pith. sign in

arxiv: 2601.17740 · v2 · submitted 2026-01-25 · 💻 cs.CV · cs.GR

Learning Sewing Patterns via Latent Flow Matching of Implicit Fields

Cong Cao , Ren Li , Corentin Dumery , Hao Li This is my paper

Pith reviewed 2026-05-16 10:58 UTC · model grok-4.3

classification 💻 cs.CV cs.GR
keywords sewing patternsimplicit fieldsflow matchinggarment modelinglatent spacepattern generationdigital fashiondistance fields
0
0 comments X

The pith

Sewing patterns are modeled by encoding each panel's boundary as a signed distance field and its seam endpoints as an unsigned distance field inside a continuous latent space learned by flow matching.

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

The work shows that garment panels can be represented implicitly by a signed distance field capturing the outer boundary and an unsigned distance field marking seam locations. These fields are mapped into a shared latent space that supports differentiable conversion back to meshes. A flow-matching model then learns the joint distribution over valid panel sets in that space, while a stitching module predicts which edge segments connect. The resulting formulation handles wide variation in panel shapes and seam layouts, supporting direct generation, image-based estimation, partial-pattern completion, and body refitting with measurable gains over prior discrete or template-based methods.

Core claim

Encoding panel boundaries and seam endpoints as signed and unsigned distance fields into a continuous latent space enables differentiable meshing, and a latent flow matching model over panel combinations together with a stitching prediction module recovers seam relations, allowing accurate modeling and generation of sewing patterns with complex structures as well as improved image-based estimation, pattern completion, and refitting.

What carries the argument

Implicit representation of each panel by a signed distance field for its boundary and an unsigned distance field for seam endpoints, jointly encoded in a latent space and modeled by latent flow matching plus a stitching prediction module.

If this is right

  • Sewing patterns with complex structures can be modeled and generated accurately.
  • Estimation of sewing patterns from images achieves improved accuracy over existing approaches.
  • Pattern completion becomes feasible by filling missing panels in the latent space.
  • Refitting of patterns to new body shapes or garment styles is supported.

Where Pith is reading between the lines

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

  • The latent representation could support direct optimization of patterns against 3D scan data without an explicit 2D projection step.
  • Coupling the flow-matching generator with a physics simulator might allow end-to-end learning of patterns that satisfy both geometric and drape constraints.
  • The same distance-field encoding may transfer to other 2D-to-3D fabrication tasks such as sheet-metal unfolding or flat-pack furniture assembly.

Load-bearing premise

Encoding panel boundaries and seam endpoints as distance fields into a continuous latent space will enable both accurate differentiable meshing and reliable recovery of seam relations from extracted edge segments across diverse garment structures.

What would settle it

A dataset of sewing patterns containing intricate multi-panel intersections where decoded edge segments produce seam connections that mismatch the ground-truth topology after latent decoding and meshing.

Figures

Figures reproduced from arXiv: 2601.17740 by Cong Cao, Corentin Dumery, Hao Li, Ren Li.

Figure 1
Figure 1. Figure 1: We model and generate sewing patterns using (1) an implicit garment repre￾sentation, where panels are encoded as continuous distance fields and assembled into garments. Based on this representation, we enable (2.a) sewing pattern estimation from a single image, (2.b) pattern completion from partial panel inputs, and (2.c) pattern refitting for transferring garments across different body shapes. Abstract. S… view at source ↗
Figure 2
Figure 2. Figure 2: Overview of the sewing pattern modeling pipeline. [PITH_FULL_IMAGE:figures/full_fig_p005_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Inferring edge endpoints. Left: We evaluate the UDF values dp on a dense grid (black dots) and retain only points near the zero roots (dark red regions inside dashed circles). Middle: These points are it￾eratively updated using Eq. 7 to move them toward the zero roots; black dots indicate the updated positions. Right: Cluster cen￾ters ci obtained from the converged points are used as edge endpoints, which … view at source ↗
Figure 4
Figure 4. Figure 4: Qualitative comparison on the SewFactory dataset. Qualitative Results [PITH_FULL_IMAGE:figures/full_fig_p012_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Qualitative comparison on the GCD dataset. 4.2 Pattern Refitting Since our method is based on an implicit panel representation that supports differentiable mesh extraction as shown in Eq. 8, we demonstrate that it can be used as a prior to refit sewing patterns for transferring generated garments across different body shapes and sizes. Given a source garment Ms fitted to a source body Bs together with its … view at source ↗
Figure 6
Figure 6. Figure 6: Pattern refitting across different body shapes. [PITH_FULL_IMAGE:figures/full_fig_p013_6.png] view at source ↗
Figure 7
Figure 7. Figure 7: Pattern completion. Top: Given partial panel inputs, our method completes the missing panels to form a full sewing pattern. Bottom: The model also recovers panel layout and stitching relationships, allowing the completed patterns to be assembled and draped in simulation to produce 3D garments. 4.3 Pattern Completion Given partial panel specifications provided by users, such as a set of m panels represented… view at source ↗
read the original abstract

Sewing patterns define the structural foundation of garments and are essential for applications such as fashion design, fabrication, and physical simulation. Despite progress in automated pattern generation, accurately modeling sewing patterns remains difficult due to the broad variability in panel geometry and seam arrangements. In this work, we introduce a sewing pattern modeling method based on an implicit representation. We represent each panel using a signed distance field that defines its boundary and an unsigned distance field that identifies seam endpoints, and encode these fields into a continuous latent space that enables differentiable meshing. A latent flow matching model learns distributions over panel combinations in this representation, and a stitching prediction module recovers seam relations from extracted edge segments. This formulation allows accurate modeling and generation of sewing patterns with complex structures. We further show that it can be used to estimate sewing patterns from images with improved accuracy relative to existing approaches, and supports applications such as pattern completion and refitting, providing a practical tool for digital fashion design.

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 paper introduces an implicit representation for sewing patterns where each panel is encoded via a signed distance field (SDF) defining its boundary and an unsigned distance field (UDF) identifying seam endpoints. These fields are mapped into a continuous latent space that supports differentiable meshing. A latent flow matching model learns distributions over panel combinations, while a dedicated stitching prediction module recovers seam relations from extracted edge segments. The method is applied to generative modeling of complex garments, pattern completion, refitting, and image-based estimation, with claims of improved accuracy over prior approaches.

Significance. If the central claims hold, the work would offer a practical advance in digital fashion by replacing discrete panel representations with a continuous latent model that enables generative sampling, differentiable operations, and applications such as image-to-pattern recovery. The combination of implicit fields and flow matching could improve handling of variable seam topologies compared with existing mesh- or graph-based methods.

major comments (2)
  1. [§4.3 (Stitching Prediction Module)] The stitching prediction module is load-bearing for the claim of accurate modeling of complex structures. The UDF encodes only endpoint locations without explicit connectivity or seam-type information; for garments containing darts, yokes, intersecting seams, or closed loops, multiple valid assignments can produce identical distance fields. The manuscript must demonstrate that the learned module reliably disambiguates these cases, for example via targeted ablations or failure-mode analysis on ambiguous configurations (see §4.3 and associated experiments).
  2. [§5 (Experimental Results)] The abstract asserts 'improved accuracy relative to existing approaches' for image-based estimation and 'accurate modeling' of complex structures, yet the provided description supplies no quantitative metrics, error tables, ablation studies, or dataset specifications. To substantiate the central claims, the experimental section must report concrete numbers (e.g., seam-error, topology-validity rates) against baselines on a clearly described sewing-pattern corpus.
minor comments (2)
  1. [§3.2] Clarify the precise formulation of the latent encoding that combines SDF and UDF channels; the current description leaves open whether the fields are concatenated, jointly encoded, or processed separately before flow matching.
  2. [Figures 4–6] Figure captions and legends should explicitly label the extracted edge segments, predicted seams, and final meshed panels so that readers can directly verify the stitching module output.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for their thorough review and valuable suggestions. We have addressed the major comments by providing additional analyses and quantitative results in the revised manuscript.

read point-by-point responses

  1. Referee: [§4.3 (Stitching Prediction Module)] The stitching prediction module is load-bearing for the claim of accurate modeling of complex structures. The UDF encodes only endpoint locations without explicit connectivity or seam-type information; for garments containing darts, yokes, intersecting seams, or closed loops, multiple valid assignments can produce identical distance fields. The manuscript must demonstrate that the learned module reliably disambiguates these cases, for example via targeted ablations or failure-mode analysis on ambiguous configurations (see §4.3 and associated experiments).

    Authors: We acknowledge the referee's concern regarding the stitching prediction module's performance on ambiguous cases. To address this, we have revised the manuscript by adding targeted ablations and failure-mode analyses in §4.3 for configurations involving darts, yokes, intersecting seams, and closed loops. These new experiments illustrate that the module reliably disambiguates such cases, supporting our claims of accurate modeling of complex structures. revision: yes

  2. Referee: [§5 (Experimental Results)] The abstract asserts 'improved accuracy relative to existing approaches' for image-based estimation and 'accurate modeling' of complex structures, yet the provided description supplies no quantitative metrics, error tables, ablation studies, or dataset specifications. To substantiate the central claims, the experimental section must report concrete numbers (e.g., seam-error, topology-validity rates) against baselines on a clearly described sewing-pattern corpus.

    Authors: We thank the referee for this observation. To substantiate the claims, we have revised §5 to report concrete quantitative metrics, including seam-error and topology-validity rates, along with ablation studies and a clear description of the sewing-pattern corpus used. Error tables comparing against baselines are now included, demonstrating the improved accuracy for image-based estimation and complex structure modeling. revision: yes

Circularity Check

0 steps flagged

No circularity: derivation is self-contained learning pipeline

full rationale

The paper defines an implicit representation (SDF for panel boundaries + UDF for seam endpoints) encoded to latent space, then applies latent flow matching to learn distributions over combinations and a separate stitching module to recover relations from edge segments. No step reduces by construction to its own inputs, fitted parameters renamed as predictions, or load-bearing self-citations; the central claims rest on standard generative modeling trained on data rather than tautological definitions or imported uniqueness theorems.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

The central claim rests on the unstated assumption that distance fields can be stably encoded and that flow matching will capture the joint distribution of panel combinations; no explicit free parameters, axioms, or invented entities are detailed in the abstract.

pith-pipeline@v0.9.0 · 5462 in / 1088 out tokens · 25209 ms · 2026-05-16T10:58:51.891678+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

59 extracted references · 59 canonical work pages

  1. [1]

    CLO3D (2023),https://www.clo3d.com/en/3

    work page 2023

  2. [2]

    In: Computer Graphics Forum

    Bang, S., Korosteleva, M., Lee, S.: Estimating garment patterns from static scan data. In: Computer Graphics Forum. vol. 40, pp. 273–287 (2021) 4

    work page 2021

  3. [3]

    In: International Conference on Computer Vision (2019) 3

    Bhatnagar, B.L., Tiwari, G., Theobalt, C., Pons-Moll, G.: Multi-Garment Net: Learning to Dress 3D People from Images. In: International Conference on Computer Vision (2019) 3

    work page 2019

  4. [4]

    In: Conference on Computer Vision and Pattern Recognition

    Bian, S., Xu, C., Xiu, Y., Grigorev, A., Liu, Z., Lu, C., Black, M., Feng, Y.: Chatgarment: Garment estimation, generation and editing via large language models. In: Conference on Computer Vision and Pattern Recognition. pp. 2924–2934 (2025) 4

    work page 2025

  5. [5]

    In: Computer Graphics Forum

    Casado-Elvira, A., Trinidad, M., Casas, D.: PERGAMO: Personalized 3d Garments from Monocular Video. In: Computer Graphics Forum. vol. 41, pp. 293–304 (2022) 3

    work page 2022

  6. [6]

    Proceedings of the ACM on Computer Graphics and Interactive Techniques8(4), 1–17 (2025) 12

    Chen, H., Larionov, E., Kavan, L., Lin, G., Roble, D., Sorkine-Hornung, O., Stuyck, T.: Dress anyone: Automatic physically-based garment pattern refitting. Proceedings of the ACM on Computer Graphics and Interactive Techniques8(4), 1–17 (2025) 12

    work page 2025

  7. [7]

    In: Advances in Neural Information Processing Systems (2022) 4

    Chen, X., Wang, G., Zhu, D., Liang, X., Torr, P., Lin, L.: Structure-Preserving 3D Garment Modeling with Neural Sewing Machines. In: Advances in Neural Information Processing Systems (2022) 4

    work page 2022

  8. [8]

    ACM Transactions on Graphics34(6), 1–12 (2015) 4

    Chen, X., Zhou, B., Lu, F., Wang, L., Bi, L., Tan, P.: Garment modeling with a depth camera. ACM Transactions on Graphics34(6), 1–12 (2015) 4

    work page 2015

  9. [9]

    In: Conference on Computer Vision and Pattern Recognition (2021) 3

    Corona, E., Pumarola, A., Alenya, G., Pons-Moll, G., Moreno-Noguer, F.: Smplicit: Topology-Aware Generative Model for Clothed People. In: Conference on Computer Vision and Pattern Recognition (2021) 3

    work page 2021

  10. [10]

    Eurographics (2017) 3

    Danerek, R., Dibra, E., öztireli, C., Ziegler, R., Gross, M.: Deepgarment : 3D Garment Shape Estimation from a Single Image. Eurographics (2017) 3

    work page 2017

  11. [11]

    In: Conference on Computer Vision and Pattern Recognition (2023) 3

    DeLuigi, L., Li, R., Guillard, B., Salzmann, M., Fua, P.: Drapenet: Generating Garments and Draping Them with Self-Supervision. In: Conference on Computer Vision and Pattern Recognition (2023) 3

    work page 2023

  12. [12]

    In: Conference on Knowledge Discovery and Data Mining (1996) 7

    Ester,M.,Kriegel,H.,Sander,J.,Xu,X.:ADensity-BasedAlgorithmforDiscovering Clusters in Large Spatial Databases with Noise. In: Conference on Knowledge Discovery and Data Mining (1996) 7

    work page 1996

  13. [13]

    In: Special Interest Group on Computer Graphics and Interactive Techniques Conference Talks

    de Goes, F., Fong, D., O’Malley, M.: Garment refitting for digital characters. In: Special Interest Group on Computer Graphics and Interactive Techniques Conference Talks. pp. 1–2 (2020) 12 16 C. Cao et al

    work page 2020

  14. [14]

    In: Eurographics (Short Papers)

    Goto, C., Umetani, N.: Data-driven Garment Pattern Estimation from 3D Geome- tries. In: Eurographics (Short Papers). pp. 17–20 (2021) 4

    work page 2021

  15. [15]

    In: ACM SIGGRAPH

    Grigorev, A., Becherini, G., Black, M., Hilliges, O., Thomaszewski, B.: ContourCraft: Learning to resolve intersections in neural multi-garment simulations. In: ACM SIGGRAPH. pp. 1–10 (2024) 13

    work page 2024

  16. [16]

    ACM SIGGRAPH31(4), 351–3510 (July 2012) 3

    Guan, P., Reiss, L., Hirshberg., D., Weiss, A., Black, M.J.: DRAPE: Dressing Any Person. ACM SIGGRAPH31(4), 351–3510 (July 2012) 3

    work page 2012

  17. [17]

    IEEE Transactions on Pattern Analysis and Machine Intelligence (2024) 8

    Guillard, B., Remelli, E., Lukoianov, A., Richter, S., Bagautdinov, T., Baque, P., Fua, P.: DeepMesh: Differentiable Iso-Surface Extraction. IEEE Transactions on Pattern Analysis and Machine Intelligence (2024) 8

    work page 2024

  18. [18]

    In: European Conference on Computer Vision (2022) 3

    Guillard, B., Stella, F., Fua, P.: MeshUDF: Fast and Differentiable Meshing of Unsigned Distance Field Networks. In: European Conference on Computer Vision (2022) 3

    work page 2022

  19. [19]

    In: Interna- tional Conference on Computer Vision/Computer Graphics Collaboration Tech- niques and Applications

    Hasler, N., Rosenhahn, B., Seidel, H.: Reverse engineering garments. In: Interna- tional Conference on Computer Vision/Computer Graphics Collaboration Tech- niques and Applications. pp. 200–211 (2007) 4

    work page 2007

  20. [20]

    ACM Transactions on Graphics 43(4), 1–13 (2024) 2, 4, 5

    He, K., Yao, K., Zhang, Q., Yu, J., Liu, L., Xu, L.: Dresscode: Autoregressively sewing and generating garments from text guidance. ACM Transactions on Graphics 43(4), 1–13 (2024) 2, 4, 5

    work page 2024

  21. [21]

    Computer Animation and Virtual Worlds26(3-4), 291–300 (2015) 4

    Jeong, M., Han, D., Ko, H.: Garment capture from a photograph. Computer Animation and Virtual Worlds26(3-4), 291–300 (2015) 4

    work page 2015

  22. [22]

    In: European Conference on Computer Vision (2020) 3

    Jiang, B., Zhang, J., Hong, Y., Luo, J., Liu, L., Bao, H.: Bcnet: Learning Body and Cloth Shape from a Single Image. In: European Conference on Computer Vision (2020) 3

    work page 2020

  23. [23]

    In: European Conference on Computer Vision

    Korosteleva, M., Kesdogan, T., 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: European Conference on Computer Vision. pp. 110–127 (2024) 9

    work page 2024

  24. [24]

    In: Advances in Neural Information Processing Systems (2021) 4, 8

    Korosteleva, M., Lee, S.: Generating Datasets of 3D Garments with Sewing Patterns. In: Advances in Neural Information Processing Systems (2021) 4, 8

    work page 2021

  25. [25]

    ACM Transactions on Graphics41(4), 1–16 (2022) 2, 4, 10

    Korosteleva, M., Lee, S.: Neuraltailor: Reconstructing sewing pattern structures from 3d point clouds of garments. ACM Transactions on Graphics41(4), 1–16 (2022) 2, 4, 10

    work page 2022

  26. [26]

    ACM Transactions on Graphics42(6), 1–15 (2023) 4, 8, 9

    Korosteleva, M., Sorkine-Hornung, O.: Garmentcode: Programming parametric sewing patterns. ACM Transactions on Graphics42(6), 1–15 (2023) 4, 8, 9

    work page 2023

  27. [27]

    In: ACM SIGGRAPH

    Li, R., Cao, C., Dumery, C., You, Y., Li, H., Fua, P.: Single View Garment Recon- struction Using Diffusion Mapping Via Pattern Coordinates. In: ACM SIGGRAPH. pp. 1–11 (2025) 4

    work page 2025

  28. [28]

    In: Advances in Neural Information Processing Systems (2024) 4

    Li, R., Dumery, C., Dang, Z., Fua, P.: Reconstruction of Manipulated Garment with Guided Deformation Prior. In: Advances in Neural Information Processing Systems (2024) 4

    work page 2024

  29. [29]

    In: Conference on Computer Vision and Pattern Recognition (2024) 4

    Li, R., Dumery, C., Guillard, B., Fua, P.: Garment Recovery with Shape and Deformation Priors. In: Conference on Computer Vision and Pattern Recognition (2024) 4

    work page 2024

  30. [30]

    In: Advances in Neural Information Processing Systems (2023) 2, 4, 7

    Li, R., Guillard, B., Fua, P.: ISP: Multi-Layered Garment Draping with Implicit Sewing Patterns. In: Advances in Neural Information Processing Systems (2023) 2, 4, 7

    work page 2023

  31. [31]

    In: Asian Conference on Computer Vision (2022) 3 Learning Sewing Patterns via Latent Flow Matching of Implicit Fields 17

    Li, R., Guillard, B., Remelli, E., Fua, P.: DIG: Draping Implicit Garment over the Human Body. In: Asian Conference on Computer Vision (2022) 3 Learning Sewing Patterns via Latent Flow Matching of Implicit Fields 17

    work page 2022

  32. [32]

    ACM Transactions on Graphics44(6), 1–23 (2025) 4

    Li, S., Liu, R., Liu, C., Wang, Z., He, G., Li, Y., Jin, X., Wang, H.: GarmageNet: A Multimodal Generative Framework for Sewing Pattern Design and Generic Garment Modeling. ACM Transactions on Graphics44(6), 1–23 (2025) 4

    work page 2025

  33. [33]

    International Joint Conference on Artificial Intelligence (2025) 4

    Li, X., Yao, Q., Wang, Y.: GarmentDiffusion: 3D Garment Sewing Pattern Genera- tion with Multimodal Diffusion Transformers. International Joint Conference on Artificial Intelligence (2025) 4

    work page 2025

  34. [34]

    In: International Conference on Learning Representations (2023) 8

    Lipman, Y., Chen, R., Ben-Hamu, H., Nickel, M., Le, M.: Flow Matching for Generative Modeling. In: International Conference on Learning Representations (2023) 8

    work page 2023

  35. [35]

    In: Advances in Neural Information Processing Systems

    Liu, H., Li, C., Wu, Q., Lee, Y.: Visual instruction tuning. In: Advances in Neural Information Processing Systems. vol. 36, pp. 34892–34916 (2023) 5

    work page 2023

  36. [36]

    International Journal of Industrial Ergonomics 72, 212–221 (2019) 4

    Liu, K., Zhu, C., Tao, X., Bruniaux, P., Zeng, X.: Parametric design of garment pattern based on body dimensions. International Journal of Industrial Ergonomics 72, 212–221 (2019) 4

    work page 2019

  37. [37]

    ACM Transactions on Graphics42(6), 1–15 (2023) 5, 9, 10

    Liu, L., Xu, X., Lin, Z., Liang, J., Yan, S.: Towards garment sewing pattern reconstruction from a single image. ACM Transactions on Graphics42(6), 1–15 (2023) 5, 9, 10

    work page 2023

  38. [38]

    IEEE Transactions on Visualization and Computer Graphics (2023) 3

    Liu, X., Li, J., Lu, G.: Modeling Realistic Clothing from a Single Image Under Normal Guide. IEEE Transactions on Visualization and Computer Graphics (2023) 3

    work page 2023

  39. [39]

    ACM SIGGRAPH Asia34(6) (2015) 9

    Loper, M., Mahmood, N., Romero, J., Pons-Moll, G., Black, M.: SMPL: A Skinned Multi-Person Linear Model. ACM SIGGRAPH Asia34(6) (2015) 9

    work page 2015

  40. [40]

    In: ACM SIGGRAPH

    Lorensen, W., Cline, H.: Marching Cubes: A High Resolution 3D Surface Construc- tion Algorithm. In: ACM SIGGRAPH. pp. 163–169 (1987) 3

    work page 1987

  41. [41]

    In: Advances in Neural Information Processing Systems

    Lu, J., Sun, Y., Huang, Q.: Jigsaw: Learning to assemble multiple fractured objects. In: Advances in Neural Information Processing Systems. vol. 36, pp. 14969–14986 (2023) 9

    work page 2023

  42. [42]

    In: European Conference on Computer Vision (2022) 3

    Moon, G., Nam, H., Shiratori, T., Lee, K.: 3D Clothed Human Reconstruction in the Wild. In: European Conference on Computer Vision (2022) 3

    work page 2022

  43. [43]

    In: Conference on Computer Vision and Pattern Recognition

    Nakayama, K., Ackermann, J., Kesdogan, T., Zheng, Y., Korosteleva, M., Sorkine- Hornung, O., Guibas, L., Yang, G., Wetzstein, G.: AIpparel: A Multimodal Founda- tion Model for Digital Garments. In: Conference on Computer Vision and Pattern Recognition. pp. 8138–8149 (2025) 2, 4, 5, 10

    work page 2025

  44. [44]

    In: Conference on Computer Vision and Pattern Recognition (2020) 3

    Patel, C., Liao, Z., Pons-Moll, G.: Tailornet: Predicting Clothing in 3D as a Function of Human Pose, Shape and Garment Style. In: Conference on Computer Vision and Pattern Recognition (2020) 3

    work page 2020

  45. [45]

    In: International Conference on Computer Vision (2025) 14

    Patel, M., Wen, S., Metaxas, D., Yang, Y.: Steering Rectified Flow Models in the Vector Field for Controlled Image Generation. In: International Conference on Computer Vision (2025) 14

    work page 2025

  46. [46]

    In: International Conference on Computer Vision

    Peebles, W., Xie, S.: Scalable diffusion models with transformers. In: International Conference on Computer Vision. pp. 4195–4205 (2023) 8

    work page 2023

  47. [47]

    ACM Transactions on Graphics41(4), 1–14 (2022) 4

    Pietroni, N., Dumery, C., Falque, R., Liu, M., Vidal-Calleja, T., Sorkine-Hornung, O.: Computational Pattern Making from 3D Garment Models. ACM Transactions on Graphics41(4), 1–14 (2022) 4

    work page 2022

  48. [48]

    In: International Conference on Machine Learning

    Radford, A., Kim, J., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning. PMLR (2021) 10

    work page 2021

  49. [49]

    In: Advances in Neural Information Processing Systems (2020) 8 18 C

    Remelli, E., Lukoianov, A., Richter, S., Guillard, B., Bagautdinov, T., Baque, P., Fua, P.: Meshsdf: Differentiable Iso-Surface Extraction. In: Advances in Neural Information Processing Systems (2020) 8 18 C. Cao et al

    work page 2020

  50. [50]

    ACM Transactions on Graphics 37(4), 1–13 (2018) 4

    Sharp, N., Crane, K.: Variational surface cutting. ACM Transactions on Graphics 37(4), 1–13 (2018) 4

    work page 2018

  51. [51]

    arXiv Preprint (2025) 10

    Siméoni, O., Vo, H., Seitzer, M., Baldassarre, F., Oquab, M., Jose, C., Khalidov, V., Szafraniec, M., Yi, S., Ramamonjisoa, M., et al.: Dinov3. arXiv Preprint (2025) 10

    work page 2025

  52. [52]

    Style3D: Style3D (2025),https://www.style3d.com/3

    work page 2025

  53. [53]

    In: ACM SIGGRAPH

    Tatsukawa, Y., Qi, A., Shen, I., Igarashi, T.: GarmentImage: Raster Encoding of Garment Sewing Patterns with Diverse Topologies. In: ACM SIGGRAPH. pp. 1–11 (2025) 4

    work page 2025

  54. [54]

    ACM Transactions on Graphics37(6), 1–13 (2018) 2, 4, 5

    Wang, T., Ceylan, D., Popović, J., J, N.M.: Learning a shared shape space for multimodal garment design. ACM Transactions on Graphics37(6), 1–13 (2018) 2, 4, 5

    work page 2018

  55. [55]

    In: Advances in Neural Information Processing Systems

    Wu, S., Lin, Y., Zhang, F., Zeng, Y., Xu, J., Torr, P., Cao, X., Yao, Y.: Direct3d: Scalable image-to-3d generation via 3d latent diffusion transformer. In: Advances in Neural Information Processing Systems. vol. 37, pp. 121859–121881 (2024) 10

    work page 2024

  56. [56]

    ACM Transactions on Graphics 37(5), 1–14 (2018) 2, 4, 5

    Yang, S., Pan, Z., Amert, T., Wang, K., Yu, L., Berg, T., Lin, M.: Physics-Inspired Garment Recovery from a Single-View Image. ACM Transactions on Graphics 37(5), 1–14 (2018) 2, 4, 5

    work page 2018

  57. [57]

    In: International Conference on Computer Vision

    Zhao, H., Jiang, L., Jia, J., Torr, P., Koltun, V.: Point transformer. In: International Conference on Computer Vision. pp. 16259–16268 (2021) 6

    work page 2021

  58. [58]

    Zhou, F., Liu, R., Liu, C., He, G., Li, Y., Jin, X., Wang, H.: In: Conference on Computer Vision and Pattern Recognition. pp. 23712–23722 (2025) 4

    work page 2025

  59. [59]

    In: Conference on Computer Vision and Pattern Recognition

    Zhu, H., Qiu, L., Qiu, Y., Han, X.: Registering Explicit to Implicit: Towards High- Fidelity Garment Mesh Reconstruction from Single Images. In: Conference on Computer Vision and Pattern Recognition. pp. 3845–3854 (2022) 3

    work page 2022