pith. machine review for the scientific record. sign in

arxiv: 2604.06773 · v1 · submitted 2026-04-08 · 💻 cs.HC

Recognition: no theorem link

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

Keiichi Ihara , Tianle Li , Yasuhisa Shiino , Ryo Suzuki
Authors on Pith no claims yet

Pith reviewed 2026-05-10 18:30 UTC · model grok-4.3

classification 💻 cs.HC
keywords memory recallmixed reality3D dioramaautobiographical memoryAI generationuser studyaugmented cues
0
0 comments X

The pith

Dynamic 3D dioramas made from everyday photos with added AI animations help users recall more details from their memories than plain photos or static scenes.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper introduces MemoryDiorama as a mixed-reality system that converts personal photos into animated 3D scenes by analyzing elements like objects, lighting, and atmosphere, then adding motions, human activities, and particle effects. It tests whether these extra cues produce stronger memory recall than viewing the original photo alone or a non-moving 3D model. In a study with 18 people, the dynamic version led to more internal and cue-related details being remembered, along with higher ratings for perceptual richness and visual vividness. A sympathetic reader would care because personal photos often lose their power to trigger full memories over time, and richer cues could support better preservation of life events. If the approach holds, it points toward everyday tools that actively shape how people revisit their past.

Core claim

MemoryDiorama extracts geographic, object, lighting, and atmospheric information from a photo using LLM-based analysis, then generates and composes 3D objects with animations, human motion, geographical effects, and particles to create dynamic mixed-reality dioramas that supply augmented memory cues; a within-subject comparison showed this condition produced more internal and in-cue recall details plus higher perceptual detail and vividness scores than either the original photo or a static 3D diorama.

What carries the argument

The MemoryDiorama pipeline that performs LLM scene analysis on a photo to derive attributes and then generates, animates, and spatially arranges 3D elements including object motions, human activities, and atmospheric particles for mixed-reality display.

Load-bearing premise

The AI-generated animations and contextual elements accurately supplement the user's actual memory instead of adding distortions or invented details.

What would settle it

A follow-up experiment in which participants later verify recalled details against independent records of the original events and find that the dynamic diorama condition produces more inaccuracies than the photo-only or static conditions.

Figures

Figures reproduced from arXiv: 2604.06773 by Keiichi Ihara, Ryo Suzuki, Tianle Li, Yasuhisa Shiino.

Figure 1
Figure 1. Figure 1: MemoryDiorama transforms everyday photos into dynamic 3D dioramas for autobiographical memory recall in [PITH_FULL_IMAGE:figures/full_fig_p001_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Conceptual placement of augmented memory cues across autobiographical connection and cue diversity. Autobiographical Connection. Autobiographical memory is shaped by what individuals perceived and experienced at the time of an event, including visual, emotional, and contextual information [18, 30]. Retrieval is typically facilitated when cues are congruent with the original encoding context, according to t… view at source ↗
Figure 3
Figure 3. Figure 3: Representative examples of augmented memory cues, illustrating sensory augmentations (smell (a), tactile (b), and ambient sound (c)) and visual-spatial extensions (expanded views (d) and 3D representations (e)). the original experience. Captured personal media such as photos and videos maintain a strong connection to lived experience, but they are inherently constrained by recording capabilities. A photo￾g… view at source ↗
Figure 4
Figure 4. Figure 4: Recurring cue patterns elicited from the formative study. [PITH_FULL_IMAGE:figures/full_fig_p005_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: MemoryDiorama system pipeline. The system transforms a photo collection from a single event into a dynamic 3D [PITH_FULL_IMAGE:figures/full_fig_p007_5.png] view at source ↗
Figure 7
Figure 7. Figure 7: Human layer. (a) Dancing. (b) Pedestrians walking. [PITH_FULL_IMAGE:figures/full_fig_p007_7.png] view at source ↗
Figure 8
Figure 8. Figure 8: Particle layer. (a) Snow. (b) Fog. (c) Cherry blossom. [PITH_FULL_IMAGE:figures/full_fig_p007_8.png] view at source ↗
Figure 9
Figure 9. Figure 9: Lighting layer. (a) Sunset lighting. (b) Streetlight. (c) [PITH_FULL_IMAGE:figures/full_fig_p008_9.png] view at source ↗
Figure 10
Figure 10. Figure 10: Geographical layer. (a) Snow-covered terrain. (b) [PITH_FULL_IMAGE:figures/full_fig_p008_10.png] view at source ↗
Figure 11
Figure 11. Figure 11: User study results comparing Photo-Only, Static Diorama, and MemoryDiorama. Left and middle panels show mean [PITH_FULL_IMAGE:figures/full_fig_p009_11.png] view at source ↗
read the original abstract

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.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

3 major / 2 minor

Summary. The paper presents MemoryDiorama, a mixed-reality prototype that converts everyday photos into dynamic 3D dioramas by combining LLM-based scene analysis with generative 3D objects, animations, human motions, geographical effects, and particle systems to supply augmented contextual cues. A within-subjects study with 18 participants compares three conditions (Photo-Only, Static Diorama, MemoryDiorama) and reports that the dynamic version produces more internal and in-cue details during recall plus higher ratings for perceptual details and visual vividness.

Significance. If the empirical claims hold after proper statistical reporting and accuracy verification, the work would demonstrate a concrete way to enrich autobiographical memory cues via generative AI in immersive settings, extending prior work on external memory aids. The system integration of LLM analysis with 3D generation and animation is a practical contribution, and the direct comparison of static versus dynamic augmentation is a useful experimental contrast.

major comments (3)
  1. [User study / evaluation] User study / evaluation section: the abstract and results claim directional benefits in internal/in-cue details and vividness ratings, yet supply no statistical details (test statistics, p-values, effect sizes, power analysis, or exclusion criteria). This under-specification makes it impossible to evaluate the reliability or magnitude of the reported differences.
  2. [Results / Discussion] Results and discussion: the central claim that MemoryDiorama produces a 'richer recollective experience' rests on counting more recalled details without any ground-truth check against the original photos or participants' verified pre-study memories. Elevated detail counts could therefore reflect AI-introduced confabulation rather than genuine memory enhancement, directly undermining the interpretation of the outcome measures.
  3. [System / Generative components] System description (around the generative components): the paper does not address or measure the risk that LLM-driven animations, motions, and particles may fabricate or distort autobiographical content. Given the application domain, an explicit discussion of fidelity safeguards or post-hoc accuracy validation is required to support the claim that the added elements 'augment' rather than alter memory.
minor comments (2)
  1. [Abstract] Abstract: the sample size (n=18) and within-subjects design should be stated explicitly rather than left implicit.
  2. [Figures] Figure captions and legends: several figures showing diorama examples would benefit from clearer labels indicating which elements are photo-derived versus AI-generated.

Simulated Author's Rebuttal

3 responses · 0 unresolved

We thank the referee for their constructive and detailed feedback, which has strengthened the rigor of our work. We address each major comment below and have revised the manuscript to improve statistical reporting, acknowledge limitations in interpretation, and discuss fidelity risks.

read point-by-point responses

  1. Referee: User study / evaluation section: the abstract and results claim directional benefits in internal/in-cue details and vividness ratings, yet supply no statistical details (test statistics, p-values, effect sizes, power analysis, or exclusion criteria). This under-specification makes it impossible to evaluate the reliability or magnitude of the reported differences.

    Authors: We agree that the statistical reporting was insufficient in the original submission. In the revised manuscript, we have added full details of the statistical analyses performed on the within-subjects data, including the tests used (repeated-measures ANOVA with Bonferroni-corrected post-hoc paired t-tests), exact p-values, effect sizes (partial eta-squared and Cohen's d), a post-hoc power analysis (achieved power > 0.8 for key comparisons), and participant exclusion criteria (e.g., two participants excluded due to incomplete recall protocols). These revisions enable proper evaluation of reliability and magnitude. revision: yes

  2. Referee: Results and discussion: the central claim that MemoryDiorama produces a 'richer recollective experience' rests on counting more recalled details without any ground-truth check against the original photos or participants' verified pre-study memories. Elevated detail counts could therefore reflect AI-introduced confabulation rather than genuine memory enhancement, directly undermining the interpretation of the outcome measures.

    Authors: This concern about potential confabulation is valid and highlights a limitation in our outcome measures. Our evaluation counted recalled details to indicate richer recollective experience but did not include explicit ground-truth verification against the original photos or pre-study memory reports. In the revised manuscript, we have expanded the Discussion to explicitly acknowledge this possibility, noting that some details could derive from generative elements. We have also revised the abstract, results, and conclusions to use more cautious phrasing (e.g., 'elicited more details, suggesting enhanced cues') and recommend future studies incorporate accuracy checks. Since new empirical verification would require additional data collection beyond the current study, we address the issue through discussion and tempered claims rather than new results. revision: partial

  3. Referee: System description (around the generative components): the paper does not address or measure the risk that LLM-driven animations, motions, and particles may fabricate or distort autobiographical content. Given the application domain, an explicit discussion of fidelity safeguards or post-hoc accuracy validation is required to support the claim that the added elements 'augment' rather than alter memory.

    Authors: We appreciate this point on the need for explicit fidelity discussion. The original system description detailed the LLM analysis and generative components (object animations, human motions, geographical and particle effects) but omitted risks of fabrication or distortion. We have added a new subsection 'Fidelity Safeguards in Generative Components' to the System section, describing prompt engineering techniques that constrain generations to photo-derived attributes (e.g., scene lighting, objects, and geography) and avoid unrelated inventions. We also expand the Discussion to address potential distortions and outline post-hoc validation approaches, such as participant accuracy ratings or automated consistency checks. These changes support our augmentation claim by transparently addressing safeguards and limitations. revision: yes

Circularity Check

0 steps flagged

No significant circularity in derivation chain

full rationale

The paper describes a prototype system that uses LLM-based scene analysis, 3D generation, and animations to create dynamic dioramas from photos, then evaluates it via a direct within-subjects user study (n=18) comparing Photo-Only, Static Diorama, and MemoryDiorama conditions on recall details and vividness ratings. No equations, fitted parameters, predictions, or self-referential derivations appear anywhere in the methodology or claims. The central empirical results are independent measurements from participant tasks, not quantities that reduce to the system's inputs by construction. No self-citation load-bearing steps, uniqueness theorems, or ansatz smuggling are invoked to support the core findings.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 0 invented entities

The paper introduces no new mathematical axioms, free parameters, or invented physical entities; it composes existing LLM and 3D-generation components under the domain assumption that those components can produce memory-relevant contextual cues.

axioms (1)
  • domain assumption LLM-based scene analysis and off-the-shelf 3D generators can reliably extract and synthesize memory-relevant contextual elements without introducing systematic distortions
    Invoked implicitly when the system adds animations and effects to support recall.

pith-pipeline@v0.9.0 · 5485 in / 1121 out tokens · 62576 ms · 2026-05-10T18:30:00.724764+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

110 extracted references · 4 canonical work pages · 3 internal anchors

  1. [1]

    Gemini 3 Developer Guide | Gemini API | Google AI for Developers

    [n.d.]. Gemini 3 Developer Guide | Gemini API | Google AI for Developers. https://ai.google.dev/gemini-api/docs/gemini-3 [Online; accessed 2026-04-01]

    2026

  2. [2]

    Genie 3 — Google DeepMind

    [n.d.]. Genie 3 — Google DeepMind. https://deepmind.google/models/genie/ [Online; accessed 2026-03-14]

    2026

  3. [3]

    Lapz: Watch F1®Races in Apple Vision Pro

    [n.d.]. Lapz: Watch F1®Races in Apple Vision Pro. https://www.lapz.io/ [Online; accessed 2026-01-07]

    2026

  4. [4]

    Nano Banana 2 - Gemini AI image generator & photo editor

    [n.d.]. Nano Banana 2 - Gemini AI image generator & photo editor. https: //gemini.google/overview/image-generation/ [Online; accessed 2026-03-18]

    2026

  5. [5]

    Runway Research | Introducing Runway GWM-1

    [n.d.]. Runway Research | Introducing Runway GWM-1. https://runwayml.com/ research/introducing-runway-gwm-1 [Online; accessed 2026-03-14]

    2026

  6. [6]

    Amy M Belfi, Brett Karlan, and Daniel Tranel. 2016. Music evokes vivid autobio- graphical memories.Memory24, 7 (2016), 979–989

    2016

  7. [7]

    Susan Bluck. 2003. Autobiographical memory: Exploring its functions in everyday life.Memory11, 2 (2003), 113–123

    2003

  8. [8]

    Andrew Bluff and Andrew Johnston. 2019. Don’t panic: Recursive interactions in a miniature metaworld. InProceedings of the 17th ACM SIGGRAPH International Conference on Virtual-Reality Continuum and its Applications in Industry. 1–9

    2019

  9. [9]

    Andrea Bonsch, Sebastian Freitag, and Torsten W Kuhlen. 2016. Automatic generation of world in miniatures for realistic architectural immersive virtual environments. In2016 IEEE Virtual Reality (VR). IEEE, 155–156

    2016

  10. [10]

    Jas Brooks and Pedro Lopes. 2023. Smell & paste: Low-fidelity prototyping for olfactory experiences. InProceedings of the 2023 CHI Conference on Human Factors in Computing Systems. 1–16

    2023

  11. [11]

    Gerd Bruder, Frank Steinicke, and Klaus H Hinrichs. 2009. Arch-explore: A natural user interface for immersive architectural walkthroughs. In2009 IEEE symposium on 3D user interfaces. IEEE, 75–82

    2009

  12. [12]

    Amy Yo Sue Chen, William Odom, Sol Kang, and Carman Neustaedter. 2023. PhotoClock: Reliving Memories in Digital Photos as the Clock Ticks in the Present Moment. InProceedings of the 2023 ACM Designing Interactive Systems Conference. 1015–1031

    2023

  13. [13]

    Amy Yo Sue Chen, William Odom, Carman Neustaedter, Ce Zhong, and Henry Lin

  14. [14]

    InProceedings of the 2023 CHI Conference on Human Factors in Computing Systems

    Exploring Memory-Oriented Interactions with Digital Photos In and Across Time: A Field Study of Chronoscope. InProceedings of the 2023 CHI Conference on Human Factors in Computing Systems. 1–20

    2023

  15. [15]

    Xingyu Chen, Fu-Jen Chu, Pierre Gleize, Kevin J Liang, Alexander Sax, Hao Tang, Weiyao Wang, Michelle Guo, Thibaut Hardin, Xiang Li, et al. 2025. Sam 3d: 3dfy anything in images.arXiv preprint arXiv:2511.16624(2025)

    work page internal anchor Pith review arXiv 2025

  16. [16]

    Luca Chittaro, Vijay Kumar Gatla, and Subramanian Venkataraman. 2005. The interactive 3d breakaway map: A navigation and examination aid for multi-floor 3d worlds. In2005 International Conference on Cyberworlds (CW’05). IEEE, 8–pp

    2005

  17. [17]

    Simon Chu and John J Downes. 2002. Proust nose best: Odors are better cues of autobiographical memory.Memory & cognition30, 4 (2002), 511–518

    2002

  18. [18]

    Dane Coffey, Nicholas Malbraaten, Trung Le, Iman Borazjani, Fotis Sotiropoulos, and Daniel F Keefe. 2011. Slice WIM: a multi-surface, multi-touch interface for overview+ detail exploration of volume datasets in virtual reality. InSymposium on Interactive 3D Graphics and Games. 191–198

    2011

  19. [19]

    Martin A Conway and Christopher W Pleydell-Pearce. 2000. The construction of autobiographical memories in the self-memory system.Psychological review107, 2 (2000), 261

    2000

  20. [20]

    Kurtis Danyluk, Barrett Ens, Bernhard Jenny, and Wesley Willett. 2021. A design space exploration of worlds in miniature. InProceedings of the 2021 CHI Conference on Human Factors in Computing Systems. 1–15

    2021

  21. [21]

    Arnaud D’Argembeau, Christine Comblain, and Martial Van der Linden. 2003. Phenomenal characteristics of autobiographical memories for positive, negative, and neutral events.Applied Cognitive Psychology: The Official Journal of the Society for Applied Research in Memory and Cognition17, 3 (2003), 281–294

    2003

  22. [22]

    Katinka Dijkstra, Michael P Kaschak, and Rolf A Zwaan. 2007. Body posture facilitates retrieval of autobiographical memories.Cognition102, 1 (2007), 139– 149

    2007

  23. [23]

    David Frohlich and Rachel Murphy. 2000. The memory box.Personal Technologies 4, 4 (2000), 238–240

    2000

  24. [24]

    bird’s eye

    Shinji Fukatsu, Yoshifumi Kitamura, Toshihiro Masaki, and Fumio Kishino. 1998. Intuitive control of “bird’s eye” overview images for navigation in an enormous virtual environment. InProceedings of the ACM symposium on Virtual reality software and technology. 67–76

    1998

  25. [25]

    Maryanne Garry and Kimberley A Wade. 2005. Actually, a picture is worth less than 45 words: Narratives produce more false memories than photographs do. Psychonomic bulletin & review12, 2 (2005), 359–366

    2005

  26. [26]

    Duncan R Godden and Alan D Baddeley. 1975. Context-dependent memory in two natural environments: On land and underwater.British Journal of psychology 66, 3 (1975), 325–331

    1975

  27. [27]

    Sudheendra Hangal, Monica S Lam, and Jeffrey Heer. 2011. Muse: Reviving memories using email archives. InProceedings of the 24th annual ACM symposium on User interface software and technology. 75–84

    2011

  28. [28]

    Sandra G Hart and Lowell E Staveland. 1988. Development of NASA-TLX (Task Load Index): Results of empirical and theoretical research. InAdvances in psy- chology. Vol. 52. Elsevier, 139–183

    1988

  29. [29]

    Devamardeep Hayatpur, Haijun Xia, and Daniel Wigdor. 2020. Datahop: Spa- tial data exploration in virtual reality. InProceedings of the 33rd Annual ACM Symposium on User Interface Software and Technology. 818–828

    2020

  30. [30]

    Steve Hodges, Lyndsay Williams, Emma Berry, Shahram Izadi, James Srinivasan, Alex Butler, Gavin Smyth, Narinder Kapur, and Ken Wood. 2006. SenseCam: A retrospective memory aid. InInternational conference on ubiquitous computing. Springer, 177–193

    2006

  31. [31]

    Alisha C Holland and Elizabeth A Kensinger. 2010. Emotion and autobiographical memory.Physics of life reviews7, 1 (2010), 88–131

    2010

  32. [32]

    Tobias Höllerer, Steven Feiner, Drexel Hallaway, Blaine Bell, Marco Lanzagorta, Dennis Brown, Simon Julier, Yohan Baillot, and Lawrence Rosenblum. 2001. User interface management techniques for collaborative mobile augmented reality. Computers & Graphics25, 5 (2001), 799–810

    2001

  33. [33]

    Yicong Hong, Kai Zhang, Jiuxiang Gu, Sai Bi, Yang Zhou, Difan Liu, Feng Liu, Kalyan Sunkavalli, Trung Bui, and Hao Tan. 2023. Lrm: Large reconstruction model for single image to 3d.arXiv preprint arXiv:2311.04400(2023)

    work page internal anchor Pith review arXiv 2023

  34. [34]

    Seokhyun Hwang, Seongjun Kang, Jeongseok Oh, Jeongju Park, Semoo Shin, Yiyue Luo, Joseph DelPreto, Sangbeom Lee, Kyoobin Lee, Wojciech Matusik, et al

  35. [35]

    InProceedings of the 2025 CHI Conference on Human Factors in Computing Systems

    Telepulse: Enhancing the teleoperation experience through biomechanical simulation-based electrical muscle stimulation in virtual reality. InProceedings of the 2025 CHI Conference on Human Factors in Computing Systems. 1–26

    2025

  36. [36]

    Hikaru Ibayashi, Yuta Sugiura, Daisuke Sakamoto, Natsuki Miyata, Mitsunori Tada, Takashi Okuma, Takeshi Kurata, Masaaki Mochimaru, and Takeo Igarashi

  37. [37]

    InSIGGRAPH Asia 2015 emerging technologies

    Dollhouse vr: a multi-view, multi-user collaborative design workspace with vr technology. InSIGGRAPH Asia 2015 emerging technologies. 1–2

    2015

  38. [38]

    Keiichi Ihara, Mehrad Faridan, Ayumi Ichikawa, Ikkaku Kawaguchi, and Ryo Suzuki. 2023. Holobots: Augmenting holographic telepresence with mobile robots for tangible remote collaboration in mixed reality. InProceedings of the 36th annual ACM symposium on user interface software and technology. 1–12

    2023

  39. [39]

    Keiichi Ihara and Ikkaku Kawaguchi. 2022. AR Object Layout Method Using Miniature Room Generated from Depth Data. InICAT-EGVE. 35–43

    2022

  40. [40]

    Keiichi Ihara and Ikkaku Kawaguchi. 2022. Virtual object placement in mr space using a 3d miniature model of a room. InProceedings of the Asian HCI Symposium

    2022

  41. [41]

    Hiroshi Ishii, Daniel Pillis, Pat Pataranutaporn, Xiao Xiao, Hayoun Noh, Lucy Li, Alaa Algargoosh, and Jean-Baptiste Labrune. 2025. TeleAbsence: A vision of past and afterlife telepresence.PRESENCE: Virtual and Augmented Reality34 (2025), 65–95

    2025

  42. [42]

    Zhuoqun Jiang, ShunYi Yeo, Donovan Seow, Wei Xuan, and Simon Tangi Perrault

  43. [43]

    Remini: Leveraging Chatbot-Mediated Mutual Reminiscence for Promoting Positive Affect and Feeling of Connectedness among Loved Ones.Proceedings of the ACM on Human-Computer Interaction9, 7 (2025), 1–43

    2025

  44. [44]

    Arata Jingu, Easa AliAbbasi, Paul Strohmeier, and Jürgen Steimle. 2025. Scene2Hap: Combining LLMs and physical modeling for automatically gen- erating vibrotactile signals for full VR scenes.arXiv preprint arXiv:2504.19611 (2025)

    work page arXiv 2025

  45. [45]

    Marcia K Johnson, Mary A Foley, Aurora G Suengas, and Carol L Raye. 1988. Phenomenal characteristics of memories for perceived and imagined autobi- ographical events.Journal of Experimental Psychology: General117, 4 (1988), 371

    1988

  46. [46]

    Michael Kalkusch, Thomas Lidy, N Knapp, Gerhard Reitmayr, Hannes Kaufmann, and Dieter Schmalstieg. 2002. Structured visual markers for indoor pathfinding. InThe First IEEE International Workshop Agumented Reality Toolkit,. IEEE, 8–pp. Conference’17, July 2017, Washington, DC, USA Ihara, et al

    2002

  47. [47]

    Bumsoo Kang, Seungwoo Kang, and Inseok Hwang. 2021. Momentmeld: Ai- augmented mobile photographic memento towards mutually stimulatory inter- generational interaction. InProceedings of the 2021 CHI Conference on Human Factors in Computing Systems. 1–16

    2021

  48. [48]

    Bernhard Kerbl, Georgios Kopanas, Thomas Leimkühler, and George Drettakis

  49. [49]

    Graph.42, 4 (2023), 139–1

    3D Gaussian splatting for real-time radiance field rendering.ACM Trans. Graph.42, 4 (2023), 139–1

    2023

  50. [50]

    Subin Kim, Sangsu Jang, Jin-young Moon, Minjoo Han, and Young-Woo Park

  51. [51]

    InProceedings of the 2022 ACM Designing Interactive Systems Conference

    Slide2remember: an interactive wall frame enriching reminiscence experi- ences by providing re-encounters of taken photos and heard music in a similar period. InProceedings of the 2022 ACM Designing Interactive Systems Conference. 288–300

    2022

  52. [52]

    Akihiro Kiuchi, Jonathan Wieland, Takeo Igarashi, and David Lindlbauer. 2025. MiniMates: Miniature Avatars for AR Remote Meetings within Limited Physical Spaces. InProceedings of the 2025 CHI Conference on Human Factors in Computing Systems. 1–20

    2025

  53. [53]

    2023.Principles and practice of structural equation modeling

    Rex B Kline. 2023.Principles and practice of structural equation modeling. Guilford publications

    2023

  54. [54]

    Joseph J LaViola Jr, Daniel Acevedo Feliz, Daniel F Keefe, and Robert C Zeleznik

  55. [55]

    InProceedings of the 2001 symposium on Interactive 3D graphics

    Hands-free multi-scale navigation in virtual environments. InProceedings of the 2001 symposium on Interactive 3D graphics. 9–15

    2001

  56. [56]

    Brian Levine, Eva Svoboda, Janine F Hay, Gordon Winocur, and Morris Moscov- itch. 2002. Aging and autobiographical memory: dissociating episodic from semantic retrieval.Psychology and aging17, 4 (2002), 677

    2002

  57. [57]

    Zisu Li, Li Feng, Chen Liang, Yuru Huang, and Mingming Fan. 2023. Exploring the Opportunities of AR for Enriching Storytelling with Family Photos between Grandparents and Grandchildren.Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies7, 3 (2023), 1–26

    2023

  58. [58]

    D Stephen Lindsay, Lisa Hagen, J Don Read, Kimberley A Wade, and Maryanne Garry. 2004. True photographs and false memories.Psychological Science15, 3 (2004), 149–154

    2004

  59. [59]

    Elizabeth F Loftus and Jacqueline E Pickrell. 1995. The formation of false memo- ries. , 720–725 pages

    1995

  60. [60]

    Karthik Mahadevan, Qian Zhou, George Fitzmaurice, Tovi Grossman, and Fraser Anderson. 2023. Tesseract: Querying spatial design recordings by manipulating worlds in miniature. InProceedings of the 2023 CHI Conference on Human Factors in Computing Systems. 1–16

    2023

  61. [61]

    Viorica Marian and Caitlin M Fausey. 2006. Language-dependent memory in bilingual learning.Applied Cognitive Psychology: The Official Journal of the Society for Applied Research in Memory and Cognition20, 8 (2006), 1025–1047

    2006

  62. [62]

    Chris B Martin, Bryan Hong, Rachel N Newsome, Katarina Savel, Melissa E Meade, Andrew Xia, Christopher J Honey, and Morgan D Barense. 2022. A smartphone intervention that enhances real-world memory and promotes differentiation of hippocampal activity in older adults.Proceedings of the National Academy of Sciences119, 51 (2022), e2214285119

    2022

  63. [63]

    David McGookin. 2019. Reveal: investigating proactive location-based remi- niscing with personal digital photo repositories. InProceedings of the 2019 CHI Conference on Human Factors in Computing Systems. 1–14

    2019

  64. [64]

    Ben Mildenhall, Pratul P Srinivasan, Matthew Tancik, Jonathan T Barron, Ravi Ramamoorthi, and Ren Ng. 2021. Nerf: Representing scenes as neural radiance fields for view synthesis.Commun. ACM65, 1 (2021), 99–106

    2021

  65. [65]

    Alessandro Mulloni, Hartmut Seichter, and Dieter Schmalstieg. 2012. Indoor navigation with mixed reality world-in-miniature views and sparse localization on mobile devices. InProceedings of the International Working Conference on Advanced Visual Interfaces. 212–215

    2012

  66. [66]

    Jung Who Nam, Krista McCullough, Joshua Tveite, Maria Molina Espinosa, Charles H Perry, Barry T Wilson, and Daniel F Keefe. 2019. Worlds-in-wedges: Combining worlds-in-miniature and portals to support comparative immersive visualization of forestry data. In2019 IEEE conference on virtual reality and 3D user interfaces (VR). IEEE, 747–755

    2019

  67. [67]

    Christopher Niederauer, Mike Houston, Maneesh Agrawala, and Greg Humphreys. 2003. Non-invasive interactive visualization of dynamic archi- tectural environments. InProceedings of the 2003 symposium on Interactive 3D graphics. 55–58

    2003

  68. [68]

    Michael Nunes, Saul Greenberg, and Carman Neustaedter. 2008. Sharing digital photographs in the home through physical mementos, souvenirs, and keepsakes. InProceedings of the 7th ACM conference on Designing interactive systems. 250– 260

    2008

  69. [69]

    Sergio Orts-Escolano, Christoph Rhemann, Sean Fanello, Wayne Chang, Adarsh Kowdle, Yury Degtyarev, David Kim, Philip L Davidson, Sameh Khamis, Ming- song Dou, et al. 2016. Holoportation: Virtual 3d teleportation in real-time. In Proceedings of the 29th annual symposium on user interface software and technology. 741–754

    2016

  70. [70]

    Sebastian Pasewaldt, Amir Semmo, Matthias Trapp, and Jürgen Döllner. 2014. Multi-perspective 3D panoramas.International Journal of Geographical Informa- tion Science28, 10 (2014), 2030–2051

    2014

  71. [71]

    Randy Pausch, Tommy Burnette, Dan Brockway, and Michael E Weiblen. 1995. Navigation and locomotion in virtual worlds via flight into hand-held miniatures. InProceedings of the 22nd annual conference on Computer graphics and interactive techniques. 399–400

    1995

  72. [72]

    S Tejaswi Peesapati, Victoria Schwanda, Johnathon Schultz, Matt Lepage, So-yae Jeong, and Dan Cosley. 2010. Pensieve: supporting everyday reminiscence. In Proceedings of the SIGCHI Conference on Human Factors in Computing Systems. 2027–2036

    2010

  73. [73]

    Daniela Petrelli, Nicolas Villar, Vaiva Kalnikaite, Lina Dib, and Steve Whittaker

  74. [74]

    InProceedings of the SIGCHI Conference on Human Factors in Computing Systems

    FM radio: family interplay with sonic mementos. InProceedings of the SIGCHI Conference on Human Factors in Computing Systems. 2371–2380

  75. [75]

    Thammathip Piumsomboon, Gun A Lee, Jonathon D Hart, Barrett Ens, Robert W Lindeman, Bruce H Thomas, and Mark Billinghurst. 2018. Mini-me: An adaptive avatar for mixed reality remote collaboration. InProceedings of the 2018 CHI conference on human factors in computing systems. 1–13

    2018

  76. [76]

    Thammathip Piumsomboon, Gun A Lee, Andrew Irlitti, Barrett Ens, Bruce H Thomas, and Mark Billinghurst. 2019. On the shoulder of the giant: A multi-scale mixed reality collaboration with 360 video sharing and tangible interaction. In Proceedings of the 2019 CHI conference on human factors in computing systems. 1–17

    2019

  77. [77]

    Henning Pohl, Klemen Lilija, Jess McIntosh, and Kasper Hornbæk. 2021. Poros: configurable proxies for distant interactions in VR. InProceedings of the 2021 CHI Conference on Human Factors in Computing Systems. 1–12

    2021

  78. [78]

    Ben Poole, Ajay Jain, Jonathan T Barron, and Ben Mildenhall. 2022. Dreamfusion: Text-to-3d using 2d diffusion.arXiv preprint arXiv:2209.14988(2022)

    work page internal anchor Pith review arXiv 2022

  79. [79]

    Simon Prince, Adrian David Cheok, Farzam Farbiz, Todd Williamson, Nik Johnson, Mark Billinghurst, and Hirokazu Kato. 2002. 3-d live: real time interaction for mixed reality. InProceedings of the 2002 ACM conference on Computer supported cooperative work. 364–371

    2002

  80. [80]

    Konstantinos Rematas, Ira Kemelmacher-Shlizerman, Brian Curless, and Steve Seitz. 2018. Soccer on your tabletop. InProceedings of the IEEE conference on computer vision and pattern recognition. 4738–4747

    2018

Showing first 80 references.