pith. sign in

arxiv: 2606.27738 · v1 · pith:ONECPVBMnew · submitted 2026-06-26 · 💻 cs.HC

HandMade: Spatial Prompting for Generative 3D Creation with Part-Labeled VR Sketches

Jialin Huang , Rana Hanocka , Ariel Shamir , Yotam Gingold This is my paper

Pith reviewed 2026-06-29 03:28 UTC · model grok-4.3

classification 💻 cs.HC
keywords spatial promptingVR sketching3D generationpart-labeled sketchesgenerative modelsspatial intentmulti-view guidancehuman-computer interaction
0
0 comments X

The pith

HandMade converts part-labeled VR sketches into multi-view guidance that steers generative 3D models while language supplies identity and details.

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

Text alone cannot reliably specify where object parts should sit or how they should relate in 3D space. HandMade instead accepts coarse VR sketches whose strokes are already segmented by part, then turns those strokes into structured multi-view prompts for existing generative models. The system keeps the sketched spatial scaffold intact while letting language control appearance, materials, and style. Tests on 20 varied objects show clearer preservation of user layout than text-only or unlabeled-sketch baselines. A study with eight participants shows how people naturally assign layout to sketching and everything else to words during both first creation and later changes.

Core claim

HandMade treats coarse, part-labeled 3D sketches not as incomplete geometry to reconstruct directly, but as spatial prompts for existing generative models. It converts segmented VR strokes into multi-view part guidance and structured prompts, allowing users to specify object layout and part relationships through 3D sketching while using language for identity, material, style, and local details. A technical evaluation shows that HandMade better preserves user-authored spatial scaffolds than text-only and sketch-based baselines on 20 varied examples.

What carries the argument

Conversion of segmented VR strokes into multi-view part guidance and structured prompts that existing generative models can read.

If this is right

  • Users can specify object layout and part relationships via 3D sketching.
  • Language is reserved for identity, material, style, and local details.
  • Spatial scaffolds are preserved better than text-only or sketch-based baselines across 20 varied examples.
  • Users split sketching for spatial layout and language for other attributes during both initial authoring and revision.

Where Pith is reading between the lines

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

  • The same prompting pattern could be tested on other generative back-ends to see whether preservation gains hold when the underlying model changes.
  • Extending the stroke-to-guidance step to accept live corrections might shorten the revision loop observed in the user study.
  • The workflow could be compared against direct 3D reconstruction methods to quantify the trade-off between flexibility and geometric fidelity.

Load-bearing premise

Converting segmented VR strokes into multi-view part guidance produces signals that existing generative models can reliably interpret without losing the intended spatial relationships.

What would settle it

Re-running the technical evaluation on the same 20 examples and finding that spatial-scaffold preservation is no better than the text-only or sketch-based baselines would falsify the central claim.

Figures

Figures reproduced from arXiv: 2606.27738 by Ariel Shamir, Jialin Huang, Rana Hanocka, Yotam Gingold.

Figure 1
Figure 1. Figure 1: From rough spatial intent to textured 3D assets. Each column shows one [PITH_FULL_IMAGE:figures/full_fig_p001_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: HandMade pipeline on a candle-holder example. The user provides a rough 3D sketch and a text description with color-coded part semantics; HandMade uses these inputs to synthesize a 3D shape, generate multiview images, and reconstruct a final textured asset. The 3D sketch carries coarse spatial structure, while the text specifies object identity, materials, and part-level appearance. intended 3D shape, exte… view at source ↗
Figure 3
Figure 3. Figure 3: Distribution of Likert responses from the eight user-study participants. Revision-related items have three valid [PITH_FULL_IMAGE:figures/full_fig_p009_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Qualitative example of guide adherence in the multi-view image synthesis stage. Left: the rendered part guide from [PITH_FULL_IMAGE:figures/full_fig_p011_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Representative technical-evaluation examples. The gallery compares input sketches and generated outputs across [PITH_FULL_IMAGE:figures/full_fig_p015_5.png] view at source ↗
read the original abstract

Text-to-3D generation lowers the barrier to 3D content creation, but text alone is a weak interface for specifying spatial intent: where parts should be placed, how they relate, and how an object should be organized in 3D. We present HandMade, a workflow that combines VR 3D sketching and language for open-domain 3D asset generation. HandMade treats coarse, part-labeled 3D sketches not as incomplete geometry to reconstruct directly, but as spatial prompts for existing generative models. It converts segmented VR strokes into multi-view part guidance and structured prompts, allowing users to specify object layout and part relationships through 3D sketching while using language for identity, material, style, and local details. A technical evaluation shows that HandMade better preserves user-authored spatial scaffolds than text-only and sketch-based baselines on 20 varied examples. A user study with eight participants characterizes how users make use of 3D sketching for spatial layout and language for identity, materials, and details across initial authoring and subsequent revision. HandMade contributes an interaction paradigm and interface-to-generation pipeline for spatially guided 3D creation.

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

1 major / 0 minor

Summary. The paper presents HandMade, a workflow combining VR 3D sketching with language for open-domain 3D asset generation. Coarse, part-labeled VR sketches are treated as spatial prompts: segmented strokes are converted into multi-view part guidance and structured prompts, with language handling identity, material, style, and local details. A technical evaluation on 20 varied examples claims HandMade better preserves user-authored spatial scaffolds than text-only and sketch-based baselines; a user study with eight participants characterizes usage patterns for layout versus details across authoring and revision.

Significance. If the preservation claim is substantiated with explicit metrics and protocols, the work would contribute a practical interaction paradigm bridging direct 3D spatial input and generative models, addressing a known weakness of text-only interfaces for part relationships and layout.

major comments (1)
  1. [Abstract] Abstract (technical evaluation paragraph): the central claim that HandMade 'better preserves user-authored spatial scaffolds' than baselines on 20 examples is unsupported by any described protocol, metric (e.g., part-position distance, relational overlap, or 3D consistency score), blinding method, or statistical test. The evaluation therefore cannot be assessed and does not yet substantiate the strongest empirical result.

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for highlighting the need for greater transparency in the abstract's description of the technical evaluation. We address this point directly below and will revise the manuscript accordingly.

read point-by-point responses

  1. Referee: [Abstract] Abstract (technical evaluation paragraph): the central claim that HandMade 'better preserves user-authored spatial scaffolds' than baselines on 20 examples is unsupported by any described protocol, metric (e.g., part-position distance, relational overlap, or 3D consistency score), blinding method, or statistical test. The evaluation therefore cannot be assessed and does not yet substantiate the strongest empirical result.

    Authors: We acknowledge that the abstract paragraph makes a comparative claim without enumerating the supporting protocol or metrics. The full manuscript (Section 5) details the evaluation on the 20 examples, including the specific spatial preservation metrics, baseline implementations, and comparison procedure. However, the abstract itself does not convey this information, which limits immediate assessment of the claim. We will revise the abstract to include a concise statement of the evaluation protocol and metrics used, ensuring the central result is better substantiated at the summary level. revision: yes

Circularity Check

0 steps flagged

No circularity: empirical system description with independent evaluation

full rationale

The paper describes an interaction workflow and pipeline for converting VR sketches into prompts for existing generative models, then reports comparative results on 20 examples. No equations, fitted parameters, predictions derived from inputs, or self-citation chains appear in the provided text. The central claim rests on external comparison to baselines rather than any definitional reduction or imported uniqueness result. This is a standard non-circular empirical HCI/systems paper.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 1 invented entities

The paper introduces an interaction paradigm and conversion pipeline with no free parameters, mathematical axioms, or new physical entities; the only invented element is the HandMade workflow itself.

invented entities (1)
  • HandMade workflow and conversion pipeline no independent evidence
    purpose: To turn part-labeled VR sketches into multi-view guidance and structured prompts for generative models
    The system is presented as a new contribution; no independent evidence outside the paper is supplied.

pith-pipeline@v0.9.1-grok · 5743 in / 1152 out tokens · 35697 ms · 2026-06-29T03:28:49.380779+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

73 extracted references · 45 canonical work pages · 2 internal anchors

  1. [1]

    Rahul Arora, Rubaiat Habib Kazi, Fraser Anderson, Tovi Grossman, Karan Singh, and George Fitzmaurice. 2017. Experimental Evaluation of Sketching on Surfaces in VR. InProceedings of the 2017 CHI Conference on Human Factors in Computing Systems. 5643–5654. doi:10.1145/3025453.3025474

    work page doi:10.1145/3025453.3025474 2017

  2. [2]

    Seok-Hyung Bae, Ravin Balakrishnan, and Karan Singh. 2008. ILoveSketch: As-natural-as-possible Sketching System for Creating 3D Curve Models. InPro- ceedings of the 21st Annual ACM Symposium on User Interface Software and Technology. 151–160. doi:10.1145/1449715.1449740

    work page doi:10.1145/1449715.1449740 2008

  3. [3]

    Hmrishav Bandyopadhyay, Subhadeep Koley, Ayan Das, Ayan Kumar Bhunia, Aneeshan Sain, Pinaki Nath Chowdhury, Tao Xiang, and Yi-Zhe Song. 2024. Doodle Your 3D: From Abstract Freehand Sketches to Precise 3D Shapes. InPro- ceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 9795–9805. doi:10.1109/CVPR52733.2024.00935

    work page doi:10.1109/cvpr52733.2024.00935 2024

  4. [4]

    Video-bench: Human-aligned video generation benchmark

    Amir Barda, Matheus Gadelha, Vladimir G. Kim, Noam Aigerman, Amit H. Bermano, and Thibault Groueix. 2025. Instant3dit: Multiview Inpainting for Fast Editing of 3D Objects. InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 16273–16282. doi:10.1109/CVPR52734.2025.01517

    work page doi:10.1109/cvpr52734.2025.01517 2025

  5. [5]

    Barrera Machuca, Paul Asente, Jingwan Lu, Byungmoon Kim, and Wolfgang Stuerzlinger

    Mayra D. Barrera Machuca, Paul Asente, Jingwan Lu, Byungmoon Kim, and Wolfgang Stuerzlinger. 2018. Multiplanes: Assisted Freehand VR Sketching. In Proceedings of the ACM Symposium on Spatial User Interaction. 36–47. doi:10. 1145/3267782.3267786

    arXiv 2018

  6. [6]

    Mark Boss, Zixuan Huang, Aaryaman Vasishta, and Varun Jampani. 2025. SF3D: Stable Fast 3D Mesh Reconstruction with UV-unwrapping and Illumination Disentanglement. InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. doi:10.1109/CVPR52734.2025.01514

    work page doi:10.1109/cvpr52734.2025.01514 2025

  7. [7]

    Minglin Chen, Longguang Wang, Weihao Yuan, Yukun Wang, Zhe Sheng, Yisheng He, Zilong Dong, Liefeng Bo, and Yulan Guo. 2024. Sketch2NeRF: Multi-view Sketch-guided Text-to-3D Generation. arXiv:2401.14257 [cs.CV] https://arxiv.org/abs/2401.14257

    arXiv 2024

  8. [8]

    Qimin Chen, Yuezhi Yang, Yifan Wang, Vladimir Kim, Siddhartha Chaudhuri, Hao Zhang, and Zhiqin Chen. 2025. ART-DECO: Arbitrary Text Guidance for 3D Detailizer Construction. InProceedings of the SIGGRAPH Asia 2025 Conference Pa- pers. Association for Computing Machinery, 1–12. doi:10.1145/3757377.3763877

    work page doi:10.1145/3757377.3763877 2025

  9. [9]

    Rui Chen, Yongwei Chen, Ningxin Jiao, and Kui Jia. 2023. Fantasia3D: Dis- entangling Geometry and Appearance for High-quality Text-to-3D Content Creation. InProceedings of the IEEE/CVF International Conference on Computer Vision. doi:10.1109/ICCV51070.2023.02033

    work page doi:10.1109/iccv51070.2023.02033 2023

  10. [10]

    Yang Chen, Yingwei Pan, Yehao Li, Ting Yao, and Tao Mei. 2023. Control3D: Towards Controllable Text-to-3D Generation. InProceedings of the 31st ACM International Conference on Multimedia. Association for Computing Machinery, 1148–1156. doi:10.1145/3581783.3612489

    work page doi:10.1145/3581783.3612489 2023

  11. [11]

    Yizi Chen, Sidi Wu, Tianyi Xiao, Nina Wiedemann, and Loic Landrieu

  12. [12]

    arXiv:2512.04761 [cs.CV] doi:10.48550/arXiv.2512.04761

    Order Matters: 3D Shape Generation from Sequential VR Sketches. arXiv:2512.04761 [cs.CV] doi:10.48550/arXiv.2512.04761

    work page doi:10.48550/arxiv.2512.04761

  13. [13]

    10 TRACER: Persistent Regularization for Robust Multimodal Finetuning Fang, A., Jose, A

    Yen-Chi Cheng, Hsin-Ying Lee, Sergey Tulyakov, Alexander G. Schwing, and Liang-Yan Gui. 2023. SDFusion: Multimodal 3D Shape Completion, Reconstruc- tion, and Generation. InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 4456–4465. doi:10.1109/CVPR52729.2023.00433

    work page doi:10.1109/cvpr52729.2023.00433 2023

  14. [14]

    Runlin Duan, Yuzhao Chen, Yichen Hu, Ziyi Liu, Chenfei Zhu, Xiyun Hu, Dizhi Ma, Xinyi Wang, and Karthik Ramani. 2026. JustShape: Exploring Co-Speech Gestures for Multimodal LLM-Powered 3D Parametric Modeling. InProceedings of the 2026 CHI Conference on Human Factors in Computing Systems. 1–31

    2026

  15. [15]

    Elisabetta Fedele, Francis Engelmann, Ian Huang, Or Litany, Marc Pollefeys, and Leonidas J. Guibas. 2026. SpaceControl: Introducing Test-Time Spatial Control to 3D Generative Modeling. InInternational Conference on Learning Representations. arXiv:2512.05343 [cs.CV] doi:10.48550/arXiv.2512.05343

    work page doi:10.48550/arxiv.2512.05343 2026

  16. [16]

    Heckbert

    Michael Garland and Paul S. Heckbert. 1997. Surface simplification using quadric error metrics. InProceedings of the 24th Annual Conference on Computer Graphics and Interactive Techniques (SIGGRAPH ’97). ACM Press/Addison-Wesley Publish- ing Co., USA, 209–216. doi:10.1145/258734.258849

    work page doi:10.1145/258734.258849 1997

  17. [17]

    Songen Gu, Haoxuan Song, Binjie Liu, Qian Yu, Sanyi Zhang, Haiyong Jiang, Jin Huang, and Feng Tian. 2025. VRsketch2Gaussian: 3D VR Sketch Guided 3D Object Generation with Gaussian Splatting. arXiv:2503.12383 [cs.CV] doi:10. 48550/arXiv.2503.12383

    arXiv 2025

  18. [18]

    Benoit Guillard, Edoardo Remelli, Pierre Yvernay, and Pascal Fua. 2021. Sketch2Mesh: Reconstructing and Editing 3D Shapes from Sketches. InPro- ceedings of the IEEE/CVF International Conference on Computer Vision. doi:10. 1109/ICCV48922.2021.01278

    arXiv 2021

  19. [19]

    Yicong Hong, Kai Zhang, Jiuxiang Gu, Sai Bi, Yang Zhou, Difan Liu, Feng Liu, Kalyan Sunkavalli, Trung Bui, and Hao Tan. 2024. LRM: Large Recon- struction Model for Single Image to 3D. InInternational Conference on Learn- ing Representations. https://proceedings.iclr.cc/paper_files/paper/2024/hash/ dcad3425f5c8c36b5b3885c091bf1257-Abstract-Conference.html

    2024

  20. [20]

    Video-bench: Human-aligned video generation benchmark

    Zixuan Huang, Mark Boss, Aaryaman Vasishta, James M. Rehg, and Varun Jampani. 2025. SPAR3D: Stable Point-Aware Reconstruction of 3D Objects from Single Images. InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 16860–16870. doi:10.1109/CVPR52734.2025.01571

    work page doi:10.1109/cvpr52734.2025.01571 2025

  21. [21]

    Zeyuan Huang, Cangjun Gao, Yaxian Shan, Haoxiang Hu, Qingkun Li, Xiaoming Deng, Cuixia Ma, Yu-Kun Lai, Yong-Jin Liu, Feng Tian, Guozhong Dai, and Hongan Wang. 2025. SketchGPT: A Sketch-based Multimodal Interface for Application-Agnostic LLM Interaction. InProceedings of the 38th Annual ACM Symposium on User Interface Software and Technology. Association f...

    work page doi:10.1145/3746059.3747598 2025

  22. [22]

    Takeo Igarashi, Satoshi Matsuoka, and Hidehiko Tanaka. 1999. Teddy: A Sketching Interface for 3D Freeform Design. InProceedings of the 26th An- nual Conference on Computer Graphics and Interactive Techniques. 409–416. doi:10.1145/311535.311602

    work page doi:10.1145/311535.311602 1999

  23. [23]

    Bret Jackson and Daniel F. Keefe. 2016. Lift-Off: Using Reference Imagery and Freehand Sketching to Create 3D Models in VR.IEEE Transactions on Visualization and Computer Graphics22, 4 (2016), 1442–1451. doi:10.1109/TVCG.2016.2518099 12 HandMade: Spatial Prompting for Generative 3D Creation with Part-Labeled VR Sketches

    work page doi:10.1109/tvcg.2016.2518099 2016

  24. [24]

    Seung-Jun Lee, Jeongche Yoon, Sang-Hyun Lee, Joon Hyub Lee, and Seok-Hyung Bae. 2025. 3D Sketching + 2D Generative AI for Car Exterior Design. InProceed- ings of the 38th Annual ACM Symposium on User Interface Software and Technology. Association for Computing Machinery, 1–14. doi:10.1145/3746059.3747609

    work page doi:10.1145/3746059.3747609 2025

  25. [25]

    Haoxuan Li, Ziya Erkoç, Lei Li, Daniele Sirigatti, Vladislav Rosov, Angela Dai, and Matthias Nießner. 2025. MeshPad: Interactive Sketch-Conditioned Artist- Reminiscent Mesh Generation and Editing. InProceedings of the IEEE/CVF Inter- national Conference on Computer Vision. 16227–16237. https://openaccess.thecvf. com/content/ICCV2025/html/Li_MeshPad_Intera...

    2025

  26. [26]

    Jiahao Li, Hao Tan, Kai Zhang, Zexiang Xu, Fujun Luan, Yinghao Xu, Yicong Hong, Kalyan Sunkavalli, Greg Shakhnarovich, and Sai Bi

  27. [27]

    InInternational Conference on Learning Representations

    Instant3D: Fast Text-to-3D with Sparse-view Generation and Large Reconstruction Model. InInternational Conference on Learning Representations. https://proceedings.iclr.cc/paper_files/paper/2024/hash/ 5e8309c9ca683e11672e3dbcd4b87776-Abstract-Conference.html

    2024

  28. [28]

    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 Conference on Computer Vision and Pattern Recognition. 300–309. doi:10.1109/ CVPR52729.2023.00037

    arXiv 2023

  29. [29]

    Feng-Lin Liu, Hongbo Fu, Yu-Kun Lai, and Lin Gao. 2024. SketchDream: Sketch- based Text-to-3D Generation and Editing.ACM Transactions on Graphics43, 4, Article 44 (2024). doi:10.1145/3658120

    work page doi:10.1145/3658120 2024

  30. [30]

    Ruoshi Liu, Rundi Wu, Basile Van Hoorick, Pavel Tokmakov, Sergey Zakharov, and Carl Vondrick. 2023. Zero-1-to-3: Zero-shot One Image to 3D Object. In Proceedings of the IEEE/CVF International Conference on Computer Vision. 9298–

    2023

  31. [31]

    doi:10.1109/ICCV51070.2023.00853

    work page doi:10.1109/iccv51070.2023.00853 2023

  32. [32]

    Yuan Liu, Cheng Lin, Zijiao Zeng, Xiaoxiao Long, Lingjie Liu, Taku Komura, and Wenping Wang. 2024. SyncDreamer: Generating Multiview-consistent Images from a Single-view Image. InInternational Conference on Learn- ing Representations. https://proceedings.iclr.cc/paper_files/paper/2024/hash/ 753d9584b57ba01a10482f1ea7734a89-Abstract-Conference.html

    2024

  33. [33]

    Xiaoxiao Long, Yuan-Chen Guo, Cheng Lin, Yuan Liu, Zhiyang Dou, Lingjie Liu, Yuexin Ma, Song-Hai Zhang, Marc Habermann, Christian Theobalt, and Wenping Wang. 2024. Wonder3D: Single Image to 3D using Cross-Domain Diffusion. InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 9970–9980. doi:10.1109/CVPR52733.2024.00951

    work page doi:10.1109/cvpr52733.2024.00951 2024

  34. [34]

    Sining Lu, Guan Chen, Nam Anh Dinh, Itai Lang, Ari Holtzman, and Rana Hanocka. 2025. LL3M: Large Language 3D Modelers. arXiv:2508.08228 [cs.GR] https://arxiv.org/abs/2508.08228

    arXiv 2025

  35. [35]

    Ling Luo, Pinaki Nath Chowdhury, Tao Xiang, Yi-Zhe Song, and Yulia Gryadit- skaya. 2023. 3D VR Sketch Guided 3D Shape Prototyping and Exploration. In Proceedings of the IEEE/CVF International Conference on Computer Vision. 9267–

    2023

  36. [36]

    doi:10.1109/ICCV51070.2023.00850

    work page doi:10.1109/iccv51070.2023.00850 2023

  37. [37]

    Meta. 2026. Get Started with Passthrough. https://developers.meta.com/horizon/ documentation/unreal/unreal-passthrough-overview-gs/ Accessed 2026-06-07

    2026

  38. [38]

    Aryan Mikaeili, Or Perel, Mehdi Safaee, Daniel Cohen-Or, and Ali Mahdavi-Amiri

  39. [39]

    Adaptive frequency filters as efficient global token mixers

    SKED: Sketch-guided Text-based 3D Editing. InProceedings of the IEEE/CVF International Conference on Computer Vision. doi:10.1109/ICCV51070.2023.01343

    work page doi:10.1109/iccv51070.2023.01343 2023

  40. [40]

    Karla Felix Navarro, Eugene Syriani, and Ian Arawjo. 2026. Reporting and Reviewing LLM-Integrated Systems in HCI: Challenges and Considerations. In Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems. Association for Computing Machinery. doi:10.1145/3772318.3790439

    work page doi:10.1145/3772318.3790439 2026

  41. [41]

    Andrew Nealen, Takeo Igarashi, Olga Sorkine, and Marc Alexa. 2007. FiberMesh: Designing Freeform Surfaces with 3D Curves.ACM Transactions on Graphics26, 3, Article 41 (2007). doi:10.1145/1276377.1276429

    work page doi:10.1145/1276377.1276429 2007

  42. [42]

    OpenAI. 2026. ChatGPT Images 2.0. https://openai.com/index/introducing- chatgpt-images-2-0/ Accessed 2026-06-07

    2026

  43. [43]

    Sharon Oviatt. 1999. Ten Myths of Multimodal Interaction.Commun. ACM42, 11 (1999), 74–81. doi:10.1145/319382.319398

    work page doi:10.1145/319382.319398 1999

  44. [44]

    Sharon Oviatt, Antonella DeAngeli, and Karen Kuhn. 1997. Integration and synchronization of input modes during multimodal human-computer interaction. InProceedings of the ACM SIGCHI Conference on Human factors in computing systems (CHI ’97). Association for Computing Machinery, New York, NY, USA, 415–422. doi:10.1145/258549.258821

    work page doi:10.1145/258549.258821 1997

  45. [45]

    DreamFusion: Text-to-3D using 2D Diffusion

    Ben Poole, Ajay Jain, Jonathan T. Barron, and Ben Mildenhall. 2023. Dream- Fusion: Text-to-3D using 2D Diffusion. InInternational Conference on Learning Representations. arXiv:2209.14988 [cs.CV] doi:10.48550/arXiv.2209.14988

    work page internal anchor Pith review Pith/arXiv arXiv doi:10.48550/arxiv.2209.14988 2023

  46. [46]

    Karl Toby Rosenberg, Rubaiat Habib Kazi, Li-Yi Wei, Haijun Xia, and Ken Perlin

  47. [47]

    In Proceedings of the 37th Annual ACM Symposium on User Interface Software and Technology

    Drawtalking: Building interactive worlds by sketching and speaking. In Proceedings of the 37th Annual ACM Symposium on User Interface Software and Technology. 1–25. doi:10.1145/3654777.3676334

    work page doi:10.1145/3654777.3676334

  48. [48]

    Aditya Sanghi, Pradeep Kumar Jayaraman, Arianna Rampini, Joseph Lambourne, Hooman Shayani, Evan Atherton, and Saeid Asgari Taghanaki. 2023. Sketch-A- Shape: Zero-Shot Sketch-to-3D Shape Generation. InProceedings of the IEEE/CVF International Conference on Computer Vision. https://www.research.autodesk. com/publications/sketch-a-shape/

    2023

  49. [49]

    Yichun Shi, Peng Wang, Jianglong Ye, Mai Long, Kejie Li, and Xiao Yang. 2024. MVDream: Multi-view Diffusion for 3D Generation. InInternational Conference on Learning Representations. https://proceedings.iclr.cc/paper_files/paper/2024/ hash/adbe936993aa7cf41e45054d8b72f183-Abstract-Conference.html

    2024

  50. [50]

    Shivam Ashok Shukla, Raghav Mittal, Lokender Tiwari, and Brojeshwar Bhowmick. 2025. SketchTo3DGen: GenAI Powered Articulation Ready 3D Asset Ideation using 3D Sketches and Audio Descriptions. InProceedings of the 31st ACM Symposium on Virtual Reality Software and Technology. Association for Computing Machinery, Article 119, 3 pages. doi:10.1145/3756884.3770540

    work page doi:10.1145/3756884.3770540 2025

  51. [51]

    Habib Slim, Shariq Farooq Bhat, Mohamed Elhoseiny, Yifan Wang, and Mike Roberts. 2026. CompoSE: Compositional Synthesis and Editing of 3D Shapes via Part-Aware Control. arXiv:2605.19350 [cs.GR] doi:10.48550/arXiv.2605.19350

    work page internal anchor Pith review Pith/arXiv arXiv doi:10.48550/arxiv.2605.19350 2026

  52. [52]

    Xinbin Sun, Zhentong Xu, Guodong Wang, Fuqing Duan, Junli Zhao, Zhenkuan Pan, and Mingquan Zhou. 2026. OmniSketch: Sketch-Guided Text-to-3D Gener- ation with High-Fidelity Geometry and Texture.IEEE Computer Graphics and ApplicationsPP (2026). doi:10.1109/MCG.2026.3667017

    work page doi:10.1109/mcg.2026.3667017 2026

  53. [53]

    Lev Tankelevitch, Viktor Kewenig, Auste Simkute, Ava Elizabeth Scott, Advait Sarkar, Abigail Sellen, and Sean Rintel. 2024. The Metacognitive Demands and Opportunities of Generative AI. InProceedings of the 2024 CHI Conference on Human Factors in Computing Systems. Association for Computing Machinery. doi:10.1145/3613904.3642902

    work page doi:10.1145/3613904.3642902 2024

  54. [54]

    Tencent Hunyuan3D Team. 2025. Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generation. arXiv:2501.12202 [cs.CV] https://arxiv.org/abs/2501.12202

    Pith/arXiv arXiv 2025

  55. [55]

    Dmitry Tochilkin, David Pankratz, Zexiang Liu, Zixuan Huang, Adam Letts, Yangguang Li, Ding Liang, Christian Laforte, Varun Jampani, and Yan-Pei Cao. 2024. TripoSR: Fast 3D Object Reconstruction from a Single Image. arXiv:2403.02151 [cs.CV] https://arxiv.org/abs/2403.02151

    Pith/arXiv arXiv 2024

  56. [56]

    Barbara Tversky and Kathleen Hemenway. 1984. Objects, Parts, and Categories. Journal of Experimental Psychology: General113, 2 (1984), 169–193. doi:10.1037/ 0096-3445.113.2.169

    1984

  57. [57]

    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. Association for Computing Machinery. doi:10.1145/3613904. 3642803

    work page doi:10.1145/3613904 2024

  58. [58]

    Zhengyi Wang, Cheng Lu, Yikai Wang, Fan Bao, Chongxuan Li, Hang Su, and Jun Zhu. 2023. ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation. InAdvances in Neural Information Processing Systems, Vol. 36. https://proceedings.neurips.cc/paper_files/paper/2023/hash/ 1a87980b9853e84dfb295855b425c262-Abstract-Conf...

    2023

  59. [59]

    Zhengyi Wang, Yikai Wang, Yifei Chen, Chendong Xiang, Shuo Chen, Dajiang Yu, Chongxuan Li, Hang Su, and Jun Zhu. 2024. CRM: Single Image to 3D Textured Mesh with Convolutional Reconstruction Model. InComputer Vision – ECCV 2024. Springer, 57–74. doi:10.1007/978-3-031-72751-1_4

    work page doi:10.1007/978-3-031-72751-1_4 2024

  60. [60]

    Weisz, Jessica He, Michael Muller, Gabriela Hoefer, Rachel Miles, and Werner Geyer

    Justin D. Weisz, Jessica He, Michael Muller, Gabriela Hoefer, Rachel Miles, and Werner Geyer. 2024. Design Principles for Generative AI Applications. InPro- ceedings of the 2024 CHI Conference on Human Factors in Computing Systems. Association for Computing Machinery. doi:10.1145/3613904.3642466

    work page doi:10.1145/3613904.3642466 2024

  61. [61]

    Suibi Che-Chuan Weng, Shih-Yu Ma, Sawyer Reinig, Pritalee Kadam, Ada Yi Zhao, Amy Banić, Ryo Suzuki, and Ellen Yi-Luen Do. 2026. Editing Reality: Designing In-Situ Co-Creation with Generative AI in Mixed Reality. InProceedings of the 2026 ACM Designing Interactive Systems Conference. Association for Computing Machinery. doi:10.1145/3800645.3813087

    work page doi:10.1145/3800645.3813087 2026

  62. [62]

    Kailu Wu, Fangfu Liu, Zhihan Cai, Runjie Yan, Hanyang Wang, Yating Hu, Yueqi Duan, and Kaisheng Ma. 2024. Unique3D: High-Quality and Efficient 3D Mesh Generation from a Single Image. InAdvances in Neural Information Processing Systems, Vol. 37. doi:10.52202/079017-3974

    work page doi:10.52202/079017-3974 2024

  63. [63]

    Yingbin Wu, Fubo Wang, Peng Zhao, Mingquan Zhou, Shengling Geng, and Dan Zhang. 2026. High-Fidelity 3D Mesh Generation from a Single Sketch Using Shape Constraints.Scientific Reports16, Article 1127 (2026). doi:10.1038/s41598- 025-30843-3

    work page doi:10.1038/s41598- 2026

  64. [64]

    Jiatong Xia, Zicheng Duan, Anton van den Hengel, and Lingqiao Liu

  65. [65]

    arXiv:2603.18782 [cs.CV] doi:10.48550/arXiv.2603.18782 Accepted to CVPR 2026

    Points-to-3D: Structure-Aware 3D Generation with Point Cloud Priors. arXiv:2603.18782 [cs.CV] doi:10.48550/arXiv.2603.18782 Accepted to CVPR 2026

    work page doi:10.48550/arxiv.2603.18782 2026

  66. [66]

    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:2404.07191 [cs.CV] https: //arxiv.org/abs/2404.07191

    Pith/arXiv arXiv 2024

  67. [67]

    Hyejeong Yoon, Wonjong Jang, Yoonha Hwang, and Seungyong Lee. 2026. 3D Character Reconstruction from Hand-Drawn Model Sheets.Computer Graphics Forum(2026). doi:10.1111/cgf.70323 Eurographics 2026

    work page doi:10.1111/cgf.70323 2026

  68. [68]

    Xue Yu, Stephen DiVerdi, Akshay Sharma, and Yotam Gingold. 2021. ScaffoldS- ketch: Accurate Industrial Design Drawing in VR. InProceedings of the 34th Annual ACM Symposium on User Interface Software and Technology. 372–384. doi:10.1145/3472749.3474756

    work page doi:10.1145/3472749.3474756 2021

  69. [69]

    Ying Zang, Yidong Han, Chaotao Ding, Jianqi Zhang, and Tianrun Chen. 2026. Magic3DSketch: Create Colorful 3D Models from Sketch-Based 3D Modeling 13 Jialin Huang, Rana Hanocka, Ariel Shamir, and Yotam Gingold Guided by Text and Language-Image Pre-Training.Neurocomputing661 (2026), 131925. doi:10.1016/j.neucom.2025.131925

    work page doi:10.1016/j.neucom.2025.131925 2026

  70. [70]

    Ying Zang, Chunan Yu, Jiahao Zhang, Jing Li, Shengyuan Zhang, Lanyun Zhu, Chaotao Ding, Renjun Xu, and Tianrun Chen. 2026. From Sketch to Reality: Enabling High-Quality, Cross-Category 3D Model Generation from Free-Hand Sketches with Minimal Data.IEEE Transactions on Visualization and Computer GraphicsPP (2026). doi:10.1109/TVCG.2026.3661544

    work page doi:10.1109/tvcg.2026.3661544 2026

  71. [71]

    Song-Hai Zhang, Yuan-Chen Guo, and Qing-Wen Gu. 2021. Sketch2Model: View-Aware 3D Modeling from Single Free-Hand Sketches. InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 6012–6021. doi:10.1109/CVPR46437.2021.00595

    work page doi:10.1109/cvpr46437.2021.00595 2021

  72. [72]

    Yuxiao Zhang, Jin Wang, Yang Zhou, Senyun Jia, Zhi Zheng, Dongliang Zhang, and Guodong Lu. 2026. 3D Modeling from a Single Sketch with Multifaceted Semantic Understanding.Expert Systems with Applications298 (2026), 129748. doi:10.1016/j.eswa.2025.129748

    work page doi:10.1016/j.eswa.2025.129748 2026

  73. [73]

    Xin-Yang Zheng, Hao Pan, Peng-Shuai Wang, Xin Tong, Yang Liu, and Heung- Yeung Shum. 2023. Locally Attentional SDF Diffusion for Controllable 3D Shape Generation.ACM Transactions on Graphics42, 4, Article 91 (2023). doi:10.1145/ 3592103 14 HandMade: Spatial Prompting for Generative 3D Creation with Part-Labeled VR Sketches Figure 5: Representative technic...

    2023