Versions:
Baballonia 1.1.0.9, published by dfgHiatus, is a cross-platform, hardware-agnostic tool designed for real-time eye and face tracking within extended-reality (XR) environments. Released in a single stable version, the software abstracts away vendor-specific SDKs so the same binary runs on OpenVR, OpenXR, and SteamVR headsets while auto-detecting attached cameras or built-in sensors from vendors such as HTC, Meta, Valve, and Varjo. By exposing a lightweight C++ API and accompanying Python bindings, developers can stream calibrated gaze vectors, 60 fps eyelid coefficients, and 52-blend-shape face poses into Unity, Unreal, or custom engines without rewriting acquisition code for each device. Typical use cases include foveated rendering pipelines that reduce GPU load by 30-50 %, avatar-driven social VR applications that mirror a user’s micro-expressions, and accessibility projects that translate eye movement into UI control. The installer ships with pre-trained ONNX models optimized for both monochrome and IR illumination, and a background service keeps tracking alive when users switch titles. Because the package is hardware-agnostic, research labs can benchmark gaze accuracy across headsets using a single dataset, while indie creators can add eye-tracking mechanics to existing games without purchasing proprietary modules. The software is available for free on get.nero.com, with downloads provided via trusted Windows package sources (e.g. winget), always delivering the latest version, and supporting batch installation of multiple applications.
Tags: