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

We present $\mathit{\text{kornia-rs}}$, 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, $\mathit{\text{kornia-rs}}$ is built from the ground up to leverage Rust’s ownership model and type system for memory and thread safety. $\mathit{\text{kornia-rs}}$ 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, $\mathit{\text{kornia-rs}}$ offers Python bindings, enabling seamless and efficient integration with Rust code. Empirical results show that $\mathit{\text{kornia-rs}}$ 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, $\mathit{\text{kornia-rs}}$ 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 $\mathit{\text{kornia-rs}}$, demonstrating its effectiveness in real-world computer vision applications.