# Kornia-rs: A Low-Level 3D Computer Vision Library In Rust

arXiv: https://arxiv.org/abs/2505.12425 · HTML: https://mlsanity.com/paper/2505.12425/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 3 of its 15 references that are in the map.
- First posted on arXiv 18 May 2025.

## Builds on (most cited first, 3 of 3)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Open3D: A Modern Library for 3D Data Processing](https://mlsanity.com/paper/1801.09847/) (2018)
- [Kornia: an Open Source Differentiable Computer Vision Library for PyTorch](https://mlsanity.com/paper/1910.02190/) (2019)

## Abstract (arXiv)

We present textitkornia-rs, a high-performance 3D computer vision library written entirely in native Rust, designed for safety-critical and real-time applications. Unlike C++-based libraries like OpenCV or wrapper-based solutions like OpenCV-Rust, textitkornia-rs is built from the ground up to leverage Rust's ownership model and type system for memory and thread safety. textitkornia-rs adopts a statically-typed tensor system and a modular set of crates, providing efficient image I/O, image processing and 3D operations. To aid cross-platform compatibility, textitkornia-rs offers Python bindings, enabling seamless and efficient integration with Rust code. Empirical results show that textitkornia-rs achieves a 3~ 5 times speedup in image transformation tasks over native Rust alternatives, while offering comparable performance to C++ wrapper-based libraries. In addition to 2D vision capabilities, textitkornia-rs addresses a significant gap in the Rust ecosystem by providing a set of 3D computer vision operators. This paper presents the architecture and performance characteristics of textitkornia-rs, demonstrating its effectiveness in real-world computer vision applications.