happyhj

happyhj / waymo-perception-studio

Public

Waymo Open Dataset on browser visualization tool

happyhj.github.iowaymo-perception-studio autonomous-driving visualization waymo waymo-open-dataset
12
1
100% credibility
Found Mar 03, 2026 at 12 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
TypeScript
AI Summary

Browser-based 3D visualization tool for Waymo Open Dataset v2.0 perception data featuring synchronized LiDAR point clouds, camera views, and object tracking without installation or servers.

How It Works

1
🔍 Discover the viewer

You hear about a simple web tool to explore self-driving car sensor data from Waymo's free dataset without any setup.

2
📥 Grab sample data

Use the provided guide to download a small folder of real driving scenes with lasers and cameras using your web browser.

3
🌐 Open the live demo

Visit the ready-to-use page in your browser—no downloads or installs needed.

4
📁 Drop your data

Drag the data folder onto the page and watch it scan and load your scenes instantly.

5
🧭 Dive into 3D views

See laser point clouds, car positions, and five camera angles all synced together in a smooth 3D world.

6
▶️ Play and interact

Scrub the timeline, switch camera views, hover objects to link 2D and 3D, and follow the car's path.

✅ Unlock insights

Easily understand what self-driving cars 'see' and detect, right in your browser, with your own data secure and private.

Sign up to see the full architecture

5 more

Sign Up Free

Star Growth

See how this repo grew from 12 to 12 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is waymo-perception-studio?

This TypeScript app is a browser-based 3D viewer for the Waymo Open Dataset perception data, letting you drag-and-drop a waymo dataset download folder to explore LiDAR point clouds from five sensors alongside synchronized camera feeds. No Python, TensorFlow, or server setup needed—your Waymo dataset lidar and camera images render instantly with bounding boxes as wireframes or low-poly models, cross-linked by hover. Toggle vehicle/world frames, scrub the timeline, or jump to camera POVs directly in Chrome.

Why is it gaining traction?

Unlike official Waymo Open Dataset tools requiring heavy Python pipelines or paid options like Foxglove, this runs natively in the browser with zero install, handling massive waymo dataset size Parquet files via efficient streaming. Developers love the interactive perks: real-time hover-linking between 2D camera detections and 3D boxes, trajectory trails, and sensor toggles—perfect for quick waymo dataset format inspections without Jupyter static plots. The live demo hooks you in seconds, bypassing waymo dataset github preprocessing scripts.

Who should use this?

Perception engineers debugging Waymo models, researchers citing the waymo dataset paper for leaderboard analysis, or self-driving devs prepping waymo interview questions github sessions. Ideal for quick waymo dataset license checks, motion dataset github explorations, or waymo research github prototypes where you need to visualize raw lidar/camera sync without a full stack.

Verdict

Grab it for instant Waymo Open Dataset viz—early at 12 stars and 1.0% credibility, but solid docs, download script, and MIT license make it a no-brainer prototype tool. Fork and contribute to push past beta.

(187 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.