Look into a reconstruction
Interactive viewer for the reconstruction results.
LiteReality
Our iOS LiDAR room scanner. Walk a room with an iPhone or iPad and it exports a single bundle — posed RGB frames, LiDAR depth, ARKit camera poses and the RoomPlan layout — everything the reconstruction pipeline needs.
How it works
LiteReality-Agent starts by initializing the room from the scan through a deterministic pipeline, then an authoring stage refines it toward a realistic appearance. At its core the agent works by editing the scene's Room.py program — its entire workspace — in a render–compare–critique loop, with quality control gating the result.
Scan
Posed RGB + LiDAR from the app.
Initialize
Walls, openings & cameras rebuilt into a blank room.
Author
Agent edits Room.py, refining against the capture.
QC
Checks the scene meets quality standards.
Final scene
The realistic, interactive, articulated 3D result.
Programmable rooms. The whole scene — geometry, materials, articulation — is one Python program the agent edits.
Purpose-built tools. A set the agent composes — render & compare, select views, measure, fetch materials, critique, compile — alongside the usual agent tools (bash, glob, read, edit) for everything else.
Quality control. Automatic checks keep every output scene within standard before it ships.
A programmable scene · Room.py
The whole scene — geometry, materials, articulation — is defined in one Room.py program. That is what makes it the agent’s editable workspace: legible, replayable and portable.
The agent edits lines of code, never raw meshes.
Rerun the file to rebuild the scene — assets are regenerated, not stored.
A fixed set of methods, so every change stays legible and traceable.
The same file exports to Blender, glTF or a simulator.
Applications
Because the whole scene is an editable Room.py program, a plain-English prompt becomes a code edit — the room is programmable. Three things it can already do, each a clip from the same authored office:
Text-based scene editing
Everything lives in a Room.py file, so the room is a programmable object — a typed request becomes a code edit. Re-texture the walls or swap the floor in a few lines: exposed brick, walnut panelling, sage-green paint. The geometry never moves.
DemonstratedScene rearrangement
Move the furniture — nothing is deleted. From a prompt the agent re-lays-out the room while keeping everything grounded and collision-free: clear the floor for a standup, or seat eight around the table.
DemonstratedDecoration
Fixtures, props and banners, placed in 3D. The agent fetches real assets and writes procedural geometry into Room.py — pendant lamps, a birthday setup, a World‑Cup party — all clear of the door swing.
DemonstratedIntrinsic outputs
Because the scene is fully authored, it renders perfect intrinsics for free — pixel-exact semantic segmentation, depth, normals and albedo, from the very same cameras. Dense ground truth no real capture can hand you.
DemonstratedRobotics & embodied AI
Export the articulated, collision-ready room to a physics simulator as a stage for training and evaluating embodied agents in real layouts.
Gallery of reconstructions
Every reconstruction, interactive in the browser — real capture beside the render, from the same camera. Click any scene to orbit it.
▸ Overview & walkthrough videos will be dropped in here. Each card links to the live, orbitable reconstruction with a real-vs-render comparison and per-group visibility toggles.
Citation
@article{huang2026litereality,
title = {LiteReality-Agent: An Agentic Harness for
Simulation-Ready Indoor Reconstruction},
author = {Huang, Zhening and Li, Yueyan and Chiu, Johnathan and
Lyu, Xiaoyang and Zhou, Matt and Yao, Yuxin and
Lasenby, Joan and Wu, Shangzhe},
year = {2026},
note = {Project page: litereality-agent}
}