# LOTA — LiDAR Over The Air

> LOTA is an iOS app that turns iPhones into professional spatial capture and streaming tools. Stream real-time depth, color, point cloud, motion capture, IMU, audio analysis, and live transcription data over NDI, TCP/UDP, OSC, and PLY. Export COLMAP and Nerfstudio datasets for Gaussian Splat and NeRF training, capture PBR material sets from flat surfaces, and inspect saved point clouds in an on-device 3D viewer. Built for creative professionals using TouchDesigner, OBS, vMix, Resolume, Max/MSP, Ableton, Unreal, Unity, Blender, and other live visual / 3D tools.

- Requires iOS 26.2+. LiDAR (iPhone 12 Pro or later) needed for Depth, Point Cloud, Blob Track, Material Capture, and the LiDAR-based 3D-scene recording formats. Color, Mono, Neural Depth (Depth Anything V2 on the Apple Neural Engine), Transcription, Motion, and Audio modes work on every iPhone. **LOTA is officially iPhone-only** — iPad Pro with LiDAR has run during beta testing but is not an officially supported target
- Nine capture modes on the Camera / Streaming page: Color (60 FPS RGB), Mono (grayscale), Depth (9 LiDAR colormaps), Neural Depth (AI depth on every iPhone), Point Cloud (LiDAR streamed over PLY; on-device view is the RGB camera, geometry visualized receiver-side), Blob Track (TouchDesigner-compatible), Transcription (on-device speech-to-text), Motion (IMU graphs), Audio (mic analysis)
- ARKit Tracking page: body (91 joints, 18 key joints over OSC), face (52 blend shapes), hand tracking (21 landmarks per hand, up to 2 hands) — all streamed over OSC
- Gaussian Capture page: COLMAP, Nerfstudio, Nerfstudio + Depth, Point Cloud PLY, Material (PBR), IMU Trace, Audio Trace, and (new in v1.2.6) PLY Viewer — a read-only 3D inspector for any `.ply` file on the device, with 3D Gaussian Splat rendering added in v1.2.7
- Streaming transports: NDI (auto-discovered as `LOTA - <deviceLabel>`), TCP / UDP (H.264 video or raw Float32 depth), OSC (camera pose at ~30 Hz, body/face/hand tracking, IMU, audio analysis, transcription), and binary PLY (live point cloud over TCP)
- iOS Camera-style **STREAM | RECORD** paradigm switch on the middle page. Record saves the live composited Metal output as an H.264 `.mov` to the Photos library (add-only access)
- GPU-accelerated via Metal compute shaders; adaptive thermal throttle keeps long sessions stable
- All processing on-device, no analytics, no data collection
- Fully accessible: VoiceOver, Voice Control, Dynamic Type, Differentiate Without Color, Increase Contrast, Reduce Motion
- Currently in public TestFlight beta — join at https://testflight.apple.com/join/jFNkCjNF; App Store release coming soon

## Documentation

- [Getting Started](https://lidarota.app/docs): Device requirements, first-launch permission flow, on-device speech model prefetch, the three-page swipe navigation, quick-start
- [Capture Modes](https://lidarota.app/docs#capture-modes): Color, Mono, Depth, Neural Depth, Point Cloud, Blob Track, Transcription, Motion, and Audio mode specifications and usage
- [Streaming Protocols](https://lidarota.app/docs#streaming): NDI auto-discovery with customizable per-device label, TCP/UDP H.264 and Float32 streaming, OSC at 30 Hz, binary PLY point cloud streaming
- [ARKit Tracking](https://lidarota.app/docs#tracking): Body, face, and hand motion capture streamed over OSC
- [TouchDesigner Integration](https://lidarota.app/docs#touchdesigner): NDI In TOP setup, LOTAPoints.tox, LOTABinaryPLYRecieverV2.tox, LOTASpeechTCP.tox, LOTASpeechUDP.tox drop-in components
- [Export & 3D Pipelines](https://lidarota.app/docs#export): COLMAP, Nerfstudio, Nerfstudio + Depth, Point Cloud PLY, Material (PBR), IMU Trace, Audio Trace, and PLY Viewer. Capture Rate setting (30 / 15 / ~7 Hz, reflecting unique LiDAR scans) and binary/ASCII PLY Format toggle for 3D-scene recording formats. Compatible with OpenSplat, Nerfstudio, gsplat, Substance Designer/Painter, Blender, Unreal, Unity, TouchDesigner
- [Settings Reference](https://lidarota.app/docs#settings): Receiver IP, transport configs, depth, point cloud, blob tracking, tracking overlays, transcription, motion, audio, Gaussian Capture, PLY Viewer
- [Accessibility](https://lidarota.app/docs#accessibility): VoiceOver, Voice Control, Dynamic Type, Dark Interface, Differentiate Without Color, Increase Contrast, Reduce Motion
- [FAQ](https://lidarota.app/docs#faq): Supported devices, network requirements, latency, compatible software, recommended export formats

## Product

- [Changelog](https://lidarota.app/changelog): Full version history through v1.2.8 (current). v1.2.8 makes the middle-page Point Cloud mode show the live RGB camera (geometry visualized receiver-side), retunes the Gaussian Capture Rate picker to 30 / 15 / ~7 Hz so it reflects unique LiDAR scans, adds backpressure to the PLY TCP transport, and fixes Balanced/Efficient Compute Quality silently dropping PLY frames. v1.2.7 adds 3D Gaussian Splat viewing in the PLY Viewer, a Splat Size control, and an ASCII PLY export option. v1.2.6 added PLY Viewer mode with orbit / pan / zoom, five color modes, and a neon axis gizmo
- [Privacy Policy](https://lidarota.app/privacy): On-device processing, no analytics, no data collection, local network streaming only