← Back to Index Scene_02 · Marble ● live
Scene 02 · World Models · 2025

Marble

World Labs · Marble · Multi-Image → World Model

Marble reconstructs David Chipperfield’s SSENSE Montreal flagship from reference photos into a navigable world. The project uses World Labs’ world-model pipeline to test how quickly architectural atmosphere can become explorable spatial output.

World Labs Marble 3DGS .spz
Montreal, QC
2025
OUTPUT
.SPZ
Navigable World
01 · Problem

Photographs usually stop at depiction instead of becoming places.

Architectural images capture surface and mood, but they rarely yield something you can traverse without a heavier reconstruction pipeline. Marble explores a faster route from reference imagery to spatial world.

The question is simple: how little capture is enough to recover a convincing sense of a place? In this case, a handful of images becomes an explorable proxy for a specific Montreal interior.

Marble generated SSENSE world overview
Marble · SSENSE Montreal reconstructed as a navigable world
02 · Context

Architecture translated through a world model.

The source subject is David Chipperfield’s brutalist SSENSE flagship in Montreal, a space with enough material contrast and spatial rhythm to stress-test generative reconstruction. The project uses that architecture as a benchmark for atmosphere as much as geometry.

Marble also marks an early world-model experiment in the Spatial Index sequence. It shifts the stack from reconstruction-by-capture toward reconstruction-by-inference, testing what contemporary models can synthesize from sparse visual evidence.

03 · Approach

Multi-image reference in, navigable `.spz` world out.

Reference photos of the SSENSE interior are submitted to World Labs’ Marble model, which reconstructs the environment into a navigable output with collider geometry. The result can be explored directly in-browser rather than treated as a static artifact.

The emphasis here is not on hand-authored cleanup but on evaluating the baseline quality of the model output: how well it preserves structure, material feel, and navigability at different resolutions.

04 · Stack

Sparse references transformed into an explorable model.

Rendering
World Labs viewer · browser navigation
Backend / Data
World Labs Marble world-model pipeline
Pipeline
Reference photos → Marble inference → `.spz` world with collider meshes
Deploy
worldlabs.ai hosted viewer · world permalink
05 · Reflections

World models compress a large amount of spatial labor.

Marble demonstrates how quickly a place can become navigable when the reconstruction burden moves from manual workflow to model inference. Even when the result is imperfect, the speed changes what kinds of experiments become realistic.

The next question is continuity: how these generated worlds can be chained, remixed, or used as input for later scenes rather than treated as isolated outputs.

06 · Build Log

From reference set to generated world.

2025
Reference selection
Chose SSENSE Montreal imagery for its brutalist geometry, material contrast, and strong spatial identity.
2025
Marble generation
Ran the multi-image set through World Labs Marble and compared output quality across available resolution settings.
2025
Navigation review
Checked the resulting world for collider behavior, continuity, and architectural legibility in-browser.
2025
Launch
Published the world permalink as Scene 02, establishing the world-model branch of the Spatial Index pipeline.