arXiv subjects

Hye-Young Jo

Publications and source records attributed to Hye-Young Jo.

3 recordsLinked to original sources

arXiv2026

CinemaWorld: Generative Augmented Reality with LLMs and 3D Scene Generation for Movie Augmentation

We introduce CinemaWorld, a generative augmented reality system that augments the viewer's physical surroundings with automatically generated mixed reality 3D content extracted from and synchronized with 2D movie scenes. Our system preprocesses films to extract key features using multimodal large language models (LLMs), generates dynamic 3D augmentations with generative AI, and embeds them spatially into the viewer's physical environment on the Meta Quest 3. To explore the design space of CinemaWorld, we conducted an elicitation study with eight film students, which led us to identify several key augmentation types, including particle effects, surrounding objects, textural overlays, character-driven augmentation, and lighting effects. We evaluated our system through a technical evaluation (N=100 video clips), a user study (N=12), and expert interviews with film creators (N=8). Results indicate that CinemaWorld enhances immersion and enjoyment, suggesting its potential to enrich the film-viewing experience.

cs.HC↗

arXiv2025

Generative Lecture: Making Lecture Videos Interactive with LLMs and AI Clone Instructors

We introduce Generative Lecture, a concept that makes existing lecture videos interactive through generative AI and AI clone instructors. By leveraging interactive avatars powered by HeyGen, ElevenLabs, and GPT-5, we embed an AI instructor into the video and augment the video content in response to students' questions. This allows students to personalize the lecture material, directly ask questions in the video, and receive tailored explanations generated and delivered by the AI-cloned instructor. From a design elicitation study (N=8), we identified four goals that guided the development of eight system features: 1) on-demand clarification, 2) enhanced visuals, 3) interactive example, 4) personalized explanation, 5) adaptive quiz, 6) study summary, 7) automatic highlight, and 8) adaptive break. We then conducted a user study (N=12) to evaluate the usability and effectiveness of the system and collected expert feedback (N=5). The results suggest that our system enables effective two-way communication and supports personalized learning.

cs.HC↗

arXiv2025

Map2Video: Street View Imagery Driven AI Video Generation

AI video generation has lowered barriers to video creation, but current tools still struggle with inconsistency. Filmmakers often find that clips fail to match characters and backgrounds, making it difficult to build coherent sequences. A formative study with filmmakers highlighted challenges in shot composition, character motion, and camera control. We present Map2Video, a street view imagery-driven AI video generation tool grounded in real-world geographies. The system integrates Unity and ComfyUI with the VACE video generation model, as well as OpenStreetMap and Mapillary for street view imagery. Drawing on familiar filmmaking practices such as location scouting and rehearsal, Map2Video enables users to choose map locations, position actors and cameras in street view imagery, sketch movement paths, refine camera motion, and generate spatially consistent videos. We evaluated Map2Video with 12 filmmakers. Compared to an image-to-video baseline, it achieved higher spatial accuracy, required less cognitive effort, and offered stronger controllability for both scene replication and open-ended creative exploration.

cs.HC↗