A scene is justthe beginning.
Read English, but get stuck saying it? Explore a familiar scene. Open a detail. Follow it to the words you can use.
Join the waitlist
A meaning. A sound. A way to say it in this situation.
Illustrated method concept.
See the situation.
A word starts in a place you recognize.
Follow the details.
Open what you need. Keep your trail.
Connect the expression.
See how the word belongs in a conversation.
01 / Drill-Down Explainer · 2D MVP
One question opens
the next layer.
Each lesson begins with a scene generated for that moment. Select an object, a word or an area. Open its explanation, then explore a smaller detail or a related question.
Start in a situation.
A café, a commute, a conversation. The scene gives the language its context.
Choose what you need.
An object, a word or an area becomes an entry point. Curiosity sets the route.
Open an explanation.
Meaning, pronunciation, an example and the reason it fits this situation.
Keep going. Keep your place.
Scene → object → part. A breadcrumb and exploration history bring you back.
Scene · At the café
Start with a familiar scene.
Pronunciation, shown as text: · pronunciation
You are ordering at a café. An object or a phrase can open a different path into the same situation.
“Coffee” opens the drink and its details. “To go” opens the way you ask to take it with you.
Choose a starting point. Each opens a connected explanation.
Open the latte, move into its cup, then examine the handle up close. Each layer reveals a more detailed illustrated view of the same scene. The “to go” branch explores the conversation. This preview uses five prepared images and fixed explanations, inspired by Flipbook’s exploratory approach; it does not generate lessons or play audio.
Learning in visible context is our product hypothesis. Lasting recall has not yet been measured.
A world you can look around.
The same path to understanding.
Our 3D direction starts with a place captured in photographs. Look around, choose a language label, then open the same layers of explanation. This experience is being explored.
01 / The starting material
A place, captured from several views.
Photographs and calibrated camera views provide the input for reconstructing a spatial scene.
Mavilo’s 2D MVP starts with a generated illustration. This proposed 3D path starts with photographs of a place.
Where NVIDIA’s 3DGUT fits
More faithful cameras.
More believable scenes.
3D Gaussian Splatting represents a photographed scene with soft 3D particles. 3DGUT improves how they project through complex camera models, helping preserve the scene as the view changes.
Distorted lenses, accounted for.
It supports nonlinear camera models, including fisheye lenses, rather than relying on an ideal pinhole camera.
Camera motion, accounted for.
It can model rolling shutter: different parts of a frame captured at different times.
An efficient rendering path.
It retains Gaussian rasterization efficiency. Mavilo’s frame rates and supported devices still need validation.
What about reflections, refractions and the Unscented Transform?
3DGUT means 3D Gaussian Unscented Transform. Representative “sigma points” pass through the camera model to estimate each particle’s screen footprint.
Reflections and refractions use hybrid rendering: the main view is splatted, while secondary rays are traced with 3DGRT. These effects do not come from splatting alone.
Language labels, object selection and explanations would be Mavilo’s product layer. The rendering research does not supply them.
3D remains a research direction for Mavilo. We have not validated real-time performance, device compatibility or learning outcomes. The illustration above demonstrates the idea.
Choose your learning companion.
Different personalities. One shared purpose: help you understand.
Poodle
The Guide
A curious poodle companion who helps you find what to explore next.
- Curious
- Practical
- Patient
Companion concept · In testing
Companion concepts are being tested. This preview does not activate a mentor.
Explore with us from the beginning.
A recognition badge for the first 100 trial participants.
Preview complete.
Your email and language interests have not been submitted or saved.
Preview only. Your email is not submitted or saved.
English first. Chinese, Japanese and more languages are future directions.