arXiv subjects

Keiichi Ihara

Publications and source records attributed to Keiichi Ihara.

6 recordsLinked to original sources

arXiv2026

MemoryDiorama: Generating Dynamic 3D Diorama from Everyday Photos for Memory Recall

We present MemoryDiorama, a prototype system that introduces augmented memory cues, a concept that extends captured personal media with AI-generated contextual information to enhance autobiographical memory recall. MemoryDiorama transforms everyday photos into dynamic 3D dioramas in mixed reality by integrating LLM-based scene analysis with 3D object generation, animation, and spatial composition. The system extracts geographic information, object attributes, lighting conditions, and atmospheric elements from the photos. It then animates these elements with generative components such as object animations, human motion, geographical effects, and particle effects to provide richer cues for memory recall. We evaluated MemoryDiorama in a within-subject user study with 18 participants, comparing three conditions: Photo-Only, Static Diorama, and MemoryDiorama. Compared with both Photo-Only and Static Diorama, MemoryDiorama elicited more internal and in-cue details during recall. It also increased perceptual details and visual vividness ratings, suggesting richer recollective experience.

cs.HC↗

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↗

arXiv2026

AR Object Layout Method Using Miniature Room Generated from Depth Data

In augmented reality (AR), users can place virtual objects anywhere in a real-world room, called AR layout. Although several object manipulation techniques have been proposed in AR, it is difficult to use them for AR layout owing to the difficulty in freely changing the position and size of virtual objects. In this study, we make the World-in-Miniature (WIM) technique available in AR to support AR layout. The WIM technique is a manipulation technique that uses miniatures, which has been proposed as a manipulation technique for virtual reality (VR). Our system uses the AR device's depth sensors to acquire a mesh of the room in real-time to create and update a miniature of a room in real-time. In our system, users can use miniature objects to move virtual objects to arbitrary positions and scale them to arbitrary sizes. In addition, because the miniature object can be manipulated instead of the real-scale object, we assumed that our system will shorten the placement time and reduce the workload of the user. In our previous study, we created a prototype and investigated the properties of manipulating miniature objects in AR. In this study, we conducted an experiment to evaluate how our system can support AR layout. To conduct a task close to the actual use, we used various objects and made the participants design an AR layout of their own will. The results showed that our system significantly reduced workload in physical and temporal demand. Although, there was no significant difference in the total manipulation time.

cs.HC↗

arXiv2025

MapStory: Prototyping Editable Map Animations with LLM Agents

We introduce MapStory, an LLM-powered animation prototyping tool that generates editable map animation sequences directly from natural language text by leveraging a dual-agent LLM architecture. Given a user written script, MapStory automatically produces a scene breakdown, which decomposes the text into key map animation primitives such as camera movements, visual highlights, and animated elements. Our system includes a researcher agent that accurately queries geospatial information by leveraging an LLM with web search, enabling automatic extraction of relevant regions, paths, and coordinates while allowing users to edit and query for changes or additional information to refine the results. Additionally, users can fine-tune parameters of these primitive blocks through an interactive timeline editor. We detail the system's design and architecture, informed by formative interviews with professional animators and by an analysis of 200 existing map animation videos. Our evaluation, which includes expert interviews (N=5) and a usability study (N=12), demonstrates that MapStory enables users to create map animations with ease, facilitates faster iteration, encourages creative exploration, and lowers barriers to creating map-centric stories.

cs.HC↗

arXiv2024

Video2MR: Automatically Generating Mixed Reality 3D Instructions by Augmenting Extracted Motion from 2D Videos

This paper introduces Video2MR, a mixed reality system that automatically generates 3D sports and exercise instructions from 2D videos. Mixed reality instructions have great potential for physical training, but existing works require substantial time and cost to create these 3D experiences. Video2MR overcomes this limitation by transforming arbitrary instructional videos available online into MR 3D avatars with AI-enabled motion capture (DeepMotion). Then, it automatically enhances the avatar motion through the following augmentation techniques: 1) contrasting and highlighting differences between the user and avatar postures, 2) visualizing key trajectories and movements of specific body parts, 3) manipulation of time and speed using body motion, and 4) spatially repositioning avatars for different perspectives. Developed on Hololens 2 and Azure Kinect, we showcase various use cases, including yoga, dancing, soccer, tennis, and other physical exercises. The study results confirm that Video2MR provides more engaging and playful learning experiences, compared to existing 2D video instructions.

cs.HC↗

arXiv2023

HoloBots: Augmenting Holographic Telepresence with Mobile Robots for Tangible Remote Collaboration in Mixed Reality

This paper introduces HoloBots, a mixed reality remote collaboration system that augments holographic telepresence with synchronized mobile robots. Beyond existing mixed reality telepresence, HoloBots lets remote users not only be visually and spatially present, but also physically engage with local users and their environment. HoloBots allows the users to touch, grasp, manipulate, and interact with the remote physical environment as if they were co-located in the same shared space. We achieve this by synchronizing holographic user motion (Hololens 2 and Azure Kinect) with tabletop mobile robots (Sony Toio). Beyond the existing physical telepresence, HoloBots contributes to an exploration of broader design space, such as object actuation, virtual hand physicalization, world-in-miniature exploration, shared tangible interfaces, embodied guidance, and haptic communication. We evaluate our system with twelve participants by comparing it with hologram-only and robot-only conditions. Both quantitative and qualitative results confirm that our system significantly enhances the level of co-presence and shared experience, compared to the other conditions.

cs.HC↗