pith. sign in

arxiv: 2605.09620 · v2 · pith:L5R24ISCnew · submitted 2026-05-10 · 💻 cs.HC

MiXR: Harvesting and Recomposing Geometry from Real-World Objects for In-Situ 3D Design

Faraz Faruqi , Demircan Tas , Arthur Caetano , Niccol\`o Meniconi , O\u{g}uz Arslan , Misha Sra , Ruofei Du , Stefanie Mueller
show 1 more author
Mustafa Doga Dogan
This is my paper

Pith reviewed 2026-05-21 08:34 UTC · model grok-4.3

classification 💻 cs.HC
keywords 3D modelingmixed realitygenerative AIcompositional designin-situ modelinggeometry harvestingXR systemsuser study
0
0 comments X

The pith

MiXR lets users harvest real-world geometry segments, assemble them manually in XR to define spatial structure, and delegate refinement to generative AI.

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

MiXR is an XR system that lets users capture real-world objects, extract geometric segments from them, and assemble those segments through direct 3D manipulation to set the spatial layout of a new model. Generative AI then synthesizes a single coherent 3D artifact from the user-composed arrangement. This hybrid method addresses the weakness of text or image prompts in expressing precise spatial relationships. In a study with twelve participants, MiXR users rated their results as closer to the target design, reported greater control, and experienced lower cognitive workload than users of a purely generative composition baseline.

Core claim

The paper claims that a hybrid workflow of harvesting geometry segments from captured real objects, letting users compose them via direct manipulation in XR, and applying generative AI to produce a unified model enables explicit specification of spatial intent that is difficult to convey through verbal prompts alone, with measurable gains in design accuracy, control, and reduced workload shown in the user study.

What carries the argument

The hybrid workflow of harvesting real-world geometry segments, user-driven direct 3D assembly in XR, and generative AI synthesis to create a coherent final model.

If this is right

  • Users can produce 3D designs that more closely match their intended spatial structure.
  • Participants experience a stronger sense of control over the modeling process.
  • Cognitive workload drops for tasks that require precise geometric composition.
  • The approach is suited to in-situ design where real objects supply starting geometry.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • Designers could begin from familiar physical surroundings rather than abstract prompts, lowering the barrier for non-experts.
  • The system might support iterative on-site customization, such as modifying objects within the actual space they will occupy.
  • Collaborative versions could let multiple users harvest segments from a shared environment for joint model creation.

Load-bearing premise

Generative AI can reliably turn a user's manually assembled collection of real geometry segments into a coherent, high-quality 3D model without major artifacts or loss of the intended spatial relationships.

What would settle it

A test case in which the AI output shows major visual artifacts, breaks the spatial relationships set by the user's assembly, or produces a model that participants judge as farther from the target than the baseline method.

Figures

Figures reproduced from arXiv: 2605.09620 by Arthur Caetano, Demircan Tas, Faraz Faruqi, Misha Sra, Mustafa Doga Dogan, Niccol\`o Meniconi, O\u{g}uz Arslan, Ruofei Du, Stefanie Mueller.

Figure 2
Figure 2. Figure 2: Compositional 3D modeling of a building block de [PITH_FULL_IMAGE:figures/full_fig_p003_2.png] view at source ↗
Figure 1
Figure 1. Figure 1: MiXR transforms real-world objects into reusable geometric primitives for design. Users select and extract segments [PITH_FULL_IMAGE:figures/full_fig_p001_1.png] view at source ↗
Figure 3
Figure 3. Figure 3: MiXR allows users to harvest 3D models from phys [PITH_FULL_IMAGE:figures/full_fig_p004_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Paint-based segmentation. (a) The captured 3D [PITH_FULL_IMAGE:figures/full_fig_p005_4.png] view at source ↗
Figure 6
Figure 6. Figure 6: Mean Chamfer Distance (squared) and mean Mesh IoU across all 25 ordered category pairs for translation, rotation, [PITH_FULL_IMAGE:figures/full_fig_p007_6.png] view at source ↗
Figure 7
Figure 7. Figure 7: Source objects and target designs for the two study [PITH_FULL_IMAGE:figures/full_fig_p007_7.png] view at source ↗
Figure 5
Figure 5. Figure 5: Spatial recomposition via direct manipulation. [PITH_FULL_IMAGE:figures/full_fig_p005_5.png] view at source ↗
Figure 8
Figure 8. Figure 8: Post-task Likert ratings by condition (7-point scale; [PITH_FULL_IMAGE:figures/full_fig_p008_8.png] view at source ↗
Figure 10
Figure 10. Figure 10: A personalized book support composed from a [PITH_FULL_IMAGE:figures/full_fig_p009_10.png] view at source ↗
Figure 11
Figure 11. Figure 11: A chair designed from household objects. (a) A [PITH_FULL_IMAGE:figures/full_fig_p009_11.png] view at source ↗
Figure 12
Figure 12. Figure 12: A custom accessibility grip for an umbrella. [PITH_FULL_IMAGE:figures/full_fig_p010_12.png] view at source ↗
read the original abstract

Recent developments in 3D generative AI enable users to create bespoke 3D models from text or image prompts. However, these approaches provide limited control over spatial structure, making them ill suited for tasks requiring precise geometric composition. We present MiXR, an XR system for in-situ compositional modeling that enables users to create new 3D models by harvesting geometry from their environment. Users extract segments from captured objects and assemble new artifacts through direct 3D manipulation, while generative AI synthesizes a coherent model from the user-defined composition. This hybrid workflow allows users to define spatial structure explicitly while delegating geometric refinement to generative models, enabling them to specify spatial intent that is difficult to express through verbal prompts alone. In a controlled user study ($N=12$), participants using MiXR rated their designs as significantly closer to the target, felt more in control, and experienced lower cognitive workload compared to a generative composition baseline.

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

2 major / 2 minor

Summary. The manuscript presents MiXR, an XR system for in-situ compositional 3D modeling. Users capture real-world objects, harvest geometric segments, assemble them via direct 3D manipulation to explicitly define spatial structure, and then invoke generative AI to synthesize a coherent final model. The central claim is that this hybrid manual-assembly-plus-generative-refinement workflow enables specification of spatial intent that is difficult to convey via text or image prompts alone. A within-subjects user study (N=12) reports that MiXR produces designs rated significantly closer to target, with higher perceived control and lower cognitive workload, relative to a generative-composition baseline.

Significance. If the results hold, the work demonstrates a practical way to combine human spatial reasoning with current 3D generative models, which could influence the design of future AR/VR authoring tools. The in-situ harvesting of real geometry and the empirical comparison against a prompt-only baseline are positive aspects. The small sample and within-subjects design limit generalizability but still provide useful initial evidence for the hybrid approach.

major comments (2)
  1. [§4] §4 (User Study), baseline condition: the manuscript must specify the exact prompt formulation and input encoding used for the generative baseline so that readers can judge whether the comparison isolates the benefit of explicit spatial assembly versus differences in prompt quality or model conditioning.
  2. [§3.3] §3.3 (Generative Synthesis): the description of how the user-assembled composition (including spatial relationships among harvested segments) is encoded and passed to the generative model is insufficient to evaluate whether intended geometry and topology are reliably preserved, which directly bears on the central claim that the hybrid workflow succeeds where pure generative methods fail.
minor comments (2)
  1. [Figures] Figure 3 and 4 captions should explicitly state the viewpoint, scale, and what visual elements (e.g., harvested segments vs. final output) are highlighted so that readers can interpret the system screenshots without ambiguity.
  2. [Abstract and §1] The abstract and §1 should briefly note the specific generative model or API employed, as this affects reproducibility and the scope of the claimed advantages.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for their positive evaluation and constructive comments, which help clarify key aspects of our hybrid workflow. We address each major comment below and have revised the manuscript to incorporate the requested details.

read point-by-point responses

  1. Referee: [§4] §4 (User Study), baseline condition: the manuscript must specify the exact prompt formulation and input encoding used for the generative baseline so that readers can judge whether the comparison isolates the benefit of explicit spatial assembly versus differences in prompt quality or model conditioning.

    Authors: We agree that explicit specification of the baseline prompts is necessary for readers to assess the fairness of the comparison. In the revised Section 4, we now include the precise prompt template used for the generative-composition baseline: 'Generate a coherent 3D model that combines the following objects into a single artifact: [list of object names and brief descriptions].' The input is encoded as a single concatenated text prompt with no additional spatial or geometric conditioning beyond the object list; no scene graph or positional data is provided. This formulation matches the information available in the prompt-only condition and isolates the contribution of explicit 3D assembly. revision: yes

  2. Referee: [§3.3] §3.3 (Generative Synthesis): the description of how the user-assembled composition (including spatial relationships among harvested segments) is encoded and passed to the generative model is insufficient to evaluate whether intended geometry and topology are reliably preserved, which directly bears on the central claim that the hybrid workflow succeeds where pure generative methods fail.

    Authors: We appreciate this observation and have expanded Section 3.3 with a detailed account of the encoding pipeline. The user-assembled composition is represented as a 3D scene graph in which each harvested segment retains its original mesh and is annotated with its world-space pose and adjacency relations derived from direct manipulation. This structure is serialized into a structured prompt that includes (1) a point-cloud sampling of the assembled geometry, (2) textual descriptors of pairwise spatial relationships (e.g., 'segment A is attached to the top face of segment B at a 30-degree angle'), and (3) a topology-preserving mask passed to the generative model via its spatial-conditioning interface. We have added pseudocode and a new figure illustrating the conversion from assembly to model input. These additions make explicit how spatial intent is conveyed and preserved, directly supporting the central claim. revision: yes

Circularity Check

0 steps flagged

No significant circularity

full rationale

The paper describes an XR system (MiXR) for harvesting real-world geometry segments, manual 3D assembly to define spatial structure, and generative AI for refinement. Central claims rest on a within-subjects user study (N=12) reporting higher target alignment, control, and lower workload versus a generative baseline. No equations, fitted parameters, derivations, or self-citation chains appear in the manuscript; the evaluation is empirical and externally falsifiable via the reported study protocol rather than reducing to any input by construction.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

This is an HCI systems paper focused on prototype design and empirical evaluation. It introduces no mathematical models, free parameters, axioms, or invented scientific entities.

pith-pipeline@v0.9.0 · 5732 in / 1246 out tokens · 51179 ms · 2026-05-21T08:34:28.694892+00:00 · methodology

Review history (2 revisions) →

discussion (0)

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

Lean theorems connected to this paper

Citations machine-checked in the Pith Canon. Every link opens the source theorem in the public Lean library.

What do these tags mean?
matches
The paper's claim is directly supported by a theorem in the formal canon.
supports
The theorem supports part of the paper's argument, but the paper may add assumptions or extra steps.
extends
The paper goes beyond the formal theorem; the theorem is a base layer rather than the whole result.
uses
The paper appears to rely on the theorem as machinery.
contradicts
The paper's claim conflicts with a theorem or certificate in the canon.
unclear
Pith found a possible connection, but the passage is too broad, indirect, or ambiguous to say the theorem truly supports the claim.

Reference graph

Works this paper leans on

56 extracted references · 56 canonical work pages · 4 internal anchors

  1. [1]

    Shm Garanganao Almeda, JD Zamfirescu-Pereira, Kyu Won Kim, Pradeep Mani Rathnam, and Bjoern Hartmann. 2024. Prompting for discovery: Flex- ible sense-making for ai art-making with dreamsheets. InProceedings of the 2024 CHI Conference on Human Factors in Computing Systems. 1–17

    work page 2024

  2. [2]

    Tyler Angert, Miroslav Suzara, Jenny Han, Christopher Pondoc, and Hariharan Subramonyam. 2023. Spellburst: A node-based interface for exploratory creative coding with natural language prompts. InProceedings of the 36th Annual ACM Symposium on User Interface Software and Technology. 1–22

    work page 2023

  3. [3]

    Oğuz Arslan, Artun Akdoğan, and Mustafa Doga Dogan. 2025. TinkerXR: In-Situ, Reality-Aware CAD and 3D Printing Interface for Novices. InProceedings of the ACM Symposium on Computational Fabrication. 1–19

    work page 2025

  4. [4]

    Karim Benharrak and Amy Pavel. 2025. HistoryPalette: Supporting Exploration and Reuse of Past Alternatives in Image Generation and Editing.arXiv preprint arXiv:2501.04163(2025)

    work page internal anchor Pith review Pith/arXiv arXiv 2025

  5. [5]

    Mark Boss, Zixuan Huang, Aaryaman Vasishta, and Varun Jampani. 2024. Sf3d: Stable fast 3d mesh reconstruction with uv-unwrapping and illumination disen- tanglement.arXiv preprint arXiv:2408.00653(2024)

    work page arXiv 2024

  6. [6]

    Stephen Brade, Bryan Wang, Mauricio Sousa, Sageev Oore, and Tovi Gross- man. 2023. Promptify: Text-to-image generation through interactive prompt exploration with large language models. InProceedings of the 36th Annual ACM Symposium on User Interface Software and Technology. 1–14

    work page 2023

  7. [7]

    Virginia Braun and Victoria Clarke. 2006. Using thematic analysis in psychology. Qualitative research in psychology3, 2 (2006), 77–101

    work page 2006

  8. [8]

    Siddhartha Chaudhuri, Evangelos Kalogerakis, Stephen Giguere, and Thomas Funkhouser. 2013. Attribit: Content Creation with Semantic Attributes. InPro- ceedings of the 26th Annual ACM Symposium on User Interface Software and Tech- nology(St. Andrews, Scotland, United Kingdom)(UIST ’13). Association for Com- puting Machinery, New York, NY, USA, 193–202. doi...

    work page doi:10.1145/2501988.2502008 2013

  9. [9]

    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 Pith/arXiv arXiv 2025

  10. [10]

    Gene Chou, Yuval Bahat, and Felix Heide. 2023. Diffusion-sdf: Conditional generative modeling of signed distance functions. InProceedings of the IEEE/CVF international conference on computer vision. 2262–2272

    work page 2023

  11. [11]

    John Joon Young Chung and Eytan Adar. 2023. Promptpaint: Steering text-to- image generation through paint medium-like interactions. InProceedings of the 36th Annual ACM Symposium on User Interface Software and Technology. 1–17

    work page 2023

  12. [12]

    Hai Dang, Frederik Brudy, George Fitzmaurice, and Fraser Anderson. 2023. World- smith: Iterative and expressive prompting for world building with a generative ai. InProceedings of the 36th Annual ACM Symposium on User Interface Software and Technology. 1–17

    work page 2023

  13. [13]

    Matt Deitke, Dustin Schwenk, Jordi Salvador, Luca Weihs, Oscar Michel, Eli VanderBilt, Ludwig Schmidt, Kiana Ehsani, Aniruddha Kembhavi, and Ali Farhadi

    work page

  14. [14]

    InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition

    Objaverse: A Universe of Annotated 3D Objects. InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 13142–13153

    work page

  15. [15]

    Mustafa Doga Dogan, Patrick Baudisch, Hrvoje Benko, Michael Nebeling, Huaishu Peng, Valkyrie Savage, and Stefanie Mueller. 2022. Fabricate It or Render It? Digital Fabrication vs. Virtual Reality for Creating Objects Instantly. InExtended Abstracts of the 2022 CHI Conference on Human Factors in Computing Systems. Association for Computing Machinery, 5. do...

    work page doi:10.1145/3491101.3516510 2022

  16. [16]

    Mustafa Doga Dogan, Eric J Gonzalez, Karan Ahuja, Ruofei Du, Andrea Colaço, Johnny Lee, Mar Gonzalez-Franco, and David Kim. 2024. Augmented object intelligence with xr-objects. InProceedings of the 37th Annual ACM Symposium on User Interface Software and Technology. 1–15

    work page 2024

  17. [17]

    Faraz Faruqi, Amira Abdel-Rahman, Leandra Tejedor, Martin Nisser, Jiaji Li, Vrushank Phadnis, Varun Jampani, Neil Gershenfeld, Megan Hofmann, and Stefanie Mueller. 2025. MechStyle: Augmenting Generative AI with Mechanical Simulation to Create Stylized and Structurally Viable 3D Models. InProceedings of the ACM Symposium on Computational Fabrication. 1–15

    work page 2025

  18. [18]

    Faraz Faruqi, Ahmed Katary, Tarik Hasic, Amira Abdel-Rahman, Nayeemur Rahman, Leandra Tejedor, Mackenzie Leake, Megan Hofmann, and Stefanie Mueller. 2023. Style2Fab: Functionality-Aware Segmentation for Fabricating Personalized 3D Models with Generative AI. InProceedings of the 36th Annual ACM Symposium on User Interface Software and Technology. 1–13

    work page 2023

  19. [19]

    Faraz Faruqi, Maxine Perroni-Scharf, Jaskaran Singh Walia, Yunyi Zhu, Shuyue Feng, Donald Degraen, and Stefanie Mueller. 2025. TactStyle: Generating Tactile Textures with Generative AI for Digital Fabrication. InProceedings of the 2025 CHI Conference on Human Factors in Computing Systems. 1–16

    work page 2025

  20. [20]

    Faraz Faruqi, Yingtao Tian, Vrushank Phadnis, Varun Jampani, and Stefanie Mueller. 2024. Shaping realities: Enhancing 3D generative AI with fabrication constraints.arXiv preprint arXiv:2404.10142(2024)

    work page arXiv 2024

  21. [21]

    Jun Gao, Tianchang Shen, Zian Wang, Wenzheng Chen, Kangxue Yin, Daiqing Li, Or Litany, Zan Gojcic, and Sanja Fidler. 2022. GET3D: A Generative Model of High Quality 3D Textured Shapes Learned from Images. InAdvances In Neural Information Processing Systems

    work page 2022

  22. [22]

    2025.Gemini 3: A Family of Highly Capable Multimodal Models

    Gemini Team, Google. 2025.Gemini 3: A Family of Highly Capable Multimodal Models. Technical Report. Google DeepMind. https://storage.googleapis.com/ deepmind-media/Model-Cards/Gemini-3-Pro-Model-Card.pdf

    work page 2025

  23. [23]

    Hyojun Go, Byeongjun Park, Jiho Jang, Jin-Young Kim, Soonwoo Kwon, and Changick Kim. 2025. SplatFlow: Multi-View Rectified Flow Model for 3D Gauss- ian Splatting Synthesis. InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 21524–21536

    work page 2025

  24. [24]

    Hudson, and Jennifer Mankoff

    Megan Hofmann, Gabriella Hann, Scott E. Hudson, and Jennifer Mankoff. 2018. Greater than the Sum of Its PARTs: Expressing and Reusing Design Intent in 3D Models. InProceedings of the 2018 CHI Conference on Human Factors in Computing Systems(Montreal QC, Canada)(CHI ’18). Association for Computing Machinery, New York, NY, USA, 1–12. doi:10.1145/3173574.3173875

    work page doi:10.1145/3173574.3173875 2018

  25. [25]

    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 Pith/arXiv arXiv 2023

  26. [26]

    Erzhen Hu, Mingyi Li, Jungtaek Hong, Xun Qian, Alex Olwal, David Kim, Seongkook Heo, and Ruofei Du. 2025. Thing2Reality: Enabling Spontaneous Creation of 3D Objects from 2D Content using Generative AI in XR Meetings. In Proceedings of the 38th Annual ACM Symposium on User Interface Software and Technology. 1–16

    work page 2025

  27. [27]

    Alexander Kirillov, Eric Mintun, Nikhila Ravi, Hanzi Mao, Chloe Rolland, Laura Gustafson, Tete Xiao, Spencer Whitehead, Alexander C Berg, Wan-Yen Lo, et al

    work page

  28. [28]

    InProceedings of the IEEE/CVF international conference on computer vision

    Segment anything. InProceedings of the IEEE/CVF international conference on computer vision. 4015–4026

    work page

  29. [29]

    Roman Klokov, Edmond Boyer, and Jakob Verbeek. 2020. Discrete point flow net- works for efficient point cloud generation. InEuropean Conference on Computer Vision. Springer, 694–710

    work page 2020

  30. [30]

    Yuki Koyama, Shinjiro Sueda, Emma Steinhardt, Takeo Igarashi, Ariel Shamir, and Wojciech Matusik. 2015. AutoConnect: Computational Design of 3D-Printable Connectors.ACM Trans. Graph.34, 6, Article 231 (nov 2015), 11 pages. doi:10. 1145/2816795.2818060

    work page arXiv 2015

  31. [31]

    Brian Lee, Savil Srivastava, Ranjitha Kumar, Ronen Brafman, and Scott R Klem- mer. 2010. Designing with interactive example galleries. InProceedings of the SIGCHI conference on human factors in computing systems. 2257–2266

    work page 2010

  32. [32]

    David Li, Nels Numan, Xun Qian, Yanhe Chen, Zhongyi Zhou, Evgenii Alekseev, Geonsun Lee, Alex Cooper, Min Xia, Scott Chung, et al. 2025. XR Blocks: Accel- erating Human-Centered AI+ XR Innovation.arXiv preprint arXiv:2509.25504 (2025)

    work page arXiv 2025

  33. [33]

    Zisu Li, Jiawei Li, Zeyu Xiong, Shumeng Zhang, Faraz Faruqi, Stefanie Mueller, Chen Liang, Xiaojuan Ma, and Mingming Fan. 2025. InteRecon: Towards Re- constructing Interactivity of Personal Memorable Items in Mixed Reality. In Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems. 1–19

    work page 2025

  34. [34]

    Chen-Hsuan Lin, Jun Gao, Luming Tang, Towaki Takikawa, Xiaohui Zeng, Xun Huang, Karsten Kreis, Sanja Fidler, Ming-Yu Liu, and Tsung-Yi Lin. 2023. Magic3d: High-resolution text-to-3d content creation. InProceedings of the IEEE/CVF Con- ference on Computer Vision and Pattern Recognition. 300–309

    work page 2023

  35. [35]

    Tianqi Liu, Guangcong Wang, Shoukang Hu, Liao Shen, Xinyi Ye, Yuhang Zang, Zhiguo Cao, Wei Li, and Ziwei Liu. 2025. MVSGaussian: Fast Generalizable Gaussian Splatting Reconstruction from Multi-View Stereo. InComputer Vision – ECCV 2024, Aleš Leonardis, Elisa Ricci, Stefan Roth, Olga Russakovsky, Torsten Sattler, and Gül Varol (Eds.). Springer Nature Switz...

    work page 2025

  36. [36]

    Damien Masson, Sylvain Malacria, Géry Casiez, and Daniel Vogel. 2024. Direct- gpt: A direct manipulation interface to interact with large language models. In Proceedings of the 2024 CHI Conference on Human Factors in Computing Systems. 1–16

    work page 2024

  37. [37]

    Yuxuan Mu, Xinxin Zuo, Chuan Guo, Yilin Wang, Juwei Lu, Xiaofeng Wu, Song- cen Xu, Peng Dai, Youliang Yan, and Li Cheng. 2025. GSD: View-Guided Gaussian Splatting Diffusion for 3D Reconstruction. InComputer Vision – ECCV 2024, Aleš Leonardis, Elisa Ricci, Stefan Roth, Olga Russakovsky, Torsten Sattler, and Gül Varol (Eds.). Springer Nature Switzerland, Ch...

    work page 2025

  38. [38]

    Savvas Petridis, Nicholas Diakopoulos, Kevin Crowston, Mark Hansen, Keren Henderson, Stan Jastrzebski, Jeffrey V Nickerson, and Lydia B Chilton. 2023. Anglekindling: Supporting journalistic angle ideation with large language models. InProceedings of the 2023 CHI conference on human factors in computing systems. 1–16

    work page 2023

  39. [39]

    Thijs Jan Roumen, Willi Müller, and Patrick Baudisch. 2018. Grafter: Remixing 3D- Printed Machines. InProceedings of the 2018 CHI Conference on Human Factors in Computing Systems(Montreal QC, Canada)(CHI ’18). Association for Computing Machinery, New York, NY, USA, 1–12. doi:10.1145/3173574.3173637

    work page doi:10.1145/3173574.3173637 2018

  40. [40]

    Ryan Schmidt and Karan Singh. 2010. Meshmixer: An Interface for Rapid Mesh Composition. InACM SIGGRAPH 2010 Talks. Association for Computing Ma- chinery, New York, NY, USA. doi:10.1145/1837026.1837034

    work page doi:10.1145/1837026.1837034 2010

  41. [41]

    Adriana Schulz, Ariel Shamir, David I. W. Levin, Pitchaya Sitthi-amorn, and Wojciech Matusik. 2014. Design and Fabrication by Example.ACM Trans. Graph. 33, 4, Article 62 (jul 2014), 11 pages. doi:10.1145/2601097.2601127

    work page doi:10.1145/2601097.2601127 2014

  42. [42]

    Maria Shugrina, Ariel Shamir, and Wojciech Matusik. 2015. Fab Forms: Cus- tomizable Objects for Fabrication with Validity and Geometry Caching.ACM Faruqi et al. Trans. Graph.34, 4, Article 100 (jul 2015), 12 pages. doi:10.1145/2766994

    work page doi:10.1145/2766994 2015

  43. [43]

    Evgeny Stemasov, Simon Demharter, Max Rädler, Jan Gugenheimer, and Enrico Rukzio. 2024. pARam: Leveraging Parametric Design in Extended Reality to Support the Personalization of Artifacts for Personal Fabrication. InProceedings of the CHI Conference on Human Factors in Computing Systems (CHI ’24). Association for Computing Machinery, New York, NY, USA, 1–...

    work page doi:10.1145/3613904 2024

  44. [44]

    Evgeny Stemasov, Jessica Hohn, Maurice Cordts, Anja Schikorr, Enrico Rukzio, and Jan Gugenheimer. 2023. BrickStARt: Enabling In-situ Design and Tangible Exploration for Personal Fabrication using Mixed Reality.Proceedings of the ACM on Human-Computer Interaction7, ISS (Oct. 2023), 64–92. doi:10.1145/3626465

    work page doi:10.1145/3626465 2023

  45. [45]

    Blair Subbaraman, Shenna Shim, and Nadya Peek. 2023. Forking a sketch: How the openprocessing community uses remixing to collect, annotate, tune, and extend creative code. InProceedings of the 2023 ACM Designing Interactive Systems Conference. 326–342

    work page 2023

  46. [46]

    Hariharan Subramonyam, Roy Pea, Christopher Lawrence Pondoc, Maneesh Agrawala, and Colleen Seifert. 2023. Bridging the Gulf of envisioning: Cognitive design challenges in LLM interfaces.arXiv preprint arXiv:2309.14459(2023)

    work page arXiv 2023

  47. [47]

    Ryo Suzuki, Parastoo Abtahi, Chen Zhu-Tian, Mustafa Doga Dogan, Andrea Colaco, Eric J Gonzalez, Karan Ahuja, and Mar Gonzalez-Franco. 2025. Pro- grammable reality.Frontiers in Virtual Reality6 (2025), 1649785

    work page 2025

  48. [48]

    Jiaxiang Tang, Zhaoxi Chen, Xiaokang Chen, Tengfei Wang, Gang Zeng, and Ziwei Liu. 2024. Lgm: Large multi-view gaussian model for high-resolution 3d content creation. InEuropean Conference on Computer Vision. Springer, 1–18

    work page 2024

  49. [49]

    Tom Veuskens, Florian Heller, and Raf Ramakers. 2021. CODA: A Design Assis- tant to Facilitate Specifying Constraints and Parametric Behavior in CAD Models. InGraphics Interface 2021. https://openreview.net/forum?id=1dLDPJeafRZ

    work page 2021

  50. [50]

    Zhijie Wang, Yuheng Huang, Da Song, Lei Ma, and Tianyi Zhang. 2024. Promptcharm: Text-to-image generation through multi-modal prompting and refinement. InProceedings of the 2024 CHI Conference on Human Factors in Com- puting Systems. 1–21

    work page 2024

  51. [51]

    Christian Weichel, Manfred Lau, David Kim, Nicolas Villar, and Hans Gellersen

    work page

  52. [52]

    doi:10.1145/2556288.2557090

    MixFab: a mixed-reality environment for personal fabrication.CHI ’14 Proceedings of the SIGCHI Conference on Human Factors in Computing Systems (April 2014), 3855–3864. doi:10.1145/2556288.2557090

    work page doi:10.1145/2556288.2557090 2014

  53. [53]

    Jianfeng Xiang, Zelong Lv, Sicheng Xu, Yu Deng, Ruicheng Wang, Bowen Zhang, Dong Chen, Xin Tong, and Jiaolong Yang. 2025. Structured 3d latents for scalable and versatile 3d generation. InProceedings of the IEEE/CVF conference on computer vision and pattern recognition. 21469–21480

    work page 2025

  54. [54]

    Jiale Xu, Weihao Cheng, Yiming Gao, Xintao Wang, Shenghua Gao, and Ying Shan. 2024. Instantmesh: Efficient 3d mesh generation from a single image with sparse-view large reconstruction models.arXiv preprint arXiv:2404.07191(2024)

    work page internal anchor Pith review Pith/arXiv arXiv 2024

  55. [55]

    J Diego Zamfirescu-Pereira, Richmond Y Wong, Bjoern Hartmann, and Qian Yang. 2023. Why Johnny can’t prompt: how non-AI experts try (and fail) to design LLM prompts. InProceedings of the 2023 CHI conference on human factors in computing systems. 1–21

    work page 2023

  56. [56]

    Lei Zhang, Jin Pan, Jacob Gettig, Steve Oney, and Anhong Guo. 2024. Vrcopilot: Authoring 3d layouts with generative ai models in vr. InProceedings of the 37th Annual ACM Symposium on User Interface Software and Technology. 1–13

    work page 2024