Saved in:
Bibliographic Details
Main Authors: Riba, Edgar, Shi, Jian, Kumar, Aditya, Shen, Andrew, Bradski, Gary
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2505.12425
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915291863187456
author Riba, Edgar
Shi, Jian
Kumar, Aditya
Shen, Andrew
Bradski, Gary
author_facet Riba, Edgar
Shi, Jian
Kumar, Aditya
Shen, Andrew
Bradski, Gary
contents We present \textit{kornia-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, \textit{kornia-rs} is built from the ground up to leverage Rust's ownership model and type system for memory and thread safety. \textit{kornia-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, \textit{kornia-rs} offers Python bindings, enabling seamless and efficient integration with Rust code. Empirical results show that \textit{kornia-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, \textit{kornia-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 \textit{kornia-rs}, demonstrating its effectiveness in real-world computer vision applications.
format Preprint
id arxiv_https___arxiv_org_abs_2505_12425
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Kornia-rs: A Low-Level 3D Computer Vision Library In Rust
Riba, Edgar
Shi, Jian
Kumar, Aditya
Shen, Andrew
Bradski, Gary
Computer Vision and Pattern Recognition
We present \textit{kornia-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, \textit{kornia-rs} is built from the ground up to leverage Rust's ownership model and type system for memory and thread safety. \textit{kornia-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, \textit{kornia-rs} offers Python bindings, enabling seamless and efficient integration with Rust code. Empirical results show that \textit{kornia-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, \textit{kornia-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 \textit{kornia-rs}, demonstrating its effectiveness in real-world computer vision applications.
title Kornia-rs: A Low-Level 3D Computer Vision Library In Rust
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2505.12425