Examples

Spatial computing & XR

Reason about the physical world in 3D

Fuse depth, meshes, calibrated cameras, and detections into a single scene you can scrub through frame by frame, from ARKit captures to multi-view reconstructions.

Live

ARKit scenes

Visualize the ARKitScenes dataset: color images, depth, the reconstructed mesh, and labeled 3D boxes around indoor furniture.

2D 3D Depth Mesh
3D line mapping revisited

Visual walkthrough of "3D Line Mapping Revisited": detection, matching, triangulation, and joint optimization.

2D 3D Structure from motion Time series
Objectron

Visualize Google Research's Objectron: per-frame images, camera poses, sparse point clouds, planes, and 3D boxes.

2D 3D Object detection Pinhole camera
SimpleRecon: 3D reconstruction without 3D convolutions

Visual walkthrough of "SimpleRecon: 3D reconstruction without 3D convolutions", showing cost volumes, depth, and normals per frame.

3D Depth Time series Pinhole camera
Decoupling human and camera motion from videos in the wild

Visual walkthrough of SLAHMR, which chains ViTPose, PHALP, DROID-SLAM, HuMoR, and SMPL across three optimization stages.

3D SLAM Keypoint detection Mesh
VRS viewer

A C++ example that loads VRS (Facebook's per-device sensor record format) into Rerun: images, audio, IMU, and more.

2D 3D VRS Viewer
Learning to render novel views from wide-baseline stereo pairs

Visual walkthrough of "Learning to Render Novel Views from Wide-Baseline Stereo Pairs" via cross-attention along rays.

2D 3D View synthesis Time series
ARFlow: a framework for simplifying AR experimentation workflow

External AR research framework that uses Rerun to visualize multi-modal sensor data from a mobile client in real time.

3D Augmented reality Spatial computing Integration

Robotics

Debug robots like you'd debug software

Log multi-rate sensor streams, joint states, controllers, and policies into one timeline. Replay a run, compare two, or watch one live as it happens.

ML & generative AI

Open the black box of your model

Visualize tensors, embeddings, diffusion intermediates, and end-to-end pipelines side-by-side. See what your model sees, at every step.

Vision

Inspect every pixel, every frame

Detections, segmentations, keypoints, and depth, overlaid on the source video, synchronized in time, and ready to scrub. Built for the messy reality of perception work.

3D reconstruction

From images to geometry, transparently

SLAM, structure-from-motion, photogrammetry, Gaussian splatting. Watch the pipeline build the scene step by step, with every intermediate inspectable.