Back to Selected Work

Independent Continuation · May 2026–Present

SceneZero

A multimodal inspiration journal and real-world scene previsualization concept for author-driven AI filmmaking—designed to begin before a creator has a complete script or prompt.

View current boundary
My role
Product direction and AI-assisted implementation
Origin
Course prototype, continued independently
Stack
SwiftUI · ARKit · RealityKit · SwiftData
Status
Buildable iOS prototype · Ongoing
01Notice

A frame, sound, note, or emotion in the real world.

02Stage

Optionally explore people, objects, light, and camera relationships in AR.

03Keep

Save the inspiration and its scene context for later development.

01 · Product problem

AI filmmaking often starts too late in the creative process

Many tools begin with a prompt or generation request. SceneZero starts earlier: when a creator notices a composition, a sound, a spatial relationship, or an emotion that is not yet a complete project.

The product direction asks how those fragments can remain lightweight at capture time, then become more structured only when the creator chooses to develop them.

02 · Product decisions

Keep capture light; make spatial tools optional

  • Inspiration first. A photo, note, sound, or emotion should be valid without completing a project form.
  • AR as an option, not a gate. Spatial staging should help when position and camera language matter, but ordinary capture must remain complete.
  • Progressive structure. Camera, lighting, and scene fields appear when useful instead of becoming mandatory metadata.
  • Creator control. Observed scene facts, user intent, and model suggestions should remain distinguishable.

03 · Current implementation

What the verified iOS target supports

The currently tracked Xcode target builds for the iOS simulator and provides an inspectable implementation base using SwiftUI, ARKit, RealityKit, SwiftData, and local media handling.

  1. 01Capture

    Use the camera as the entry point for real-world visual references.

  2. 02Previsualize

    Place scene elements in AR to explore spatial and camera relationships.

  3. 03Persist

    Store structured inspiration data with local media using SwiftData.

  4. 04Revisit

    Return to saved material as input for later creative development.

04 · Iteration

From a course demo to an independent product direction

Course origin

Mobile AR prototype

Established the initial camera and spatial interaction direction.

Independent continuation

Reframed around inspiration

Moved away from a narrow production tool toward lightweight multimodal capture for individual creators.

Current work

Separating concept from verified build

Maintains a buildable target while treating broader V2 product ideas as work in development.

05 · Ownership boundary

Product reasoning is the strongest contribution

I defined the product positioning, target creator, interaction principles, information hierarchy, and iteration priorities. The implementation was developed substantially through AI-assisted coding, so I do not present generated code volume as evidence of original algorithmic work.

The defensible contribution is the connection between a product hypothesis and a working iOS artifact: deciding what the tool should help creators preserve, which capabilities should remain optional, and where implementation claims must stop.

06 · Outcome & limits

A product hypothesis with an implementation base

  • The current target builds, but simulator success does not establish field reliability on a range of devices.
  • No user study has tested whether creators understand, revisit, or benefit from the proposed workflow.
  • V2-only prompt compilation, spatial reasoning, and creative-advisor features are not presented as released or validated.
  • Real screenshots and device-based testing remain necessary before the page can serve as final product evidence.