Clean point clouds: Tersus GNSS MVP S1 scans turned into high-quality splats in LichtFeld Studio

janusch_patas · x · 2026-11-11

januschpatas shared first results scanning with the Tersus GNSS MVP S1 and importing the data into LichtFeld Studio (an integration is planned):

• A street-scene point cloud of 5.36M points (1,134 trajectory cameras) rendered in LichtFeld Studio, with quality/performance scale, reconstruction params and mesh export visible in the UI
• A third screenshot shows a GLIM CPU-built map: 221,738 points along a 171 m trajectory, with clean structure in a top-down colored view
• The author highlights how clean the point cloud is and how smooth the pipeline feels, producing high-quality 3D Gaussian splats directly

Original post →

More from Embodied

• Flashing cheap ESP32 IoT devices with ESPHome for a smart-home upgrade — haydendevs · 2026-11-11
• MessyMem on Compact Long-Term Memory for Agentic Robots Hits CoRL 2026 Main Poster — leto__jean · 2026-11-11
• NYU's Steertuning Lets a Robot Learn a Chore From 5 Minutes of Human Demo — CyberRobooo · 2026-11-11
• Boston Dynamics Atlas demoed with Blender 5.3 — TomLikesRobots · 2026-11-11
• Lamport Robotics posts robot 'wake-up test' demo video — R4nsack · 2026-11-11
• Embodied AI Faces Two-Order-of-Magnitude Data Gap as Industry Heads to 10M Hours — GaryMarcus · 2026-11-11

Embodied channel →