pith. sign in

arxiv: 2607.00829 · v1 · pith:TT5UALOAnew · submitted 2026-07-01 · 💻 cs.CV

Stitched Embeddings: A Unified Latent Space for 3D Garments and 2D Patterns

Andrea Sanchietti , Riccardo Marin , Bharat Lal Bhatnagar , Yuanlu Xu , Gerard Pons-Moll This is my paper

Pith reviewed 2026-07-02 13:52 UTC · model grok-4.3

classification 💻 cs.CV
keywords stitched embeddings3D garments2D sewing patternslatent spacegarment reconstructionpattern inferencesimulation-freeBoxMesh
0
0 comments X

The pith

Stitched Embeddings create a single bidirectional latent space that maps 3D garments to 2D sewing patterns and back without simulation.

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

The paper tries to establish that a unified latent space can handle both reconstructing 3D garments from scans and inferring the 2D sewing patterns needed to make them, all without running any physical simulation. A sympathetic reader would care because traditional approaches require slow simulations to connect flat patterns to 3D shapes, and high-quality garment data is scarce. The method uses geometric priors from a pretrained 3D model to compensate for limited data and introduces BoxMesh as an intermediate form that lines up 2D panels in 3D space. This setup reaches high accuracy on pattern reconstruction, runs faster, and supports new tasks such as pulling patterns out of existing 3D meshes or editing 3D shapes by changing 2D patterns. If correct, the work would give a direct computational bridge from neural vision outputs to the physical steps of cutting and sewing clothes.

Core claim

Stitched Embeddings is the first simulation-free framework to unify 3D garment reconstruction and sewing pattern inference within a single bidirectional latent space. By leveraging the geometric priors of a pretrained 3D foundation model, the approach overcomes data scarcity. The BoxMesh serves as a critical intermediate representation to align 2D panels into 3D configurations without the computational overhead of a simulator. This architecture achieves state-of-the-art accuracy in pattern reconstruction while significantly improving efficiency. The differentiable pipeline enables pattern recovery from meshes and 3D editing from 2D patterns, providing a scalable link between neural 3D vision

What carries the argument

The bidirectional latent space of Stitched Embeddings, which uses BoxMesh as the intermediate representation to align 2D panels into 3D without simulation.

If this is right

  • Achieves state-of-the-art accuracy in pattern reconstruction.
  • Significantly improves efficiency compared with simulation-based methods.
  • Enables pattern recovery from meshes.
  • Allows 3D editing from modifications to 2D patterns.
  • Provides a scalable link between neural 3D vision and the physical garment manufacturing pipeline.

Where Pith is reading between the lines

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

  • Design tools could let users switch freely between editing a 2D pattern and seeing the immediate 3D result in the same space.
  • The latent space might support fit prediction on varied body shapes by treating body variation as an additional conditioning signal.
  • The same alignment approach could be tested on other flat-to-3D manufacturing tasks such as sheet-metal bending or inflatable structures.
  • A direct check would measure whether seam lengths and panel areas remain consistent across the 2D-to-3D round trip without extra constraints.

Load-bearing premise

The BoxMesh representation can align 2D panels into accurate 3D configurations without simulation, and the pretrained 3D model supplies enough geometric priors to handle the scarcity of garment data.

What would settle it

Running the model on a set of 3D garment meshes and finding that the output 2D patterns, when physically sewn, produce shapes that deviate measurably from the input meshes in key dimensions such as seam lengths or overall fit.

Figures

Figures reproduced from arXiv: 2607.00829 by Andrea Sanchietti, Bharat Lal Bhatnagar, Gerard Pons-Moll, Riccardo Marin, Yuanlu Xu.

Figure 1
Figure 1. Figure 1: In this work, we propose Stitched Embeddings (StEm), a unified latent space to jointly represent 3D garments and their corresponding 2D sewing patterns. Our method, StEm-Net, provides state-of-the-art performance for sewing pattern pre￾diction from 3D garments. Our approach is trained end-to-end, and supports test-time adaptation for sewing pattern predictions and seamless propagation of editing from sewin… view at source ↗
Figure 2
Figure 2. Figure 2: An example of sewing patterns. Ev￾ery garment is represented by a set of pan￾els. While sometimes their semantic meaning is clear (e.g., for the body), for others it is dif￾ficult to guess without simulating them (e.g., the pieces on the right are a skirt and pants) [PITH_FULL_IMAGE:figures/full_fig_p005_2.png] view at source ↗
Figure 4
Figure 4. Figure 4: On the left: StEm-Net is the first end-to-end differentiable method that unifies multiple different representations in a common compact representation. The model can map BoxMeshes and 3D garments into Stitched Embeddings. From such a latent space, we decode sewing pattern parameters and UDFs. On the right, we show our method’s modalities: prediction of Pattern Parameters from an input Mesh (top), and editi… view at source ↗
Figure 5
Figure 5. Figure 5: Autoencoding of StEm-Net. On the left, we show the input mesh. We pass this mesh to our garment encoder Eg, which maps it into our StEm latent space. From that, we recover the 3D garment via D3D, and the sewing patterns via DSP , which we also simulate to obtain the corresponding 3D. We can appreciate that both the 3D output and the simulated sewing patterns produce geometry close to the ground truth, prov… view at source ↗
Figure 6
Figure 6. Figure 6: Qualitative comparison on NeuralTailor test set. Our method provides robust predictions, even in the presence of nuances such as strings or hoodies with long, large sleeves. NeuralTailor [28] predicts inaccurate patterns, often resulting in dramatic fail￾ures. Our test-time latent optimization often recovers nuances and fixes inconsistencies, whereas in the worst case, it preserves the quality of the origi… view at source ↗
Figure 7
Figure 7. Figure 7: Qualitative comparison on GarmentCodeData [26] [PITH_FULL_IMAGE:figures/full_fig_p013_7.png] view at source ↗
Figure 8
Figure 8. Figure 8: Editing examples. For each example, we show on the left the initial sewing pat￾tern with its 3D physical simulation (blue garment). On the right, the edited sewing pattern, with our network’s prediction (red) and the ground truth (green). We ob￾serve that our framework provides an accurate estimation of the garment’s appearance without requiring physical simulation, both for global behaviors (e.g., length … view at source ↗
Figure 9
Figure 9. Figure 9: Qualitative comparison on scans from 4DDress. StEm-Net reconstructs garments that adhere more closely to the input geometry than NeuralTailor. Translation Noise σ (cm) Normal Noise σ Chamfer Distance (cm) Chamfer Distance (cm) Input D3D σ0 σ5 σ10 σ0.0 σ0.25 σ0.50 [PITH_FULL_IMAGE:figures/full_fig_p015_9.png] view at source ↗
read the original abstract

While garments are essential for realistic digital humans, their topological variety makes them much harder to model than parametric bodies. Traditional tailoring relies on 2D sewing patterns, yet bridging these patterns to 3D geometry currently requires physical simulations. We present Stitched Embeddings, the first simulation-free framework to unify 3D garment reconstruction and sewing pattern inference within a single bidirectional latent space. By leveraging the geometric priors of a pretrained 3D foundation model, our approach overcomes the data scarcity typically associated with high-quality garment modeling. We propose to use the BoxMesh as a critical intermediate representation to align 2D panels into 3D configurations without the computational overhead of a simulator. This architecture achieves state-of-the-art accuracy in pattern reconstruction while significantly improving efficiency. Furthermore, our differentiable pipeline enables novel applications, including pattern recovery from meshes and 3D editing from 2D patterns. Finally, this work provides a scalable link between neural 3D vision and the physical garment manufacturing pipeline. Project Page: https://andreus00.github.io/stitchedembeddings

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 / 1 minor

Summary. The manuscript presents Stitched Embeddings, the first simulation-free framework to unify 3D garment reconstruction and sewing pattern inference within a single bidirectional latent space. It leverages geometric priors from a pretrained 3D foundation model to address data scarcity and proposes the BoxMesh as an intermediate representation to align 2D panels into 3D configurations without physical simulation. The architecture is claimed to achieve state-of-the-art accuracy in pattern reconstruction with improved efficiency, while the differentiable pipeline enables applications such as pattern recovery from meshes and 3D editing from 2D patterns, providing a scalable link between neural 3D vision and garment manufacturing.

Significance. If the empirical claims hold, the work would represent a meaningful advance in 3D garment modeling by removing the computational cost of simulations and enabling bidirectional inference between 2D patterns and 3D geometry. The use of pretrained priors to mitigate data scarcity and the introduction of BoxMesh as an alignment mechanism are potentially impactful if shown to be robust. The bidirectional latent space and differentiability open avenues for downstream tasks in digital humans and manufacturing pipelines.

major comments (2)
  1. [Abstract] Abstract: the central claim of 'state-of-the-art accuracy in pattern reconstruction' and 'significantly improving efficiency' is presented without any quantitative results, baseline comparisons, error metrics, or ablation studies. This absence is load-bearing for the superiority assertion and prevents assessment of whether the data or methods support the stated performance.
  2. [Abstract] Abstract: the claim that BoxMesh serves as 'a critical intermediate representation to align 2D panels into 3D configurations without the computational overhead of a simulator' is a load-bearing assumption, yet no description of the alignment procedure, geometric constraints, or validation against simulation-based methods is provided. Without this, it is impossible to evaluate whether the approach truly avoids hidden simulation-like costs or failure modes.
minor comments (1)
  1. The project page URL is referenced but the manuscript should include a stable citation or DOI for reproducibility.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for their comments, which focus on strengthening the abstract's support for its claims. We address each point below and will revise the abstract accordingly.

read point-by-point responses

  1. Referee: [Abstract] Abstract: the central claim of 'state-of-the-art accuracy in pattern reconstruction' and 'significantly improving efficiency' is presented without any quantitative results, baseline comparisons, error metrics, or ablation studies. This absence is load-bearing for the superiority assertion and prevents assessment of whether the data or methods support the stated performance.

    Authors: The referee is correct that the abstract, as written, states these performance claims at a high level without supporting numbers. The full manuscript reports quantitative results, baselines, error metrics, and ablations in the experiments section. To address the concern directly, we will revise the abstract to include concise quantitative highlights (e.g., key error reductions and runtime improvements) drawn from those results. revision: yes

  2. Referee: [Abstract] Abstract: the claim that BoxMesh serves as 'a critical intermediate representation to align 2D panels into 3D configurations without the computational overhead of a simulator' is a load-bearing assumption, yet no description of the alignment procedure, geometric constraints, or validation against simulation-based methods is provided. Without this, it is impossible to evaluate whether the approach truly avoids hidden simulation-like costs or failure modes.

    Authors: The referee correctly notes that the abstract provides no procedural details on BoxMesh alignment. The manuscript describes the alignment procedure, geometric constraints, and validation (including comparisons to simulation) in the methods and experiments sections. We will revise the abstract to add a brief clause summarizing the alignment approach and its validation, while keeping the abstract concise. revision: yes

Circularity Check

0 steps flagged

No significant circularity detected

full rationale

The provided text is limited to the abstract, which contains no equations, derivations, or load-bearing methodological steps. No specific quotes from the paper can be exhibited to show any reduction by construction, self-definition, fitted inputs called predictions, or self-citation chains. Per the hard rules, circularity requires quoting the paper and exhibiting the specific reduction; absent any such technical content, the finding is no significant circularity (score 0). The high-level claims about BoxMesh and pretrained priors cannot be inspected for circularity from the given material alone.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

Only the abstract is available; no specific free parameters, axioms, or invented entities can be identified from the given information.

pith-pipeline@v0.9.1-grok · 5734 in / 1036 out tokens · 33664 ms · 2026-07-02T13:52:44.560469+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

80 extracted references · 8 canonical work pages · 3 internal anchors

  1. [1]

    In: 2024 international conference on 3D vision (3DV)

    Antić, D., Tiwari, G., Ozcomlekci, B., Marin, R., Pons-Moll, G.: Close: A 3d cloth- ing segmentation dataset and model. In: 2024 international conference on 3D vision (3DV). pp. 591–601. IEEE (2024)

    2024

  2. [2]

    In: Computer Graphics Forum

    Bang, S., Korosteleva, M., Lee, S.H.: Estimating garment patterns from static scan data. In: Computer Graphics Forum. vol. 40, pp. 273–287. Wiley Online Library (2021)

    2021

  3. [3]

    Acm Transactions on Graphics (TOG)32(4), 1–12 (2013)

    Berthouzoz, F., Garg, A., Kaufman, D.M., Grinspun, E., Agrawala, M.: Parsing sewing patterns into 3d garments. Acm Transactions on Graphics (TOG)32(4), 1–12 (2013)

    2013

  4. [4]

    In: Proceedings of the IEEE/CVF Inter- national Conference on Computer Vision (ICCV) (October 2019)

    Bhatnagar, B.L., Tiwari, G., Theobalt, C., Pons-Moll, G.: Multi-garment net: Learning to dress 3d people from images. In: Proceedings of the IEEE/CVF Inter- national Conference on Computer Vision (ICCV) (October 2019)

    2019

  5. [5]

    Bian, S., Xu, C., Xiu, Y., Grigorev, A., Liu, Z., Lu, C., Black, M.J., Feng, Y.: Chat- garment: Garment estimation, generation and editing via large language models (2025)

    2025

  6. [6]

    arXiv preprint arXiv:2601.09658 (2026)

    Can, S.E., Ackermann, J., Nakayama, K., Liu, R., Wu, T., Zheng, Y., Bertiche, H., Chai, M., Beeler, T., Wetzstein, G.: Image2garment: Simulation-ready garment generation from a single image. arXiv preprint arXiv:2601.09658 (2026)

    work page arXiv 2026

  7. [7]

    In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)

    Chen, C.H., Su, J.W., Hu, M.C., Yao, C.Y., Chu, H.K.: Panelformer: Sewing pat- tern reconstruction from 2d garment images. In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV). pp. 454–463 (January 2024)

    2024

  8. [8]

    ACM Transactions on Graphics (TOG)34(6), 1–12 (2015)

    Chen, X., Zhou, B., Lu, F., Wang, L., Bi, L., Tan, P.: Garment modeling with a depth camera. ACM Transactions on Graphics (TOG)34(6), 1–12 (2015)

    2015

  9. [9]

    In: Advances in Neural Information Processing Systems (NeurIPS) (December 2020)

    Chibane, J., Mir, A., Pons-Moll, G.: Neural unsigned distance fields for im- plicit function learning. In: Advances in Neural Information Processing Systems (NeurIPS) (December 2020)

    2020

  10. [10]

    In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition

    De Luigi, L., Li, R., Guillard, B., Salzmann, M., Fua, P.: Drapenet: Garment gen- eration and self-supervised draping. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 1451–1460 (2023)

    2023

  11. [11]

    Advances in Neural Information Processing Systems36, 35799–35813 (2023)

    Deitke, M., Liu, R., Wallingford, M., Ngo, H., Michel, O., Kusupati, A., Fan, A., Laforte, C., Voleti, V., Gadre, S.Y., et al.: Objaverse-xl: A universe of 10m+ 3d objects. Advances in Neural Information Processing Systems36, 35799–35813 (2023)

    2023

  12. [12]

    In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition

    Deitke, M., Schwenk, D., Salvador, J., Weihs, L., Michel, O., VanderBilt, E., Schmidt, L., Ehsani, K., Kembhavi, A., Farhadi, A.: Objaverse: A universe of annotated 3d objects. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. pp. 13142–13153 (2023)

    2023

  13. [13]

    In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

    Eskandar, D., Kabadayi, B., Tiwari, G., Pons-Moll, G.: Dama: Disentangled body- anchored gaussians for controllable multi-layered avatars. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). pp. 5799–5811 (June 2026)

    2026

  14. [14]

    Computers & Graphics p

    Garavaso, D., Masi, F., Musoni, P., Castellani, U.: Point cloud segmentation for 3d clothed human layering. Computers & Graphics p. 104393 (2025)

    2025

  15. [15]

    arXiv preprint arXiv:2405.12663 (2024) Stitched Embeddings 17

    Gong, J., Ji, S., Foo, L.G., Chen, K., Rahmani, H., Liu, J.: Laga: Layered 3d avatar generation and customization via gaussian splatting. arXiv preprint arXiv:2405.12663 (2024) Stitched Embeddings 17

    work page arXiv 2024

  16. [16]

    In: Proceedings of the 29th annual conference on Computer graphics and interactive techniques

    Gu, X., Gortler, S.J., Hoppe, H.: Geometry images. In: Proceedings of the 29th annual conference on Computer graphics and interactive techniques. pp. 355–361 (2002)

    2002

  17. [17]

    Guo, J., Chen, J., Chen, W., Sun, Z., Li, L., Zhao, B., Zhu, L., Wang, X., Liu, Q.: Garmentx: Autoregressive parametric representations for high-fidelity 3d garment generation (2025)

    2025

  18. [18]

    In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

    Guo, M., Chiang, M.J.Y., Santesteban, I., Sarafianos, N., Chen, H.y., Halimi, O., Božič, A., Saito, S., Wu, J., Liu, C.K., Stuyck, T., Larionov, E.: Pgc: Physics-based gaussian cloth from a single pose. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). pp. 21215–21225 (June 2025)

    2025

  19. [19]

    ACM Transactions on Graph- ics (TOG)43(4), 1–13 (2024)

    He, K., Yao, K., Zhang, Q., Yu, J., Liu, L., Xu, L.: Dresscode: Autoregressively sewing and generating garments from text guidance. ACM Transactions on Graph- ics (TOG)43(4), 1–13 (2024)

    2024

  20. [20]

    In: 2023 nicograph international (NicoInt)

    He, Y., Xie, H., Miyata, K.: Sketch2cloth: Sketch-based 3d garment generation with unsigned distance fields. In: 2023 nicograph international (NicoInt). pp. 38–

    2023

  21. [21]

    In: Computer Vision – ECCV 2020

    Heming, Z., Yu, C., Hang, J., Weikai, C., Dong, D., Zhangye, W., Shuguang, C., Xiaoguang, H.: Deep fashion3d: A dataset and benchmark for 3d garment recon- struction from single images. In: Computer Vision – ECCV 2020. pp. 512–530. Springer International Publishing (2020)

    2020

  22. [22]

    Neural computation 9(8), 1735–1780 (1997)

    Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural computation 9(8), 1735–1780 (1997)

    1997

  23. [23]

    arXiv preprint arXiv:2203.00806 , year=

    Howell, T.A., Le Cleac’h, S., Kolter, J.Z., Schwager, M., Manchester, Z.: Dojo: A differentiable simulator for robotics. arXiv preprint arXiv:2203.008069(2), 4 (2022)

    work page arXiv 2022

  24. [24]

    IEEE Transactions on Visualization and Computer Graphics32(7), 6350–6362 (2026)

    Jin, L., Jin, Z., Ye, Z., Pang, H., Han, X., Zheng, Y., Li, H.: Inversedraping: Recovering sewing patterns from 3d garment surfaces via boxmesh bridging. IEEE Transactions on Visualization and Computer Graphics32(7), 6350–6362 (2026)

    2026

  25. [25]

    In: Computer Graphics Forum

    Jung, M., Lee, D., Lee, I.K.: Clothingtwin: Reconstructing inner and outer layers of clothing using 3d gaussian splatting. In: Computer Graphics Forum. vol. 44, p. e70240. Wiley Online Library (2025)

    2025

  26. [26]

    In: Computer Vision – ECCV 2024 (2024)

    Korosteleva, M., Kesdogan, T.L., Kemper, F., Wenninger, S., Koller, J., Zhang, Y., Botsch, M., Sorkine-Hornung, O.: GarmentCodeData: A dataset of 3D made- to-measure garments with sewing patterns. In: Computer Vision – ECCV 2024 (2024)

    2024

  27. [27]

    In: Vanschoren, J., Yeung, S

    Korosteleva, M., Lee, S.H.: Generating datasets of 3d garments with sewing pat- terns. In: Vanschoren, J., Yeung, S. (eds.) Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks. vol. 1 (2021)

    2021

  28. [28]

    ACM Trans

    Korosteleva, M., Lee, S.H.: Neuraltailor: Reconstructing sewing pattern structures from 3d point clouds of garments. ACM Trans. Graph.41(4) (2022)

    2022

  29. [29]

    ACM Transaction on Graphics42(6) (2023), sIGGRAPH ASIA 2023 issue

    Korosteleva, M., Sorkine-Hornung, O.: GarmentCode: Programming parametric sewing patterns. ACM Transaction on Graphics42(6) (2023), sIGGRAPH ASIA 2023 issue

    2023

  30. [30]

    In: European Conference on Computer Vision (ECCV) (2026)

    Kostyrko,M.,Xue,Y.,Tiwari,G.,Pons-Moll,G.:Revisitingavatar-as-image:High- fidelity registration is all you need. In: European Conference on Computer Vision (ECCV) (2026)

    2026

  31. [31]

    ReWeaver: Towards Simulation-Ready and Topology-Accurate Garment Reconstruction

    Li, M., Shan, H., Zheng, K., Shen, C., Liu, S., Fu, Y., Chen, Z., Huang, X.: Reweaver: Towards simulation-ready and topology-accurate garment reconstruc- tion. arXiv preprint arXiv:2601.16672 (2026) 18 A. Sanchietti et al

    work page internal anchor Pith review Pith/arXiv arXiv 2026

  32. [32]

    ACM Transactions on Graphics (TOG)44(6), 1–23 (2025)

    Li, S., Liu, R., Liu, C., Wang, Z., He, G., Li, Y.L., Jin, X., Wang, H.: Garmagenet: A multimodal generative framework for sewing pattern design and generic garment modeling. ACM Transactions on Graphics (TOG)44(6), 1–23 (2025)

    2025

  33. [33]

    In: Kwok, J

    Li, X., Yao, Q., Wang, Y.: Garmentdiffusion: 3d garment sewing pattern genera- tion with multimodal diffusion transformers. In: Kwok, J. (ed.) Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25. pp. 1458–1466. International Joint Conferences on Artificial Intelligence Organiza- tion (8 2025), main Track

    2025

  34. [34]

    In: ProceedingsoftheIEEE/CVFConferenceonComputerVisionandPatternRecog- nition (CVPR) (June 2024)

    Li, Y., Chen, H.y., Larionov, E., Sarafianos, N., Matusik, W., Stuyck, T.: Dif- fAvatar: Simulation-ready garment optimization with differentiable simulation. In: ProceedingsoftheIEEE/CVFConferenceonComputerVisionandPatternRecog- nition (CVPR) (June 2024)

    2024

  35. [35]

    ACM Transactions on Graphics (SIGGRAPH Asia) (2023)

    Liu, L., Xu, X., Lin, Z., Liang, J., Yan, S.: Towards garment sewing pattern recon- struction from a single image. ACM Transactions on Graphics (SIGGRAPH Asia) (2023)

    2023

  36. [36]

    Inter- national Conference on Computer Vision (ICCV) (2025)

    Liu, S., Cheng, Y., Chen, Z., Ren, X., Zhu, W., Li, L., Bi, M., Yang, X., Yan, Y.: Multimodal latent diffusion model for complex sewing pattern generation. Inter- national Conference on Computer Vision (ICCV) (2025)

    2025

  37. [37]

    IEEE Transactions on Visualization and Computer Graphics31(4), 2142–2154 (2024)

    Liu, X., Li, J., Lu, G.: Reconstructing complex shaped clothing from a single image with feature stable unsigned distance fields. IEEE Transactions on Visualization and Computer Graphics31(4), 2142–2154 (2024)

    2024

  38. [38]

    liu et al

    Liu, Y., Tang, J., Zheng, C., Zhu, J., Wang, C., Huang, D.: Clothedreamer: Text- guided garment generation with 3d gaussians: Y. liu et al. Applied Intelligence 55(10), 767 (2025)

    2025

  39. [39]

    In: ICLR (2024)

    Liu, Z., Feng, Y., Xiu, Y., Liu, W., Paull, L., Black, M.J., Schölkopf, B.: Ghost on the shell: An expressive representation of general 3d shapes. In: ICLR (2024)

    2024

  40. [40]

    Loper, M., Mahmood, N., Romero, J., Pons-Moll, G., Black, M.J.: SMPL: A skinnedmulti-personlinearmodel.ACMTrans.Graphics(Proc.SIGGRAPHAsia) 34(6), 248:1–248:16 (Oct 2015)

    2015

  41. [41]

    IEEE Transactions on Circuits and Systems for Video Technology (2025)

    Luo, J., Qu, H., Zhao, Y., Zhang, J., Yang, Y.: Deep learning for 3d fashion design: A survey from a sewing pattern-driven perspective. IEEE Transactions on Circuits and Systems for Video Technology (2025)

    2025

  42. [42]

    In: NVIDIA GPU Technology Conference (GTC)

    Macklin, M.: Warp: A high-performance python framework for gpu simulation and graphics. In: NVIDIA GPU Technology Conference (GTC). vol. 3 (2022)

    2022

  43. [43]

    In: European Conference on Computer Vision (ECCV) (2026)

    Mir, A., Guler, R.A., Tang, X., Wonka, P., Pons-Moll, G.: Ahoy! animatable hu- mans under occlusion from youtube videos with gaussian splatting and video dif- fusion priors. In: European Conference on Computer Vision (ECCV) (2026)

    2026

  44. [44]

    In: Smart Tools and Applications in Graphics - Eurographics Italian Chapter Conference

    Musoni, P., Melzi, S., Castellani, U.: Gim3d: A 3d dataset for garment segmenta- tion. In: Smart Tools and Applications in Graphics - Eurographics Italian Chapter Conference. The Eurographics Association (2022)

    2022

  45. [45]

    Graphical models129, 101187 (2023)

    Musoni, P., Melzi, S., Castellani, U.: Gim3d plus: A labeled 3d dataset to design data-driven solutions for dressed humans. Graphical models129, 101187 (2023)

    2023

  46. [46]

    In: European Conference on Computer Vision

    Musoni, P., Melzi, S., Castellani, U.: Capturing and modeling real cloth deforma- tions for virtual garment design. In: European Conference on Computer Vision. pp. 320–336. Springer (2024)

    2024

  47. [47]

    In: Proceedings of the Computer Vision and Pattern Recognition Conference

    Nakayama, K., Ackermann, J., Kesdogan, T.L., Zheng, Y., Korosteleva, M., Sorkine-Hornung, O., Guibas, L.J., Yang, G., Wetzstein, G.: Aipparel: A multi- modal foundation model for digital garments. In: Proceedings of the Computer Vision and Pattern Recognition Conference. pp. 8138–8149 (2025) Stitched Embeddings 19

    2025

  48. [48]

    In: SIGGRAPH Conference Papers ’26 (2026)

    Nakayama, K., Shen, I.C., Liu, R., Wang, Y., Wetzstein, G., Igarashi, T.: Garment particles: A 2d–3d symmetric garment representation for generation and editing. In: SIGGRAPH Conference Papers ’26 (2026)

    2026

  49. [49]

    Graph.41(4), 157–1 (2022)

    Pietroni, N., Dumery, C., Falque, R., Liu, M., Vidal-Calleja, T.A., Sorkine- Hornung,O.:Computationalpatternmakingfrom3dgarmentmodels.ACMTrans. Graph.41(4), 157–1 (2022)

    2022

  50. [50]

    ACM Transactions on Graphics (ToG)36(4), 1–15 (2017)

    Pons-Moll, G., Pujades, S., Hu, S., Black, M.J.: Clothcap: Seamless 4d clothing capture and retargeting. ACM Transactions on Graphics (ToG)36(4), 1–15 (2017)

    2017

  51. [51]

    In: 2025 International Conference on 3D Vision (3DV)

    Rong, B., Grigorev, A., Wang, W., Black, M.J., Thomaszewski, B., Tsalicoglou, C., Hilliges, O.: Gaussian garments: Reconstructing simulation-ready clothing with photorealistic appearance from multi-view video. In: 2025 International Conference on 3D Vision (3DV). pp. 1054–1063. IEEE (2025)

    2025

  52. [52]

    In: European Conference on Computer Vision

    Shen, Y., Liang, J., Lin, M.C.: Gan-based garment generation using sewing pat- tern images. In: European Conference on Computer Vision. pp. 225–247. Springer (2020)

    2020

  53. [53]

    In: ACM SIGGRAPH 2025 Conference Proceedings (2025)

    Tatsukawa, Y., Qi, A., Shen, I.C., Igarashi, T.: Garmentimage: Raster encoding of garment sewing patterns with diverse topologies. In: ACM SIGGRAPH 2025 Conference Proceedings (2025)

    2025

  54. [54]

    Team, T.H.: Hunyuan3d 2.1: From images to high-fidelity 3d assets with production-ready pbr material (2025)

    2025

  55. [55]

    In: European Con- ference on Computer Vision

    Tiwari, G., Bhatnagar, B.L., Tung, T., Pons-Moll, G.: Sizer: A dataset and model for parsing 3d clothing and learning size sensitive 3d clothing. In: European Con- ference on Computer Vision. pp. 1–18. Springer (2020)

    2020

  56. [56]

    In: Proceedings of the IEEE/CVF International Conference on Computer Vision

    Tiwari, G., Sarafianos, N., Tung, T., Pons-Moll, G.: Neural-gif: Neural general- ized implicit functions for animating people in clothing. In: Proceedings of the IEEE/CVF International Conference on Computer Vision. pp. 11708–11718 (2021)

    2021

  57. [57]

    In: British Machine Vision Conference (BMVC) (2025)

    Vuran, O., Ho, H.I.: Remu: Reconstructing multi-layer 3d clothed human from images. In: British Machine Vision Conference (BMVC) (2025)

    2025

  58. [58]

    In: Proceedings of the Computer Vision and Pattern Recognition Conference

    Wang, J., Chen, M., Karaev, N., Vedaldi, A., Rupprecht, C., Novotny, D.: Vggt: Visual geometry grounded transformer. In: Proceedings of the Computer Vision and Pattern Recognition Conference. pp. 5294–5306 (2025)

    2025

  59. [59]

    IEEE Transactions on Image Processing (2025)

    Wang, K., Wang, C., Yang, J., Zhang, G.: Clocap-gs: clothed human performance capture with 3d gaussian splatting. IEEE Transactions on Image Processing (2025)

    2025

  60. [60]

    Learning a Shared Shape Space for Multimodal Garment Design

    Wang, T.Y., Ceylan, D., Popovic, J., Mitra, N.J.: Learning a shared shape space for multimodal garment design. arXiv preprint arXiv:1806.11335 (2018)

    work page internal anchor Pith review Pith/arXiv arXiv 2018

  61. [61]

    In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition

    Wang, W., Ho, H.I., Guo, C., Rong, B., Grigorev, A., Song, J., Zarate, J.J., Hilliges, O.: 4d-dress: A 4d dataset of real-world human clothing with semantic annotations. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 550–560 (2024)

    2024

  62. [62]

    arXiv preprint arXiv:2503.08678 (2025)

    Wang, Y., Zhang, C., Frazão, G., Yang, J., Ichim, A.E., Beeler, T., De la Torre, F.: Garmentcrafter: Progressive novel view synthesis for single-view 3d garment reconstruction and editing. arXiv preprint arXiv:2503.08678 (2025)

    work page arXiv 2025

  63. [63]

    In: Proceedings of the IEEE/CVF International Conference on Computer Vision

    Wen, M., Wu, S., Wang, K., Liang, D.: Intergsedit: Interactive 3d gaussian splat- ting editing with 3d geometry-consistent attention prior. In: Proceedings of the IEEE/CVF International Conference on Computer Vision. pp. 26136–26145 (2025)

    2025

  64. [64]

    In: European Conference on Computer Vision

    Wolf, Y., Bracha, A., Kimmel, R.: Gs2mesh: Surface reconstruction from gaussian splatting via novel stereo views. In: European Conference on Computer Vision. pp. 207–224. Springer (2024)

    2024

  65. [65]

    Wolff, K., Herholz, P., Sorkine-Hornung, O.: Reflection symmetry in textured sewing patterns. In: VMV. pp. 11–18 (2019) 20 A. Sanchietti et al

    2019

  66. [66]

    In: Computer Graphics Fo- rum

    Wolff, K., Herholz, P., Ziegler, V., Link, F., Brügel, N., Sorkine-Hornung, O.: De- signing personalized garments with body movement. In: Computer Graphics Fo- rum. vol. 42, pp. 180–194. Wiley Online Library (2023)

    2023

  67. [67]

    In: European Conference on Computer Vision

    Wu, Q., Zheng, J., Cai, J.: Surface reconstruction from 3d gaussian splatting via local structural hints. In: European Conference on Computer Vision. pp. 441–458. Springer (2024)

    2024

  68. [68]

    In: 2020 International Con- ference on 3D Vision (3DV)

    Xiang, D., Prada, F., Wu, C., Hodgins, J.: Monoclothcap: Towards temporally coherent clothing capture from monocular rgb video. In: 2020 International Con- ference on 3D Vision (3DV). pp. 322–332. IEEE (2020)

    2020

  69. [69]

    In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition

    Xiang, J., Lv, Z., Xu, S., Deng, Y., Wang, R., Zhang, B., Chen, D., Tong, X., Yang, J.: Structured 3d latents for scalable and versatile 3d generation. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. pp. 21469–21480 (2025)

    2025

  70. [70]

    Xue, Y., Xie, X., Marin, R., Pons-Moll, G.: Human-3diffusion: realistic avatar creationviaexplicit3dconsistentdiffusionmodels.AdvancesinNeuralInformation Processing Systems37, 99601–99645 (2024)

    2024

  71. [71]

    IEEE Transactions on Pattern Analysis and Machine Intelligence (2025)

    Xue, Y., Xie, X., Marin, R., Pons-Moll, G.: Gen-3diffusion: Realistic image-to-3d generation via 2d & 3d diffusion synergy. IEEE Transactions on Pattern Analysis and Machine Intelligence (2025)

    2025

  72. [72]

    Arxiv (2024)

    Xueting, L., Yuan, Y., De Mello, S., Daviet, G., Leaf, J., Macklin, M., Kautz, J., Iqbal, U.: Simavatar: Simulation-ready avatars with layered hair and clothing. Arxiv (2024)

    2024

  73. [73]

    Yang, S., Ambert, T., Pan, Z., Wang, K., Yu, L., Berg, T., Lin, M.C.: Detailed garmentrecoveryfromasingle-viewimage.arXivpreprintarXiv:1608.01250(2016)

    work page internal anchor Pith review Pith/arXiv arXiv 2016

  74. [74]

    Computer Graphics Forum (2024)

    Yu, B., Cordier, F., Seo, H.: Inverse garment and pattern modeling with a differ- entiable simulator. Computer Graphics Forum (2024)

    2024

  75. [75]

    arXiv preprint arXiv:2311.17050 (2023)

    Yu, Z., Dou, Z., Long, X., Lin, C., Li, Z., Liu, Y., Müller, N., Komura, T., Haber- mann, M., Theobalt, C., et al.: Surf-d: High-quality surface generation for arbitrary topologies using diffusion models. arXiv preprint arXiv:2311.17050 (2023)

    work page arXiv 2023

  76. [76]

    In: Proceedings of the IEEE conference on computer vision and pattern recognition

    Zhang, C., Pujades, S., Black, M.J., Pons-Moll, G.: Detailed, accurate, human shape estimation from clothed 3d scan sequences. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 4191–4200 (2017)

    2017

  77. [77]

    IEEE transactions on pattern analysis and machine intelligence46(8), 5625–5644 (2024)

    Zhang, J., Huang, J., Jin, S., Lu, S.: Vision-language models for vision tasks: A survey. IEEE transactions on pattern analysis and machine intelligence46(8), 5625–5644 (2024)

    2024

  78. [78]

    In: Proceedings of the IEEE/CVF International Conference on Computer Vision

    Zhang, X., Liu, Z., Zhang, Y., Ge, X., He, D., Xu, T., Wang, Y., Lin, Z., Yan, S., Zhang, J.: Mega: Memory-efficient 4d gaussian splatting for dynamic scenes. In: Proceedings of the IEEE/CVF International Conference on Computer Vision. pp. 27828–27838 (2025)

    2025

  79. [79]

    In: Pro- ceedings of the Computer Vision and Pattern Recognition Conference

    Zhou, F., Liu, R., Liu, C., He, G., Li, Y.L., Jin, X., Wang, H.: Design2garmentcode: Turning design concepts to tangible garments through program synthesis. In: Pro- ceedings of the Computer Vision and Pattern Recognition Conference. pp. 23712– 23722 (2025)

    2025

  80. [80]

    In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition

    Zou, X., Han, X., Wong, W.: Cloth4d: A dataset for clothed human reconstruction. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 12847–12857 (2023)

    2023