AI3D Foundation / Publications

Publications

The public record of systems, interfaces, and ideas built across the AI3D research lineage.

Publication record

Papers, demonstrations, workshops, and books

Records are listed in reverse chronological order. The bibliography includes the works in the supplied Google Scholar profile that credit Yosun Chang as an author, every paper in the open author archive, and AI3D Foundation demonstrations already documented on this site.

2026

AI3D Canvas with Spatial Creation Agents

AI3D Canvas lets people sketch, trace, place, stretch, compose, and otherwise manipulate forms directly in freeform space. It translates that spatial expression into the representation an AI model requires, then returns the result to an editable 3D world: the human works in space while the machinery of representation happens underneath.

Spatial Creation Agents receive geometry, objects, relationships, and composition as context, then create in relation to the world already there—moving from AI as generator to AI as a participant in a continuing spatial creation environment.

ECCV 2026 Demonstration

ECCV 2026 demonstration

2026

Virtual Theatre: Producing Live Theatre on Virtual Stages

Joe Geigel, Stephen Butchko, Yosun Chang, Alex Coulombe, and Jason Moore.

A spatial storytelling publication on the systems and production practices required to stage live theatre in virtual environments.

ACM SIGGRAPH 2026 Spatial Storytelling, pp. 1–2

DOI 10.1145/3799822.3812463

2025

AI3D Co-Create with AI3D Render

Yosun Chang, Caramel Corgi.cam Chang, and Michael Gold.

Co-Create treats 3D as a shared representation for iterative creation between people and multimodal AI: rough geometry communicates spatial intent, model output informs the next action, and the loop remains editable. AI3D Render adds scene, camera, composition, and animation controls for generative image and video.

ACM SIGGRAPH 2025 Appy Hour, pp. 1–3

DOI 10.1145/3721260.3733979 Open author PDF CVPR 2025 recognition

2025

Implementing SOTA Generative AI Pipelines in Your 3D Application

Yosun Chang, Michael Gold, and Caramel Corgi.cam Chang.

A hands-on lab on integrating contemporary generative models into interactive 3D systems, carrying the research into practical creative and technical workflows.

ACM SIGGRAPH 2025 Labs, pp. 1–4

DOI 10.1145/3721251.3734070

2025

Innovating with Generative AI: A Hands-On ComfyUI Workshop

Michael Gold and Yosun Chang.

A practical course for building and adapting node-based generative AI workflows with ComfyUI.

ACM SIGGRAPH 2025 Courses, pp. 1–4

DOI 10.1145/3721241.3734004

2024

VolumeMatic and the AI3D.foundation: Text to Interactive Volume App Spatial Computing Creator App

Yosun Chang.

VolumeMatic investigates generative AI for executable spatial experiences. A natural-language workflow combines generated assets, behaviors, and interactions inside an Apple Vision Pro volume app, alongside an AI3D benchmark card for comparing 3D generation systems.

ACM SIGGRAPH 2024 Appy Hour, pp. 1–3

DOI 10.1145/3664294.3664361 Open author PDF

2024

AI3D Sculpt

AI3D Sculpt explores direct spatial manipulation as an interface to generative 3D. A rough construction communicates proportion, orientation, topology, perspective, and spatial relationships directly: the model is not only the result; it can be the prompt.

ECCV 2024 Demonstration

ECCV 2024 demonstration

2024

AI3D Desktop: Creating 3D Using AI in Skeuomorphic XR and the Future of Work

Yosun Chang.

AI3D Desktop makes generative 3D a native operation in a persistent creative workspace, combining text-to-3D, image-to-3D, 3D-to-3D, and direct spatial manipulation inside a skeuomorphic XR environment.

ACM SIGGRAPH 2024 Appy Hour, pp. 1–2

DOI 10.1145/3664294.3664363 Open author PDF CVPR 2024 demonstration

2024

Napkinmatic App as a Ubiquitous Pocket AGI: Utility-Context-Sensitive 3D AR XR HCI for Vision-to-LLM

Yosun Chang.

Napkinmatic Ubiquitous turns an image of an object, diagram, or place into a context-sensitive interface for multimodal AI. It can analyze or narrate the image, retrieve or generate related 3D content, chain models, and place results back into the world through AR.

ACM SIGGRAPH 2024 Appy Hour, pp. 1–2

DOI 10.1145/3664294.3664364 Open author PDF

2023

Napkinmatic 3D

Yosun Chang.

Napkinmatic 3D turns an ordinary drawing on a napkin, notebook, receipt, or another available surface into a bridge from human visual intuition to generated geometry. It asks why a person should first translate an idea into the representation preferred by a computer.

ACM SIGGRAPH 2023 Real-Time Live!, pp. 1–2

DOI 10.1145/3588430.3597253 Open author PDF

2023

PhysicsAR: Problem Set Reality

Yosun Chang.

An augmented-reality learning interface that treats the physical problem set as the starting point for interactive, contextual assistance.

ACM SIGGRAPH 2023 Appy Hour, pp. 1–2

DOI 10.1145/3588427.3595359

2023

earrings.ai

Yosun Chang.

A generative design system for describing and creating earrings, trying them on in augmented reality, and connecting digital designs to physical production.

ACM SIGGRAPH 2023 Appy Hour, pp. 1–2

DOI 10.1145/3588427.3595358 Open author PDF

2023

Napkinmatic

Yosun Chang.

A mobile spatial-computing platform that turns an everyday sketch into generated visual or interactive content, linking a physical drawing to AI tools and returning the result to the surrounding world.

ACM SIGGRAPH 2023 Appy Hour, pp. 1–3

DOI 10.1145/3588427.3595357 Open author PDF

2022

Arithmagical: Magical Platform Technology Towards a Strong AI Virtual Tutor

Yosun Chang.

An AI tutor platform that turns photographed math work into interaction with a virtual dragon, combining computer vision, AR, virtual-pet mechanics, memory, and open-ended game creation.

ACM SIGGRAPH 2022 Appy Hour, pp. 1–2

DOI 10.1145/3532723.3535464 Open author PDF

2020

DrawmaticAR: Automagical AR Content from Written Words!

Yosun Chang.

An AI-and-AR system that interprets written story words on a physical marker and turns them into interactive animated 3D experiences.

ACM SIGGRAPH 2020 Real-Time Live!, p. 1

DOI 10.1145/3407662.3407755

2019

PlayGAMI: Augmented Reality Origami Creativity Platform

Uttam Grandhi and Ina Yosun Chang.

A creativity platform that connects drawing on physical origami with digitized augmented-reality characters and play.

ACM SIGGRAPH 2019 Appy Hour, pp. 1–2

DOI 10.1145/3305365.3329729

2019

sur.faced.io: Augmented Reality Content Creation for Your Face and Beyond by Drawing on Paper

Yosun Chang.

A paper-drawing interface for creating augmented-reality face content and extending those authoring methods to other 3D media.

ACM SIGGRAPH 2019 Appy Hour, pp. 1–2

DOI 10.1145/3305365.3329730

2018

Augmented Reality Interfaces for the Internet of Things

I. Yosun Chang.

A generalized augmented-reality interface for discovering, understanding, and operating connected devices through spatial overlays.

ACM SIGGRAPH 2018 Appy Hour, pp. 1–2

DOI 10.1145/3213779.3213789

2018

WallText: Augmented Reality Messaging Platforms

I. Yosun Chang.

A family of location-aware AR messaging interfaces spanning rendered graffiti, localized annotation conversations, and captured 3D content.

ACM SIGGRAPH 2018 Appy Hour, pp. 1–2

DOI 10.1145/3213779.3213788

2011

Pro iOS 5 Augmented Reality

Kyle Roche, Yosun Chang, Pascal Ma, and Gary Wood.

A practical book on the foundations of augmented-reality application development for iPhone and iPad.

Apress, 2011

Book record

Historical index

Additional Scholar-indexed technical work

These authored records appear on Google Scholar without enough formal venue or DOI metadata to place them in the archival bibliography above. They are retained here so the public record remains complete without overstating their publication status.

2018