# deepinv

> DeepInverse is the leading open-source PyTorch-based library for solving imaging inverse problems with deep learning. It provides imaging operators, pretrained reconstruction networks and denoisers, plug-and-play and unfolded optimization, sampling algorithms, training losses and datasets.


deepinverse contributors 2026

## Pages in this subsection

- [Benchmarks](https://deepinv.org/auto_benchmarks/benchmarks.html.md): This section provides benchmark results for various datasets and physics models.
- [Blur](https://deepinv.org/auto_benchmarks/blur_benchmarks.html.md): &#42; DIV2K Gaussian Deblurring
- [DIV2K Gaussian Deblurring](https://deepinv.org/auto_benchmarks/div2k_gaussian_deblurring.html.md): - &#42;Dataset&#42;: &#96;DIV2K&#96;
- [Denoising](https://deepinv.org/auto_benchmarks/denoising_benchmarks.html.md): &#42; CBSD68 gaussian denoising
- [CBSD68 gaussian denoising](https://deepinv.org/auto_benchmarks/cbsd68_gaussian_denoising.html.md): - &#42;Dataset&#42;: &#96;CBSD68&#96;
- [Downsampling](https://deepinv.org/auto_benchmarks/downsampling_benchmarks.html.md): &#42; DIV2K Super Resolution 2x
- [DIV2K Super Resolution 2x](https://deepinv.org/auto_benchmarks/div2k_super_resolution_2x.html.md): - &#42;Dataset&#42;: &#96;DIV2K&#96;
- [Inpainting](https://deepinv.org/auto_benchmarks/inpainting_benchmarks.html.md): &#42; DIV2K Inpainting easy
- [DIV2K Inpainting easy](https://deepinv.org/auto_benchmarks/div2k_inpainting_easy.html.md): - &#42;Dataset&#42;: &#96;DIV2K&#96;

## Optional

- [Top-level llms.txt](https://deepinv.org/llms.txt): Complete documentation index.