIA GPU. Then install packages via pip:
```bash
> pip install --upgrade pip
> pip install -r requirements.txt
```

## Use with pre-trained models
Download checkpoints:


Backbone
Variant
Download


EDSR-baseline
Air
🤗 Hugging Face | Google Drive


Plus
🤗 Hugging Face | Google Drive


Pro
🤗 Hugging Face | Google Drive


RDN
Air
🤗 Hugging Face | Google Drive


Plus
🤗 Hugging Face | Google Drive


Pro
🤗 Hugging Face | Google Drive

Super-resolve any image with:
```bash
> ./super_resolve.py IN_FILE OUT_FILE --scale 3.14 --checkpoint thera-rdn-pro.pkl
```

You can evaluate the models on datasets using the `run_eval.py` script, e.g.:

```bash
> python run_eval.py --checkpoint thera-rdn-pro.pkl --data-dir path_to_data_parent_folder --eval-sets data_folder_1 data_folder_2 ...
```

You can run `python run_eval.py -h` to display all testing options.

## Use with interactive Gradio app
You can also host a local version of our [Hugging Face demo](https://huggingface.co/spaces/prs-eth/thera). To do so, clone the dedicated demo repo:

```bash
> git clone https://huggingface.co/spaces/prs-eth/thera thera-demo
```

Instructions for running the demo locally can be found in [the repo's README.md](https://huggingface.co/spaces/prs-eth/thera/blob/main/README.md).

## Training
> Training code will be released soon.

## Useful XLA flags
* Disable pre-allocation of entire VRAM: `XLA_PYTHON_CLIENT_PREALLOCATE=false`
* Disable jitting for debugging: `JAX_DISABLE_JIT=1`

## Citation

If you found our work helpful, consider citing our paper 😊:

```
@article{becker2025thera,
title={Thera: Aliasing-Free Arbitrary-Scale Super-Resolution with Neural Heat Fields},
author={Becker, Alexander and Daudt, Rodrigo Caye and Narnhofer, Dominik and Peters, Torben and Metzger, Nando and Wegner, Jan Dirk and Schindler, Konrad},
journal={arXiv preprint arXiv:2311.17643},
year={2025}
}
```