KIO Outdoor Test — 13.01.2026

KIO Outdoor Test — 13.01.2026 Hardware: • Camera: GoPro Hero 12 Black action Cam x3 • Selfie stick: 2.5 M • Apriltags • Custom 3D-printed lens hood Software: • Training Pipeline: Reality scan for Colmap data, • LichtFeld Studio (Windows nightly build — 13.01.2026) Workflow: The capture path was walked once in a zig-zag pattern using three cameras mounted at three different heights. This was followed by an additional walk around the sorting container and the transporter, Two extra capture paths were conducted parallel to the main elevation of the two buildings. AprilTags were used for scaling and orientation. Camera capture was triggered simultaneously on all three cameras using a Bluetooth remote app. • Height: ~2.6 m • Height: ~1.5 m • Height: ~0.6 m Dataset: • Total number of images: 2451 • Date of Capture: 07.01.2026 • Time to Capture: 12 Minutes • Operator: A.B. Key Observations: • Switching the pipeline from Postshot to LichtFeld Studio makes the workflow fully open source, with a notable training speed increase of approximately 2.4×, even when using MCMC models. • Although the scan was captured on a sunny day (which is generally not recommended) the additional light enabled higher shutter speeds and sharper images, resulting in a very crisp Gaussian Splat. A downside of these conditions is that operator shadows may be visible as hallucinations, particularly when moving around the scene. • The custom 3D-printed lens hood helped reduce floaters and glare artifacts in sunny areas. KreativInstitut.OWL @kreativinstitutowl