Splatcam: LiDAR Capture

Welcome to the premiere of Splatcam, the world's best way to get the files you need to generate 3D Gaussian Splats!

SplatCam captures everything you need for 3D Gaussian Splatting training in a single session — images, camera poses, and a dense colored point cloud — using iPhone's LiDAR sensor. NOTE: You will then need to transfer this data to a PC for processing with splatting software like LichtFeld Studio, Postshot, etc. to get the final scene.

Walk around any object or scene and SplatCam handles the rest. Each capture records the camera frame, full intrinsic and extrinsic parameters, and accumulates a spatially-deduplicated point cloud from the LiDAR depth buffer in real time. When you're done, export a ready-to-train .zip containing a transforms.json, point cloud PLY, and images — no COLMAP or SfM pipeline required. Just load the folder into LichtFeld Studio (free), Postshot (paid), or any other RealityScan-compatible system and you're good to go.

Features:

• Real-time dense point cloud accumulation from LiDAR depth with spatial deduplication
• Manual shutter mode with volume button trigger
• Continuous auto-capture mode with distance/angle thresholds and blur rejection
• Live camera-perspective and overhead point cloud preview during capture
• Tracking quality indicator with motion and feature warnings
• Loop closure guidance to improve reconstruction accuracy
• Exports LichtFeld Studio / Postshot compatible transforms.json with full camera intrinsics and extrinsics
• Binary PLY point cloud with per-vertex color
• One-tap .zip export to Dropbox, AirDrop, Files, etc for transport to PC for processing

Output is directly compatible with LichtFeld Studio, Postshot, and other tools that accept the standard transforms.json + images + point cloud format.

Requires iPhone 12 Pro or later (LiDAR-equipped device). Gaussian Splat generation generally requires a CUDA-capable PC.