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

TL;DR

kornia-rs is a high-performance, safe, and modular 3D computer vision library in Rust, offering efficient image processing and 3D operations with cross-platform Python bindings, outperforming native Rust alternatives.

Contribution

It introduces a comprehensive 3D vision library in Rust built from scratch, leveraging Rust's safety features and providing cross-platform Python integration, filling a gap in the Rust ecosystem.

Findings

Achieves 3-5x speedup over native Rust image transformation tools.

Provides comparable performance to C++ wrapper libraries.

Addresses a significant gap by including 3D vision operators in Rust.

Abstract

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.