# Kornia: an Open Source Differentiable Computer Vision Library for PyTorch

arXiv: https://arxiv.org/abs/1910.02190 · HTML: https://mlsanity.com/paper/1910.02190/

## Key facts

- Cited by 232 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Oct 2019.

## Built on by (most cited first, 30 of 232)

- [Nerfstudio: A Modular Framework for Neural Radiance Field Development](https://mlsanity.com/paper/2302.04264/) (2023)
- [MONAI: An open-source framework for deep learning in healthcare](https://mlsanity.com/paper/2211.02701/) (2022)
- [Dataset Distillation by Matching Training Trajectories](https://mlsanity.com/paper/2203.11932/) (2022)
- [FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects](https://mlsanity.com/paper/2312.08344/) (2023)
- [VQGAN-CLIP: Open Domain Image Generation and Editing with Natural Language Guidance](https://mlsanity.com/paper/2204.08583/) (2022)
- [Scaling Up Dataset Distillation to ImageNet-1K with Constant Memory](https://mlsanity.com/paper/2211.10586/) (2022)
- [Behavior From the Void: Unsupervised Active Pre-Training](https://mlsanity.com/paper/2103.04551/) (2021)
- [ControlNet++: Improving Conditional Controls with Efficient Consistency Feedback](https://mlsanity.com/paper/2404.07987/) (2024)
- [Towards Robust Vision Transformer](https://mlsanity.com/paper/2105.07926/) (2021)
- [Dataset Distillation via Factorization](https://mlsanity.com/paper/2210.16774/) (2022)
- [VectorFusion: Text-to-SVG by Abstracting Pixel-Based Diffusion Models](https://mlsanity.com/paper/2211.11319/) (2022)
- [Equivariance with Learned Canonicalization Functions](https://mlsanity.com/paper/2211.06489/) (2022)
- [SimpleRecon: 3D Reconstruction Without 3D Convolutions](https://mlsanity.com/paper/2208.14743/) (2022)
- [TorchGeo: Deep Learning With Geospatial Data](https://mlsanity.com/paper/2111.08872/) (2021)
- [Fishing for User Data in Large-Batch Federated Learning via Gradient Magnification](https://mlsanity.com/paper/2202.00580/) (2022)
- [Deep Patch Visual SLAM](https://mlsanity.com/paper/2408.01654/) (2024)
- [SimPLE: Similar Pseudo Label Exploitation for Semi-Supervised Classification](https://mlsanity.com/paper/2103.16725/) (2021)
- [Unsupervised Depth Completion with Calibrated Backprojection Layers](https://mlsanity.com/paper/2108.10531/) (2021)
- [Local-to-Global Registration for Bundle-Adjusting Neural Radiance Fields](https://mlsanity.com/paper/2211.11505/) (2022)
- [WOUAF: Weight Modulation for User Attribution and Fingerprinting in Text-to-Image Diffusion Models](https://mlsanity.com/paper/2306.04744/) (2023)
- [NAVI: Category-Agnostic Image Collections with High-Quality 3D Shape and Pose Annotations](https://mlsanity.com/paper/2306.09109/) (2023)
- [TrustMark: Universal Watermarking for Arbitrary Resolution Images](https://mlsanity.com/paper/2311.18297/) (2023)
- [FFCV: Accelerating Training by Removing Data Bottlenecks](https://mlsanity.com/paper/2306.12517/) (2023)
- [Feature Guided Masked Autoencoder for Self-supervised Learning in Remote Sensing](https://mlsanity.com/paper/2310.18653/) (2023)
- [Motion-aware Contrastive Video Representation Learning via Foreground-background Merging](https://mlsanity.com/paper/2109.15130/) (2021)
- [SECANT: Self-Expert Cloning for Zero-Shot Generalization of Visual Policies](https://mlsanity.com/paper/2106.09678/) (2021)
- [MONAI Label: A framework for AI-assisted Interactive Labeling of 3D Medical Images](https://mlsanity.com/paper/2203.12362/) (2022)
- [Revisiting Image Pyramid Structure for High Resolution Salient Object Detection](https://mlsanity.com/paper/2209.09475/) (2022)
- [PyTorch Image Quality: Metrics for Image Quality Assessment](https://mlsanity.com/paper/2208.14818/) (2022)
- [Generalized Differentiable RANSAC](https://mlsanity.com/paper/2212.13185/) (2022)

## Abstract (arXiv)

This work presents Kornia -- an open source computer vision library which consists of a set of differentiable routines and modules to solve generic computer vision problems. The package uses PyTorch as its main backend both for efficiency and to take advantage of the reverse-mode auto-differentiation to define and compute the gradient of complex functions. Inspired by OpenCV, Kornia is composed of a set of modules containing operators that can be inserted inside neural networks to train models to perform image transformations, camera calibration, epipolar geometry, and low level image processing techniques, such as filtering and edge detection that operate directly on high dimensional tensor representations. Examples of classical vision problems implemented using our framework are provided including a benchmark comparing to existing vision libraries.