Pith. sign in

REVIEW 5 major objections 5 minor 46 references

A single pipeline turns a sketch and a fabric texture into a simulation-ready 3D garment, fusing both elements in a shared latent space.

Reviewed by Pith at T0; open to challenge. T0 means a machine referee read the full paper against a public rubric. the ladder, T0–T4 →

Challenge this review Re-run · record.json Download PDF Read on arXiv ↗

T0 review · deepseek-v4-flash

2026-08-01 03:20 UTC pith:CNTDSK62

load-bearing objection The task formulation is genuinely new, but the SOTA claim collapses on the copied baseline numbers; the paper should be revised before it can be judged. the 5 major comments →

arxiv 2607.23189 v1 pith:CNTDSK62 submitted 2026-07-25 cs.CV cs.AI

Fashion-3DLR: A Controllable 3D Garment Generation Using Pairwise Fashion Elements for Intelligent Design

Shenghao Yang , Hongtao Zhang , Yuhan Yi , Zhihao Tang , Zihao Cui , Lian Wen , Han Yan , Yuan Gao
show 1 more author
Mingbo Zhao
This is my paper
classification cs.CV cs.AI
keywords intelligent fashion design3D generative modelimage-to-image translationfashion synthesis3D garment generationdiffusion transformer3D Gaussian splattingcloth simulation
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved

The pith

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

This paper sets out to show that 3D garment generation can be controlled by the same two design elements a fashion designer actually uses—a structural sketch and an appearance reference such as a fabric texture or brush painting. It introduces Fashion-3DLR, an end-to-end model that bridges the semantic gap between these heterogeneous 2D inputs, fuses them into a shared latent space, and decodes the result into both 3D Gaussians and meshes that preserve the sketch's silhouette and the texture's material look. If the premise holds, designers could generate, refine, and physically simulate garment concepts without manual topology modeling or sewing-pattern reconstruction, and the same asset could serve virtual try-on. The paper reports that its outputs are non-watertight and wearable, support material-specific dynamics for cotton, silk, wool, and nylon, and outperform the comparison methods on the metrics they define.

Core claim

The central claim is that pairing a sketch and a texture (or oil-brush painting) is a sufficient condition set for generating a complete, wear-ready 3D garment in two exchangeable output formats. To achieve this, the authors propose a Garment Feature Fusion Diffusion Transformer (GFF-DiT) that bidirectionally modulates the two inputs—each modality is normalized and rescaled by affine factors predicted from the other—so that neither element dominates and the structural and appearance semantics are preserved together. The fused condition is then fed, through cross-attention, into a rectified flow transformer that denoises a noisy latent into a garment latent, which is upsampled into voxelized

What carries the argument

The load-bearing mechanism is the Garment Feature Fusion Diffusion Transformer (GFF-DiT), a diffusion transformer that fuses two heterogeneous design elements into one conditional latent via symmetric bidirectional modulation: sketch features are normalized and then rescaled by scale-and-shift factors predicted from texture features, and vice versa, so either modality can steer the fusion while both are preserved. The fused condition is injected as keys and values into a rectified flow transformer, where the noisy garment latent serves as the query; after denoising, convolutional up-sampling converts the latent into 3D Gaussian splats or a mesh. The physical-simulation extension rests on a p

Load-bearing premise

The entire controllability claim rests on the assumption that automatically generated stand-ins for design elements—edge maps for sketches, automated stylizations for brush strokes, and random cropped patches for fabric texture—faithfully capture how a human designer would draw, paint, and specify fabric.

What would settle it

Take a set of hand-drawn fashion sketches and scanned fabric swatches from a public garment dataset, run Fashion-3DLR on those without any automatic-proxy preprocessing, and compare the output silhouettes and texture fidelity to outputs from the edge-map/random-patch pairs; if the alignment metrics degrade to the level of an un-conditioned baseline, the data-equivalence assumption that underwrites the controllability claim is false.

Watch this falsifier — get emailed when new claim-graph text bears on it.

If this is right

  • A sketch and a fabric texture (or brush painting) become sufficient control signals to generate a complete 3D garment that preserves the sketch's silhouette and the texture's appearance.
  • The generated 3D Gaussian garment can be simulated directly, without an intermediate mesh, and the motion parameters can be tuned per fabric (cotton, silk, wool, nylon) while keeping fine geometric details such as thin straps.
  • The same latent representation can be decoded into a mesh for virtual try-on, and the mesh inherits the input sketch's flat hems, sleeve lengths, and openings rather than collapsing into a watertight shell.
  • The reported ablation shows the fusion module is the source of the method's controllability: removing GFF-DiT degrades all evaluated quality and alignment metrics.

Where Pith is reading between the lines

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

  • A fair test of the controllability claim would be to run the trained model on hand-drawn designer sketches and real fabric photographs, since the paper's training and evaluation pairs are built from automatic proxies (edge maps, stylization filters, and random patches); if performance drops sharply on authentic inputs, the practical gains may be smaller than the reported metrics suggest.
  • The same bidirectional-fusion architecture is not inherently garment-specific; it could plausibly be retrained for other pairwise heterogeneous conditions, such as a blueprint plus a material palette for furniture, or character line-art plus a color palette, and would likely face the same semantic-gap problem.
  • Because the fusion is symmetric and operates before geometry generation, the framework offers a natural way to disentangle structure from appearance—fixing the texture and varying the sketch (or vice versa) explores shape or material variations independently, which the paper demonstrates qualitatively but does not formalize as an editing API.
  • The paper itself closes by naming two boundaries: the Gaussian garment does not yet interact with mesh-based human bodies, and the mesh garment does not encode sewing-pattern structure; those are the places where the demonstrated gains stop and where the garment would need to be re-integrated into a full production pipeline.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit.

Referee Report

5 major / 5 minor

Summary. The paper proposes Fashion-3DLR, a controllable 3D garment generation framework that takes paired design elements (e.g., sketch and texture/brush) as input, fuses them via a Garment Feature Fusion Diffusion Transformer (GFF-DiT), generates garment latents with a rectified flow transformer, and decodes them into 3D Gaussian Splatting (3DGS) and mesh representations. The framework also supports physics-based 3DGS cloth simulation and mesh-based virtual try-on. The central claims are that Fashion-3DLR surpasses prior state-of-the-art in generation quality and controllability, and that it is the first end-to-end pipeline to produce simulation-ready garments from paired design elements.

Significance. If the results were valid, this would be a useful contribution to intelligent fashion design, enabling designers to control 3D garment geometry and appearance from 2D sketch and texture inputs. The GFF-DiT fusion mechanism is a sensible extension of prior pairwise fusion work, and the integration with 3DGS physics simulation is relevant. However, the current evidence is not sufficient to support the claims. The duplicated baseline numbers in Tables 1 and 2 invalidate the quantitative SOTA comparison, and the proposed validation of fabric dynamics is self-referential. The paper's strengths are the conceptual pipeline and qualitative results, but these alone do not meet the standard for acceptance.

major comments (5)
  1. [Sec. 4.3, Table 2] Table 2 reuses the baseline entries from Table 1 verbatim: DressCode (FIDCLIP=0.4524, LPIPS=0.6803) copies Tripo's row, and ChatGarment (0.4648, 0.7001) copies Hunyuan3D's row. These are different methods evaluated on a different task (sewing-pattern draping vs. sketch+texture 3D generation). Exact equality to four decimals cannot be coincidental. As a result, the conclusion in Sec. 4.3 that 'Fashion-3DLR consistently surpasses all baseline methods' lacks valid quantitative support.
  2. [Sec. 4.1, Metric definitions] The FIDCLIP metric is defined as 'a higher score indicates better alignment', yet Tables 1–3 label it with a downward arrow, indicating lower is better. This contradiction makes the reported improvements ambiguous; if the definition is correct, the table entries may actually indicate worse performance. Please clarify the metric direction and, if necessary, rerun the evaluation.
  3. [Sec. 4.1, Data construction] The controllability and diversity claims are based entirely on automatically derived proxies for design elements: HED edge maps for sketches, neural-painting stylization for brush, random 32×32 patches for textures, and GPT-4o captions. No evidence is given that these proxies match how designers specify elements. If the proxies differ from real inputs, the reported test-set metrics (computed on the same proxy-derived pairs) would overestimate real-world controllability. The paper should include at least a small user study or evaluation with genuine designer-provided inputs.
  4. [Sec. 3.4, Physical parameter identification] The fabric-specific parameters θ = {k_b, k_s, k_sh, ρ} are optimized to match a commercial cloth simulator's output (Eq. 7). This validates the 'fabric-specific dynamics' claim only against the simulator used to generate the reference, not against physical measurements. The claim of 'realistic, fabric-specific dynamics' (Sec. 1) is therefore not supported by the presented evidence; the authors should temper the claim or validate against real fabric video.
  5. [General experimental rigor] None of the quantitative tables include error bars, number of seeds, or significance tests, and the user study (Sec. 4.4) reports only aggregate percentages without statistical detail. The paper also states no code/data/checkpoints will be released. This lack of experimental rigor, especially together with the duplicated baseline numbers, makes it impossible to verify the reported results or assess the significance of the improvements.
minor comments (5)
  1. [Eq. (1) and surrounding text] The operators ⊕ and ⊗ are reversed relative to standard convention: the text says '⊕ denotes multiplication and ⊗ indicates element-wise addition', which makes the modulation equation difficult to parse. Please fix.
  2. [Eq. (6)] Eq. (6) appears malformed: 'A_p(t)=F_p(t), A_p, F_p(t)⊤' is unclear and should be rewritten with proper notation for the deformation gradient and covariance update.
  3. [Table 1 and References] Table 1 cites [4] for Hunyuan3D-3.0, but reference [4] is the HunyuanImage 3.0 technical report (a 2D image model). Please verify the correct baseline and citation.
  4. [Abstract and Sec. 1] The claim of being 'the first end-to-end pipeline' is too strong given the lack of comparison to recent garment-specific 3D generation methods (e.g., GarmentDreamer, Garment3DGen) and the limited evaluation. Suggest softening this claim.
  5. [Throughout] Placeholder conference information ('Woodstock, NY', 'June 03–05, 2018', 'Conference acronym XX') should be updated or removed. Also, minor typos: 'We introduce' should be lowercase in the Abstract; 'surpass' should be 'surpasses'.

Circularity Check

1 steps flagged

Core generation pipeline is not circular, but the quantitative SOTA comparison relabels Table 1 baseline numbers as different methods in Table 2.

specific steps
  1. renaming known result [Table 2 vs Table 1 (Sec. 4.3 'Virtual Try-on' / Sec. 4.2 'Quantitative Comparison')]
    "Table 2: 'DressCode [11][SIGGRAPH2024] 0.4524 0.6803 0.8311' and 'ChatGarment [2][CVPR2025] 0.4648 0.7001 0.7946'. Table 1: 'Tripo [37][2024] 0.4524 0.6803 0.7961' and 'Hunyuan3D-3.0 [4][2025] 0.4648 0.7001 0.7946'."

    The Table 2 baseline rows are numerically identical to Table 1 rows for different methods evaluated on a different task. DressCode is assigned the exact FIDCLIP/LPIPS/CLIP-I values reported for Tripo, and ChatGarment the exact values reported for Hunyuan3D. The conclusion in Sec. 4.3 that 'Fashion-3DLR consistently surpasses all baseline methods' is therefore not supported by independent measurements of those baselines on the draped sewing-pattern task; the comparison is a relabeling of the paper's own earlier numbers. This is a renamed/imported result rather than a derived prediction, so the central quantitative SOTA claim is circular in the sense that its evidence is the paper's own Table 1 recycled under new names.

full rationale

The generation pipeline itself is largely self-contained: GFF-DiT is specified by Eqs. (1)-(3), the rectified-flow objective by Eq. (5), and the losses are standard denoising/CFM objectives. The citation to FashionDiff [42] (co-authored by a current author) is contextual and not load-bearing because the fusion equations are given in the paper. The fabric parameter fitting in Sec. 3.4 is explicitly an identification procedure matched to simulator-generated reference videos, not a prediction, so it is not circular. The main circularity concern is the quantitative SOTA comparison: Table 2 reuses Table 1 values under different method names, so the numerical superiority claim for the draped-garment task is not independently measured. A separate correctness issue, not circularity, is that FIDCLIP is described as 'higher score indicates better alignment' while the tables use a downward arrow. Overall, the core architectural derivation is independent, but the central quantitative evidence for 'surpassing SOTA' relies on relabeled numbers, warranting a partial circularity score of 4.

Axiom & Free-Parameter Ledger

1 free parameters · 6 axioms · 0 invented entities

The central claim rests on automatically generated paired design elements, voxelized feature aggregation from pretrained encoders, and fitted MPM fabric parameters; none of these is independently validated in the paper.

free parameters (1)
  • Fabric parameter vector θ = {k_b, k_s, k_sh, ρ} = Not reported numerically
    Eq. 7 optimizes θ per fabric type by matching MPM-driven 3DGS motion to reference videos from a commercial simulator; values are never given, so the material-specific simulation claim cannot be independently checked.
axioms (6)
  • domain assumption HED edge maps are treated as designer sketches.
    Sec. 4.1 builds sketch supervision by applying Holistically-Nested Edge Detection to garment images; if real sketches differ systematically from HED edges, the control signal in training is not the control signal in deployment.
  • domain assumption Neural-painting stylizations and random 32×32 foreground patches represent brush areas and fabric textures.
    Sec. 4.1 uses these automatic proxies to create paired element data; their equivalence to real brush/texture inputs is asserted, not validated.
  • domain assumption Averaging DINOv2 features projected from multi-view renders onto voxels preserves enough geometry and appearance for decoding.
    Sec. 3.2 adopts the Trellis-style feature aggregation; the paper provides no ablation or independent check of this representation for garments.
  • domain assumption Commercial cloth simulator output is valid ground truth for fabric dynamics, and MPM parameters fitted to it transfer to real cloth.
    Sec. 3.4 fits θ against a commercial cloth simulator [3]; no comparison to real fabric measurements is provided.
  • standard math Rectified-flow linear interpolation (CFM objective) is well-posed for the structured garment latents used here.
    Eq. 5 is the standard conditional flow matching objective; its applicability to this particular voxel-latent space is assumed without analysis.
  • domain assumption SewFactory 3D assets plus GPT-4o captions and Polyvore images form sufficient supervision for controllable garment generation.
    Sec. 4.1 describes the combined training set; no human verification of GPT-4o captions or garment-quality filtering is reported.

pith-pipeline@v1.3.0-alltime-deepseek · 12852 in / 15656 out tokens · 136975 ms · 2026-08-01T03:20:39.186875+00:00 · methodology

0 comments
read the original abstract

AI-generated content (AIGC) has made significant progress, with 2D generative models becoming ready-to-use tools for the digital fashion industry. However, 3D garment generation remains in its nascent stage, where in the realm of fashion, the semantic information of diverse design elements exhibits intricate coupling relationships in 3D representations, posing substantial challenges for generating diverse 3D garments. In this work, to handle the above problem, We introduce Fashion-3DLR, a novel 3D garment generation framework that utilizes diverse design elements to create high-quality, versatile 3D garment assets. Specifically, to bridge the semantic gaps between different fashion elements, we propose a Garment Feature Fusion Diffusion Transformer (GFF-DiT) module to integrate 2D fashion design elements, e.g., sketch and texture, into latent space. Within the latent space, we then employ a rectified flow transformer to generate geometry latents, which can be decoded into various 3D garment representations, including 3D Gaussians and meshes. Furthermore, we integrate Fashion-3DLR into downstream tasks, achieving the 3D Gaussian Splatting (3DGS)-driven cloth physical simulation and mesh-based virtual try-on. Experimental results indicate that Fashion-3DLR surpass the previous state-of-the-art methods, which verify that the proposed work can generate well-structured, non-watertight garments capable of physical simulation and virtual try-on, underscoring its potential as a versatile 3D garment design tool.

Figures

Figures reproduced from arXiv: 2607.23189 by Han Yan, Hongtao Zhang, Lian Wen, Mingbo Zhao, Shenghao Yang, Yuan Gao, Yuhan Yi, Zhihao Tang, Zihao Cui.

Figure 1
Figure 1. Figure 1: Given paired design elements, e.g., sketch and texture, Fashion [PITH_FULL_IMAGE:figures/full_fig_p003_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Overall pipeline for Fashion-3DLR. Our approach processes paired design element images by fusing their features [PITH_FULL_IMAGE:figures/full_fig_p003_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Details of the proposed GFF process. approaches, our method eliminates the need for intermediate mesh representations and operates directly on 3D Gaussian primitives. This design preserves the rich visual fidelity of 3D Gaussians as￾sets while enabling realistic cloth dynamics, thereby expanding the applicability of 3D Gaussians for garment modeling and simulation. 3 Methods Overview. The Fashion-3DLR fram… view at source ↗
Figure 4
Figure 4. Figure 4: Qualitative results using sketch images with texture images, and sketch images with oil brush images. [PITH_FULL_IMAGE:figures/full_fig_p006_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Qualitative comparisons with baselines for 3D garment generation with fusion of sketch, texture and oil brush. [PITH_FULL_IMAGE:figures/full_fig_p007_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: 360° demonstration of qualitative results using sketch images with oil brush images. suffers from unstable reconstruction with frequent topology col￾lapse. Although it partially inherits texture colors, most generated surfaces become desaturated or entirely white, with substantial loss of fine-scale detail. In contrast, Fashion-3DLR consistently recon￾structs sketch-aligned, non-watertight garments while p… view at source ↗
Figure 7
Figure 7. Figure 7: Physical simulation demonstration of generated [PITH_FULL_IMAGE:figures/full_fig_p008_7.png] view at source ↗
Figure 8
Figure 8. Figure 8: Qualitative comparison of existing SOTA clothing [PITH_FULL_IMAGE:figures/full_fig_p008_8.png] view at source ↗

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

46 extracted references · 13 linked inside Pith

  1. [1]

    Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Floren- cia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al. 2023. Gpt-4 technical report.arXiv preprint arXiv:2303.08774 (2023)

    Pith/arXiv arXiv 2023

  2. [2]

    Siyuan Bian, Chenghao Xu, Yuliang Xiu, Artur Grigorev, Zhen Liu, Cewu Lu, Michael J Black, and Yao Feng. 2025. Chatgarment: Garment estimation, gen- eration and editing via large language models. InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2924–2934

    2025

  3. [3]

    Katherine L Bouman, Bei Xiao, Peter Battaglia, and William T Freeman. 2013. Estimating the material properties of fabric from video. InProceedings of the IEEE international conference on computer vision. 1984–1991

    2013

  4. [4]

    Siyu Cao, Hangting Chen, Peng Chen, Yiji Cheng, Yutao Cui, Xinchi Deng, Ying Dong, Kipper Gong, Tianpeng Gu, Xiusen Gu, et al. 2025. HunyuanImage 3.0 Technical Report.arXiv preprint arXiv:2509.23951(2025)

    Pith/arXiv arXiv 2025

  5. [5]

    Jiahao Chang, Chongjie Ye, Yushuang Wu, Yuantao Chen, Yidan Zhang, Zhongjin Luo, Chenghong Li, Yihao Zhi, and Xiaoguang Han. 2025. ReconViaGen: Towards Accurate Multi-view 3D Object Reconstruction via Generation.arXiv preprint arXiv:2510.23306(2025)

    arXiv 2025

  6. [6]

    Yabo Chen, Jiemin Fang, Yuyang Huang, Taoran Yi, Xiaopeng Zhang, Lingxi Xie, Xinggang Wang, Wenrui Dai, Hongkai Xiong, and Qi Tian. 2024. Cascade- zero123: One image to highly consistent 3d with self-prompted nearby views. In European Conference on Computer Vision. Springer, 311–330

    2024

  7. [7]

    Yen-Chi Cheng, Hsin-Ying Lee, Sergey Tulyakov, Alexander G Schwing, and Liang-Yan Gui. 2023. Sdfusion: Multimodal 3d shape completion, reconstruction, and generation. InProceedings of the IEEE/CVF conference on computer vision and pattern recognition. 4456–4465

    2023

  8. [8]

    Antonia Creswell, Tom White, Vincent Dumoulin, Kai Arulkumaran, Biswa Sen- gupta, and Anil A Bharath. 2018. Generative adversarial networks: An overview. IEEE signal processing magazine35, 1 (2018), 53–65

    2018

  9. [9]

    Yi Rui Cui, Qi Liu, Cheng Ying Gao, and Zhongbo Su. 2018. FashionGAN: Display your fashion design using conditional generative adversarial nets. InComputer Graphics Forum, Vol. 37. Wiley Online Library, 109–119

    2018

  10. [10]

    Haoye Dong, Xiaodan Liang, Yixuan Zhang, Xujie Zhang, Xiaohui Shen, Zhenyu Xie, Bowen Wu, and Jian Yin. 2020. Fashion editing with adversarial parsing learning. InProceedings of the IEEE/CVF conference on computer vision and pattern recognition. 8120–8128

    2020

  11. [11]

    Kai He, Kaixin Yao, Qixuan Zhang, Jingyi Yu, Lingjie Liu, and Lan Xu. 2024. Dresscode: Autoregressively sewing and generating garments from text guidance. ACM Transactions on Graphics (TOG)43, 4 (2024), 1–13

    2024

  12. [12]

    Yuanming Hu, Yu Fang, Ziheng Ge, Ziyin Qu, Yixin Zhu, Andre Pradhana, and Chenfanfu Jiang. 2018. A moving least squares material point method with displacement discontinuity and two-way rigid body coupling.ACM Transactions on Graphics (TOG)37, 4 (2018), 1–14

    2018

  13. [13]

    Chenfanfu Jiang, Craig Schroeder, Andrew Selle, Joseph Teran, and Alexey Stom- akhin. 2015. The affine particle-in-cell method.ACM Transactions on Graphics (TOG)34, 4 (2015), 1–10

    2015

  14. [14]

    Shuhui Jiang, Jun Li, and Yun Fu. 2021. Deep learning for fashion style generation. IEEE Transactions on Neural Networks and Learning Systems33, 9 (2021), 4538– 4550

    2021

  15. [15]

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

  16. [16]

    Gergely Klár, Theodore Gast, Andre Pradhana, Chuyuan Fu, Craig Schroeder, Chenfanfu Jiang, and Joseph Teran. 2016. Drucker-prager elastoplasticity for sand animation.ACM Transactions on Graphics (TOG)35, 4 (2016), 1–12

    2016

  17. [17]

    Maria Korosteleva and Sung-Hee Lee. 2022. Neuraltailor: Reconstructing sewing pattern structures from 3d point clouds of garments.ACM Transactions on Graphics (TOG)41, 4 (2022), 1–16

    2022

  18. [18]

    Boqian Li, Xuan Li, Ying Jiang, Tianyi Xie, Feng Gao, Huamin Wang, Yin Yang, and Chenfanfu Jiang. 2025. GarmentDreamer: 3DGS Guided Garment Synthesis with Diverse Geometry and Texture Details. InInternational Conference on 3D Vision

    2025

  19. [19]

    Weiyu Li, Jiarui Liu, Hongyu Yan, Rui Chen, Yixun Liang, Xuelin Chen, Ping Tan, and Xiaoxiao Long. 2024. Craftsman3d: High-fidelity mesh generation with 3d na- tive generation and interactive geometry refiner.arXiv preprint arXiv:2405.14979 (2024)

    Pith/arXiv arXiv 2024

  20. [20]

    Zhihao Li, Yufei Wang, Heliang Zheng, Yihao Luo, and Bihan Wen. [n. d.]. Sparc3D: Sparse Representation and Construction for High-Resolution 3D Shapes Modeling. InThe Thirty-ninth Annual Conference on Neural Information Processing Systems

  21. [21]

    Lijuan Liu, Xiangyu Xu, Zhijie Lin, Jiabin Liang, and Shuicheng Yan. 2023. To- wards garment sewing pattern reconstruction from a single image.ACM Trans- actions on Graphics (TOG)42, 6 (2023), 1–15

    2023

  22. [22]

    Minghua Liu, Ruoxi Shi, Linghao Chen, Zhuoyang Zhang, Chao Xu, Xinyue Wei, Hansheng Chen, Chong Zeng, Jiayuan Gu, and Hao Su. 2024. One-2-3-45++: Fast single image to 3d objects with consistent multi-view generation and 3d diffusion. InProceedings of the IEEE/CVF conference on computer vision and pattern recognition. 10072–10083

    2024

  23. [23]

    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– 9309

    2023

  24. [24]

    Yuan Liu, Cheng Lin, Zijiao Zeng, Xiaoxiao Long, Lingjie Liu, Taku Komura, and Wenping Wang. 2023. Syncdreamer: Generating multiview-consistent images from a single-view image.arXiv preprint arXiv:2309.03453(2023)

    Pith/arXiv arXiv 2023

  25. [25]

    Xiaoxiao Long, Yuan-Chen Guo, Cheng Lin, Yuan Liu, Zhiyang Dou, Lingjie Liu, Yuexin Ma, Song-Hai Zhang, Marc Habermann, Christian Theobalt, et al. 2024. Wonder3d: Single image to 3d using cross-domain diffusion. InProceedings of the IEEE/CVF conference on computer vision and pattern recognition. 9970–9980

    2024

  26. [26]

    Alex Nichol, Prafulla Dhariwal, Aditya Ramesh, Pranav Shyam, Pamela Mishkin, Bob McGrew, Ilya Sutskever, and Mark Chen. 2021. Glide: Towards photorealistic image generation and editing with text-guided diffusion models.arXiv preprint arXiv:2112.10741(2021)

    Pith/arXiv arXiv 2021

  27. [27]

    Maxime Oquab, Timothée Darcet, Théo Moutakanni, Huy Vo, Marc Szafraniec, Vasil Khalidov, Pierre Fernandez, Daniel Haziza, Francisco Massa, Alaaeldin El- Nouby, et al. 2023. Dinov2: Learning robust visual features without supervision. arXiv preprint arXiv:2304.07193(2023)

    Pith/arXiv arXiv 2023

  28. [28]

    William Peebles and Saining Xie. 2023. Scalable diffusion models with transform- ers. InProceedings of the IEEE/CVF international conference on computer vision. 4195–4205

    2023

  29. [29]

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

    Pith/arXiv arXiv 2022

  30. [30]

    Robin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser, and Björn Ommer. 2022. High-resolution image synthesis with latent diffusion models. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 10684–10695

    2022

  31. [31]

    Boxiang Rong, Artur Grigorev, Wenbo Wang, Michael J Black, Bernhard Thomaszewski, Christina Tsalicoglou, and Otmar Hilliges. 2024. Gaussian gar- ments: Reconstructing simulation-ready clothing with photorealistic appearance from multi-view video.arXiv preprint arXiv:2409.08189(2024)

    Pith/arXiv arXiv 2024

  32. [32]

    Nikolaos Sarafianos, Tuur Stuyck, Xiaoyu Xiang, Yilei Li, Jovan Popovic, and Rakesh Ranjan. 2024. Garment3dgen: 3d garment stylization and texture genera- tion.arXiv preprint arXiv:2403.18816(2024)

    Pith/arXiv arXiv 2024

  33. [33]

    Ruoxi Shi, Hansheng Chen, Zhuoyang Zhang, Minghua Liu, Chao Xu, Xinyue Wei, Linghao Chen, Chong Zeng, and Hao Su. 2023. Zero123++: a single image to consistent multi-view diffusion base model.arXiv preprint arXiv:2310.15110 (2023)

    Pith/arXiv arXiv 2023

  34. [34]

    Ivan Skorokhodov, Sergey Tulyakov, Yiqun Wang, and Peter Wonka. 2022. Epigraf: Rethinking training of 3d gans.Advances in Neural Information Processing Systems Conference acronym ’XX, June 03–05, 2018, Woodstock, NY Shenghao Yang, Hongtao Zhang, Yuhan Yi, Zhihao Tang, Zihao Cui, Lian Wen, Han Yan, Yuan Gao, and Mingbo Zhao 35 (2022), 24487–24501

    2022

  35. [35]

    Alexey Stomakhin, Craig Schroeder, Lawrence Chai, Joseph Teran, and Andrew Selle. 2013. A material point method for snow simulation.ACM Transactions on Graphics (TOG)32, 4 (2013), 1–10

    2013

  36. [36]

    Jiaxiang Tang, Jiawei Ren, Hang Zhou, Ziwei Liu, and Gang Zeng. 2023. Dream- gaussian: Generative gaussian splatting for efficient 3d content creation.arXiv preprint arXiv:2309.16653(2023)

    Pith/arXiv arXiv 2023

  37. [37]

    Dmitry Tochilkin, David Pankratz, Zexiang Liu, Zixuan Huang, , Adam Letts, Yangguang Li, Ding Liang, Christian Laforte, Varun Jampani, and Yan-Pei Cao

  38. [38]

    Peng Wang, Lingjie Liu, Yuan Liu, Christian Theobalt, Taku Komura, and Wenping Wang. 2021. Neus: Learning neural implicit surfaces by volume rendering for multi-view reconstruction.arXiv preprint arXiv:2106.10689(2021)

    Pith/arXiv arXiv 2021

  39. [39]

    Jianfeng Xiang, Zelong Lv, Sicheng Xu, Yu Deng, Ruicheng Wang, Bowen Zhang, Dong Chen, Xin Tong, and Jiaolong Yang. 2025. Structured 3d latents for scalable and versatile 3d generation. InProceedings of the Computer Vision and Pattern Recognition Conference. 21469–21480

    2025

  40. [40]

    Saining Xie and Zhuowen Tu. 2015. Holistically-nested edge detection. InPro- ceedings of the IEEE international conference on computer vision. 1395–1403

    2015

  41. [41]

    Tianyi Xie, Zeshun Zong, Yuxing Qiu, Xuan Li, Yutao Feng, Yin Yang, and Chen- fanfu Jiang. 2024. Physgaussian: Physics-integrated 3d gaussians for generative dynamics. InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 4389–4398

    2024

  42. [42]

    Han Yan, Haijun Zhang, Xiangyu Mu, Jicong Fan, and Zhao Zhang. 2023. Fashion- diff: a controllable diffusion model using pairwise fashion elements for intelligent design. InProceedings of the 31st ACM International Conference on Multimedia. 1401–1411

    2023

  43. [43]

    Lvmin Zhang, Anyi Rao, and Maneesh Agrawala. 2023. Adding conditional con- trol to text-to-image diffusion models. InProceedings of the IEEE/CVF international conference on computer vision. 3836–3847

    2023

  44. [44]

    Shizhan Zhu, Raquel Urtasun, Sanja Fidler, Dahua Lin, and Chen Change Loy. 2017. Be your own prada: Fashion synthesis with structural coherence. InProceedings of the IEEE international conference on computer vision. 1680–1688

    2017

  45. [2023]

    Graph.42, 4 (2023), 139–1

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

    2023

  46. [2024]

    TripoSR: Fast 3D Object Reconstruction from a Single Image.arXiv preprint arXiv:2403.02151(2024)

    Pith/arXiv arXiv 2024