Pith. sign in

REVIEW 2 major objections 1 minor 111 references

Singular fiber twists on group-algebra CSS codes can raise the number of logical qubits at fixed blocklength, while invertible twists leave the binary code unchanged.

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 · grok-4.5

2026-07-13 14:22 UTC pith:MDG34OIT

load-bearing objection Abstract-only quantum coding claim; the supplied full text is UniRecGen, so the twisted-fiber results cannot be verified. the 2 major comments →

arxiv 2604.01478 v2 pith:MDG34OIT submitted 2026-04-01 quant-ph

Twisted Fiber Bundle Codes over Group Algebras

Chaobin Liu This is my paper
classification quant-ph MSC 81P7094B05
keywords quantum CSS codeslifted product codesgroup algebrasfiber twistsquantum LDPCchain complexesencoded dimensionflatness condition
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.

Lifted-product quantum CSS codes over a group algebra are a standard way to build structured quantum error-correcting codes from a base complex and a fiber. This paper attaches an R-linear twist to each base generator, subject to a flatness condition so the total object remains a valid chain complex. When those twists are invertible, the twisted complex is chain-isomorphic to the ordinary lifted product, so the resulting binary CSS code has the same length n and encoded dimension k. When the twists are singular but still chain-compatible, the ranks of the boundary maps can fall, which increases k at the same n. Small examples over the group algebra of the dihedral group of order six show that k can rise while the minimum distance stays the same. That is offered as evidence that singular twisting enlarges the design space beyond ordinary lifted products.

Core claim

A twisted fiber-bundle construction of quantum CSS codes over R = F_2[G] recovers the untwisted lifted product when all twists are identities; invertible flat twists give a chain-isomorphic complex and thus the same binary parameters n and k; singular chain-compatible twists can lower boundary ranks and strictly increase the number of logical qubits, and in the reported finite examples over F_2[D_3] the minimum distance is unchanged.

What carries the argument

Twisted fiber bundle over a group algebra: each base generator carries a generator-dependent R-linear fiber twist obeying a flatness condition (and, for non-invertible twists, a chain-compatibility condition) so that the total complex still defines a CSS code.

Load-bearing premise

That singular twists meeting the flatness and chain-compatibility conditions exist for a wide enough family of base complexes and groups that the observed gain in logical dimension is not an artifact of the small dihedral examples, and that distance stays competitive as blocklength grows.

What would settle it

Find a family of singular chain-compatible twists on larger base complexes or larger groups where either k never increases relative to the untwisted lifted product, or the minimum distance drops below the untwisted code at the same blocklength.

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

If this is right

  • Invertible twists do not create new binary parameters; only singular chain-compatible twists can improve the rate k/n of a given lifted product.
  • Code designers gain an extra continuous family of CSS parameters controlled by choosing singular endomorphisms of the fiber module.
  • If the D_3 examples generalize, boundary rank can be traded for logical dimension without an immediate distance penalty.
  • The same base complex and group algebra can yield more distinct CSS codes than the ordinary lifted-product construction alone.

Where Pith is reading between the lines

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

  • A general formula relating the drop in boundary rank to the kernels of the singular twists would turn the finite examples into a systematic design recipe rather than case-by-case evidence.
  • The same twisting idea may extend to other product constructions of quantum LDPC codes once an analogous flatness condition is written down.
  • If distance is preserved under singular twisting in asymptotic families, one could raise the rate of known good quantum LDPC codes without inventing new base complexes.

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

2 major / 1 minor

Summary. The manuscript claims a twisted fiber bundle construction of quantum CSS codes over group algebras R=F_2[G], in which each base generator is equipped with a generator-dependent R-linear fiber twist subject to a flatness condition. Invertible twists satisfying flatness are asserted to yield a chain complex isomorphic to the ordinary (untwisted) lifted product, hence the same binary blocklength n and dimension k. Singular but chain-compatible twists are claimed to lower boundary ranks and thereby increase k at fixed n; finite examples over R=F_2[D_3] are said to realize this increase while leaving the minimum distance d unchanged, suggesting that singular twisting enlarges the design space beyond ordinary lifted products.

Significance. If the algebraic statements and the D_3 examples hold, the work would enlarge the constructive toolkit for quantum CSS codes over group algebras by showing that non-invertible twists can raise the number of logical qubits without lengthening the code. That would be a useful, if incremental, extension of the lifted-product literature. The abstract alone, however, supplies no theorems, no explicit complexes, and no distance proofs, so the significance remains conditional on material that is not present in the supplied manuscript body.

major comments (2)
  1. The body of the supplied manuscript is the unrelated UniRecGen paper (multi-view 3D reconstruction/generation, arXiv:2604.01479). None of the claimed objects—generator-dependent R-linear fiber twists, the flatness/chain-compatibility conditions, the chain-isomorphism argument for invertible twists, boundary-rank calculations, or the F_2[D_3] examples—appear. The central claims of the abstract therefore cannot be verified from the document under review.
  2. Because the algebraic development and the finite examples that are supposed to demonstrate an increase in k at fixed n with d unchanged are absent, there is no load-bearing derivation or numerical evidence that can be checked. The paper as submitted does not establish its principal result.
minor comments (1)
  1. The abstract is well-written and self-contained, but it cannot substitute for the missing technical sections.

Circularity Check

0 steps flagged

No circularity: full text is a mismatched CV paper (UniRecGen); abstract of claimed codes paper is a non-circular algebraic construction with no fitted predictions or self-referential reductions.

full rationale

The CACHEABLE full manuscript is UniRecGen (arXiv:2604.01479, multi-view 3D recon/generation), not Twisted Fiber Bundle Codes (arXiv:2604.01478). No definitions, flatness conditions, boundary-rank arguments, chain-isomorphisms, or F_2[D_3] examples appear, so no derivation chain can be walked or reduced. From the supplied abstract alone the claims are definitional (twists extend lifted products; invertible flat twists yield chain-isomorphic complexes with identical n,k; singular chain-compatible twists can raise k at fixed n in finite examples while d is unchanged). There are no fitted parameters renamed as predictions, no self-citation uniqueness theorems, and no ansatz smuggled via prior author work that forces the result. This is ordinary constructive coding theory; circularity is absent. Score 0 with empty steps is the honest outcome forced by source mismatch plus abstract content.

Axiom & Free-Parameter Ledger

0 free parameters · 4 axioms · 1 invented entities

Abstract-only ledger. The construction rests on standard CSS / chain-complex algebra over group rings, plus paper-specific flatness and chain-compatibility conditions for the twists. No free numerical parameters are mentioned. The main invented objects are the generator-dependent fiber twists themselves.

axioms (4)
  • domain assumption CSS codes arise from chain complexes (or pairs of matrices with AB^T=0) over F_2, with n, k, d determined by ranks and minimum weights of homology.
    Standard quantum coding background assumed throughout the abstract.
  • domain assumption Lifted-product / fiber-bundle constructions over group algebras R=F_2[G] produce valid CSS codes when the base complex is a chain complex over R.
    The untwisted case is treated as known prior art recovered when all twists are identities.
  • ad hoc to paper A flatness condition on generator-dependent R-linear fiber twists ensures the twisted object remains a chain complex.
    Paper-specific compatibility condition required for the twisted construction to be well-defined; details not in the abstract.
  • ad hoc to paper Invertible twists satisfying flatness induce a chain isomorphism to the untwisted complex, preserving binary n and k.
    Central structural claim of the abstract; proof not available in abstract-only review.
invented entities (1)
  • Generator-dependent R-linear fiber twist (twisted fiber bundle code) no independent evidence
    purpose: Deform the ordinary lifted product so that singular twists can change boundary ranks and encoded dimension.
    The twist maps are the new algebraic data; invertible case is isomorphic to prior work, singular case is the claimed novelty.

pith-pipeline@v1.1.0-grok45 · 24336 in / 2668 out tokens · 26256 ms · 2026-07-13T14:22:18.441830+00:00 · methodology

0 comments
read the original abstract

We introduce a twisted fiber bundle construction of quantum CSS codes over group algebras \(R=\mathbb F_2[G]\), where each base generator carries a generator-dependent \(R\)-linear fiber twist satisfying a flatness condition. This construction extends the untwisted lifted product code, recovered when all twists are identities. We show that invertible twists (satisfying a flatness condition) give a complex chain-isomorphic to the untwisted one, so the resulting binary CSS codes have the same blocklength \(n\) and encoded dimension \(k\). In contrast, singular chain-compatible twists can lower boundary ranks and increase the number of logical qubits. Examples over \(R=\mathbb F_2[D_3]\) show that singular chain-compatible twists can increase the encoded dimension \(k\) at fixed blocklength \(n\), and in these finite examples the minimum distance \(d\) remains unchanged. This provides evidence that singular twisting enlarges the design space beyond the ordinary lifted product construction.

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

111 extracted references · 18 linked inside Pith

  1. [1]

    Eric R Chan, Connor Z Lin, Matthew A Chan, Koki Nagano, Boxiao Pan, Shalini De Mello, Orazio Gallo, Leonidas Guibas, Jonathan Tremblay, Sameh Khamis, et al. 2022. Efficient geometry-aware 3D generative adversarial networks. In �������� ������������� ���������� �� �������� ������

    2022

  2. [2]

    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.����� �������� ����������������(2025)

    2025

  3. [3]

    David Charatan, Sizhe Lester Li, Andrea Tagliasacchi, and Vincent Sitzmann

  4. [4]

    In�������� ���������� �� �������� ������ ��� ������� �����������

    pixelSplat: 3d gaussian splats from image pairs for scalable generaliz- able 3d reconstruction. In�������� ���������� �� �������� ������ ��� ������� �����������. 19457–19467

  5. [5]

    Hansheng Chen, Jiatao Gu, Anpei Chen, Wei Tian, Zhuowen Tu, Lingjie Liu, and Hao Su. 2023. Single-stage diffusion nerf: A unified approach to 3d generation and reconstruction. In����������� �� ��� �������� ������������� ���������� �� �������� ������. 2416–2425

    2023

  6. [6]

    Sijin Chen, Xin Chen, Anqi Pang, Xianfang Zeng, Wei Cheng, Yijun Fu, Fukun Yin, Billzb Wang, Jingyi Yu, Gang Yu, et al. 2024. Meshxl: Neural coordinate field for generative 3d foundation models.�������� �� ������ ����������� ���������� ������� ���������(2024)

    2024

  7. [7]

    Xingyu Chen, Fu-Jen Chu, Pierre Gleize, Kevin J Liang, Alexander Sax, Hao Tang, Weiyao Wang, Michelle Guo, Thibaut Hardin, Xiang Li, et al. 2025. Sam 3d: 3dfy anything in images.����� �������� ����������������(2025)

    2025

  8. [8]

    Yiwen Chen, Tong He, Di Huang, Weicai Ye, Sijin Chen, Jiaxiang Tang, Xin Chen, Zhongang Cai, Lei Yang, Gang Yu, Guosheng Lin, and Chi Zhang. 2024. Me- shAnything: Artist-Created Mesh Generation with Autoregressive Transformers. arXiv:2406.10163 [cs.CV] https://arxiv.org/abs/2406.10163

    Pith/arXiv arXiv 2024

  9. [9]

    Yiwen Chen, Yikai Wang, Yihao Luo, Zhengyi Wang, Zilong Chen, Jun Zhu, Chi Zhang, and Guosheng Lin. 2024. MeshAnything V2: Artist-Created Mesh Generation With Adjacent Mesh Tokenization. arXiv:2408.02555 [cs.CV] https: //arxiv.org/abs/2408.02555

    Pith/arXiv arXiv 2024

  10. [10]

    Zilong Chen, Yikai Wang, Wenqiang Sun, Feng Wang, Yiwen Chen, and Huaping Liu. 2025. MeshGen: Generating PBR Textured Mesh with Render-Enhanced Auto-Encoder and Generative Data Augmentation. arXiv:2505.04656 [cs.GR] https://arxiv.org/abs/2505.04656

    Pith/arXiv arXiv 2025

  11. [11]

    Zilong Chen, Yikai Wang, Feng Wang, Zhengyi Wang, and Huaping Liu

  12. [12]

    V3d: Video diffusion models are effective 3d generators.����� �������� ����������������(2024)

    2024

  13. [13]

    Matt Deitke, Ruoshi Liu, Matthew Wallingford, Huong Ngo, Oscar Michel, Aditya Kusupati, Alan Fan, Christian Laforte, Vikram Voleti, Samir Yitzhak Gadre, et al. 2023. Objaverse-xl: A universe of 10m+ 3d objects.�������� �� ������ ����������� ���������� �������36 (2023), 35799–35813

    2023

  14. [14]

    Laura Downs, Anthony Francis, Nate Maggio, Brandon Cavalcanti, Gerard Tagli- abue, Jake Varley, and Brian Ichter. 2022. Google scanned objects: A high-quality dataset of 3D scanned household items. In���� ������������� ���������� �� �������� ��� ���������� ������. IEEE, 2553–2560

    2022

  15. [15]

    Zhiwen Fan, Wenyan Cong, Kairun Wen, Kevin Wang, Jian Zhang, Xinghao Ding, Danfei Xu, Boris Ivanovic, Marco Pavone, Georgios Pavlakos, et al. 2024. Instantsplat: Unbounded sparse-view pose-free gaussian splatting in 40 seconds. ����� �������� ����������������2, 3 (2024), 4

    2024

  16. [16]

    Yang Fu, Sifei Liu, Amey Kulkarni, Jan Kautz, Alexei A Efros, and Xiaolong Wang. 2023. COLMAP-Free 3D Gaussian Splatting.���� �������� ���������� �� �������� ������ ��� ������� ����������� ������(2023), 20796–20805

    2023

  17. [17]

    Jun Gao, Tianchang Shen, Zian Wang, Wenzheng Chen, Kangxue Yin, Daiqing Li, Or Litany, Zan Gojcic, and Sanja Fidler. 2022. Get3d: A generative model of high quality 3d textured shapes learned from images.�������� �� ������ ����������� ���������� �������35 (2022), 31841–31854

    2022

  18. [18]

    Hyojun Go, Dominik Narnhofer, Goutam Bhat, Prune Truong, Federico Tombari, and Konrad Schindler. 2025. VIST3A: Text-to-3D by Stitching a Multi-view Reconstruction Network to a Video Generator.����� �������� ���������������� (2025)

    2025

  19. [19]

    Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. 2014. Generative adversarial nets.�������� �� ������ ����������� ���������� �������27 (2014)

    2014

  20. [20]

    Xiaodong Gu, Zhiwen Fan, Siyu Zhu, Zuozhuo Dai, Feitong Tan, and Ping Tan

  21. [21]

    In����������� �� ��� �������� ���������� �� �������� ������ ��� ������� ����������� ������

    Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matching. In����������� �� ��� �������� ���������� �� �������� ������ ��� ������� ����������� ������. 2495–2504

  22. [22]

    Romero, Tsung-Yi Lin, and Ming-Yu Liu

    Zekun Hao, David W. Romero, Tsung-Yi Lin, and Ming-Yu Liu. 2024. Meshtron: High-Fidelity, Artist-Like 3D Mesh Generation at Scale. arXiv:2412.09548 [cs.GR] https://arxiv.org/abs/2412.09548

    Pith/arXiv arXiv 2024

  23. [23]

    Hao He, Yixun Liang, Luozhou Wang, Yuanhao Cai, Xinli Xu, Hao-Xiang Guo, Xiang Wen, and Ying-Cong Chen. 2024. Lucidfusion: Generating 3d gaussians with arbitrary unposed images. (2024)

    2024

  24. [24]

    Xianglong He, Junyi Chen, Sida Peng, Di Huang, Yangguang Li, Xiaoshui Huang, Chun Yuan, Wanli Ouyang, and Tong He. 2024. GVGEN: Text-to-3D Generation with Volumetric Representation. In�������� ���������� �� �������� ������

    2024

  25. [25]

    Xianglong He, Zi-Xin Zou, Chia-Hao Chen, Yuan-Chen Guo, Ding Liang, Chun Yuan, Wanli Ouyang, Yan-Pei Cao, and Yangguang Li. 2025. SparseFlex: High-Resolution and Arbitrary-Topology 3D Shape Modeling. arXiv:2503.21732 [cs.CV] https://arxiv.org/abs/2503.21732

    Pith/arXiv arXiv 2025

  26. [26]

    Jonathan Ho, Ajay Jain, and Pieter Abbeel. 2020. Denoising diffusion probabilistic models.�������� �� ������ ����������� ���������� �������33 (2020), 6840–6851. ACM Trans. Graph., Vol. 1, No. 1, Article . Publication date: April 2026. UniRecGen: Unifying Multi-View 3D Reconstruction and Generation�9

    2020

  27. [27]

    Fangzhou Hong, Jiaxiang Tang, Ziang Cao, Min Shi, Tong Wu, Zhaoxi Chen, Tengfei Wang, Liang Pan, Dahua Lin, and Ziwei Liu. 2024. 3DTopia: Large Text- to-3D Generation Model with Hybrid Diffusion Priors.����abs/2403.02234 (2024)

    Pith/arXiv arXiv 2024

  28. [28]

    Jiaxin Huang, Yuanbo Yang, Bangbang Yang, Lin Ma, Yuewen Ma, and Yiyi Liao

  29. [29]

    Gen3R: 3D Scene Generation Meets Feed-Forward Reconstruction.����� �������� ����������������(2026)

    2026

  30. [30]

    Ka-Hei Hui, Ruihui Li, Jingyu Hu, and Chi-Wing Fu. 2022. Neural wavelet- domain diffusion for 3d shape generation. In�������� ���� ���� ���������� ������. 1–9

    2022

  31. [31]

    Team Hunyuan3D, Shuhui Yang, Mingxin Yang, Yifei Feng, Xin Huang, Sheng Zhang, Zebin He, Di Luo, Haolin Liu, Yunfei Zhao, et al. 2025. Hunyuan3D 2.1: From Images to High-Fidelity 3D Assets with Production-Ready PBR Material. ����� �������� ����������������(2025)

    2025

  32. [32]

    Team Hunyuan3D, Bowen Zhang, Chunchao Guo, Haolin Liu, Hongyu Yan, Huiwen Shi, Jingwei Huang, Junlin Yu, Kunhong Li, Penghao Wang, et al. 2025. Hunyuan3d-omni: A unified framework for controllable generation of 3d assets. ����� �������� ����������������(2025)

    2025

  33. [33]

    Shubhendu Jena, Shishir Reddy Vutukur, and Adnane Boukhayma. 2025. Spar- Splat: Fast Multi-View Reconstruction with Generalizable 2D Gaussian Splatting. ����� �������� ����������������(2025)

    2025

  34. [34]

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

  35. [35]

    3D Gaussian Splatting for Real-Time Radiance Field Rendering.��� ������������ �� ��������42, 4 (2023), 139–1

    2023

  36. [36]

    Zeqiang Lai, Yunfei Zhao, Haolin Liu, Zibo Zhao, Qingxiang Lin, Huiwen Shi, Xianghui Yang, Mingxin Yang, Shuhui Yang, Yifei Feng, Sheng Zhang, Xin Huang, Di Luo, Fan Yang, Fang Yang, Lifu Wang, Sicong Liu, Yixuan Tang, Yulin Cai, Zebin He, Tian Liu, Yuhong Liu, Jie Jiang, Linus, Jingwei Huang, and Chunchao Guo. 2025. Hunyuan3D 2.5: Towards High-Fidelity 3...

    Pith/arXiv arXiv 2025

  37. [37]

    Yushi Lan, Fangzhou Hong, Shuai Yang, Shangchen Zhou, Xuyi Meng, Bo Dai, Xingang Pan, and Chen Change Loy. 2024. LN3Diff: Scalable Latent Neural Fields Diffusion for Speedy 3D Generation. In����

    2024

  38. [38]

    Vincent Leroy, Yohann Cabon, and Jérôme Revaud. 2024. Grounding image matching in 3d with MASt3R. In�������� ���������� �� �������� ������. 71– 91

    2024

  39. [39]

    Jiahao Li, Hao Tan, Kai Zhang, Zexiang Xu, Fujun Luan, Yinghao Xu, Yicong Hong, Kalyan Sunkavalli, Greg Shakhnarovich, and Sai Bi. 2023. Instant3d: Fast text-to-3d with sparse-view generation and large reconstruction model.����� �������� ����������������(2023)

    2023

  40. [40]

    Weiyu Li, Jiarui Liu, Rui Chen, Yixun Liang, Xuelin Chen, Ping Tan, and Xi- aoxiao Long. 2024. CraftsMan: High-fidelity Mesh Generation with 3D Native Generation and Interactive Geometry Refiner.����� �������� ���������������� (2024)

    2024

  41. [41]

    Yangguang Li, Zi-Xin Zou, Zexiang Liu, Dehu Wang, Yuan Liang, Zhipeng Yu, Xingchao Liu, Yuan-Chen Guo, Ding Liang, Wanli Ouyang, et al. 2025. TripoSG: High-Fidelity 3D Shape Synthesis using Large-Scale Rectified Flow Models.����� �������� ����������������(2025)

    2025

  42. [42]

    Zhihao Li, Yufei Wang, Heliang Zheng, Yihao Luo, and Bihan Wen. 2025. Sparc3D: Sparse Representation and Construction for High-Resolution 3D Shapes Model- ing. arXiv:2505.14521 [cs.CV] https://arxiv.org/abs/2505.14521

    Pith/arXiv arXiv 2025

  43. [43]

    Hanwen Liang, Junli Cao, Vidit Goel, Guocheng Qian, Sergei Korolev, Demetri Terzopoulos, Konstantinos N Plataniotis, Sergey Tulyakov, and Jian Ren. 2025. Wonderland: Navigating 3d scenes from a single image. In�������� ���������� �� �������� ������ ��� ������� �����������. 798–810

    2025

  44. [44]

    Chenguo Lin, Panwang Pan, Bangbang Yang, Zeming Li, and Yadong MU. 2025. DiffSplat: Repurposing Image Diffusion Models for Scalable Gaussian Splat Generation. In������������� ���������� �� �������� ���������������

    2025

  45. [45]

    Chen-Hsuan Lin, Wei-Chiu Ma, Antonio Torralba, and Simon Lucey. 2021. BARF: Bundle-Adjusting Neural Radiance Fields. In����������� �� ��� �������� ������ �������� ���������� �� �������� ������ ������. 5741–5751

    2021

  46. [46]

    Yuchen Lin, Chenguo Lin, Panwang Pan, Honglei Yan, Yiqiang Feng, Yadong Mu, and Katerina Fragkiadaki. 2025. PartCrafter: Structured 3D Mesh Generation via Compositional Latent Diffusion Transformers. arXiv:2506.05573 [cs.CV] https://arxiv.org/abs/2506.05573

    Pith/arXiv arXiv 2025

  47. [47]

    Minghua Liu, Chao Xu, Haian Jin, Linghao Chen, Mukund Varma T, Zexiang Xu, and Hao Su. 2023. One-2-3-45: Any single image to 3d mesh in 45 seconds without per-shape optimization.�������� �� ������ ����������� ���������� �������36 (2023), 22226–22246

    2023

  48. [48]

    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 ����������� �� ��� �������� ������������� ���������� �� �������� ������. 9298– 9309

    2023

  49. [49]

    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. In����������� �� ��� �������� ���������� �� �������� ������ ��� ������� �����������. 9970–9980

    2024

  50. [50]

    William E Lorensen and Harvey E Cline. 1987. Marching cubes: A high resolution 3D surface construction algorithm.��� �������� �������� ��������21, 4 (1987), 163–169

    1987

  51. [51]

    Shitong Luo and Wei Hu. 2021. Diffusion probabilistic models for 3d point cloud generation. In����������� �� ��� �������� ���������� �� �������� ������ ��� ������� �����������. 2837–2845

    2021

  52. [52]

    Ben Mildenhall, Pratul P Srinivasan, Matthew Tancik, Jonathan T Barron, Ravi Ramamoorthi, and Ren Ng. 2020. NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis. In�������� ���������� �� �������� ������ ������. 405–421

    2020

  53. [53]

    Norman Müller, Yawar Siddiqui, Lorenzo Porzi, Samuel Rota Bulo, Peter Kontschieder, and Matthias Nießner. 2023. Diffrf: Rendering-guided 3d radiance field diffusion. In����������� �� ��� �������� ���������� �� �������� ������ ��� ������� �����������. 4328–4338

    2023

  54. [54]

    Alex Nichol, Heewoo Jun, Prafulla Dhariwal, Pamela Mishkin, and Mark Chen

  55. [55]

    ����� �������� ����������������(2022)

    Point-e: A system for generating 3d point clouds from complex prompts. ����� �������� ����������������(2022)

    2022

  56. [56]

    Barron, Ben Mildenhall, Mehdi S

    Michael Niemeyer, Jonathan T. Barron, Ben Mildenhall, Mehdi S. M. Sajjadi, An- dreas Geiger, and Noha Radwan. 2022. RegNeRF: Regularizing Neural Radiance Fields for View Synthesis from Sparse Inputs. In���� �������� ���������� �� �������� ������ ��� ������� ����������� ������. IEEE, New Orleans, LA, USA. doi:10.1109/CVPR52688.2022.00540

    doi:10.1109/cvpr52688.2022.00540 2022

  57. [57]

    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. ����� �������� ����������������(2023)

    2023

  58. [58]

    Jeong Joon Park, Peter Florence, Julian Straub, Richard Newcombe, and Steven Lovegrove. 2019. Deepsdf: Learning continuous signed distance functions for shape representation. In����������� �� ��� �������� ���������� �� �������� ������ ��� ������� �����������. 165–174

    2019

  59. [59]

    Ben Poole, Ajay Jain, Jonathan T Barron, and Ben Mildenhall. 2023. Dream- Fusion: Text-to-3D using 2D Diffusion. In������������� ���������� �� �������� ���������������

    2023

  60. [60]

    Robin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser, and Björn Ommer. 2022. High-resolution image synthesis with latent diffusion models. In ����������� �� ��� �������� ���������� �� �������� ������ ��� ������� �������� ����. 10684–10695

    2022

  61. [61]

    Johannes L Schönberger and Jan-Michael Frahm. 2016. Structure-from-motion revisited. In���� ���������� �� �������� ������ ��� ������� �����������. 4104– 4113

    2016

  62. [62]

    Schönberger, Enliang Zheng, Marc Pollefeys, and Jan-Michael Frahm

    Johannes L. Schönberger, Enliang Zheng, Marc Pollefeys, and Jan-Michael Frahm

  63. [63]

    In�������� ���������� �� �������� ������ ������

    Pixelwise View Selection for Unstructured Multi-View Stereo. In�������� ���������� �� �������� ������ ������. 501–518

  64. [64]

    Katja Schwarz, Norman Mueller, and Peter Kontschieder. 2025. Generative Gaussian splatting: Generating 3D scenes with video diffusion priors.����� �������� ����������������(2025)

    2025

  65. [65]

    Yichun Shi, Peng Wang, Jianglong Ye, Long Mai, Kejie Li, and Xiao Yang. 2024. MVDream: Multi-view Diffusion for 3D Generation. In������������� ���������� �� �������� ���������������

    2024

  66. [66]

    Yawar Siddiqui, Antonio Alliegro, Alexey Artemov, Tatiana Tommasi, Daniele Sirigatti, Vladislav Rosov, Angela Dai, and Matthias Nießner. 2024. Meshgpt: Generating triangle meshes with decoder-only transformers. In����������� �� ��� �������� ���������� �� �������� ������ ��� ������� ����������� ������

    2024

  67. [67]

    Jascha Sohl-Dickstein, Eric Weiss, Niru Maheswaranathan, and Surya Ganguli

  68. [68]

    In ������������� ���������� �� ������� ��������

    Deep unsupervised learning using nonequilibrium thermodynamics. In ������������� ���������� �� ������� ��������. 2256–2265

  69. [69]

    Stefan Stojanov, Anh Thai, and James M Rehg. 2021. Using shape to categorize: Low-shot learning with an explicit shape bias. In����������� �� ��� �������� ���������� �� �������� ������ ��� ������� �����������. 1798–1808

    2021

  70. [70]

    Stanislaw Szymanowicz, Jason Y Zhang, Pratul Srinivasan, Ruiqi Gao, Arthur Brussee, Aleksander Holynski, Ricardo Martin-Brualla, Jonathan T Barron, and Philipp Henzler. 2025. Bolt3D: Generating 3D scenes in seconds.����� �������� ����������������(2025)

    2025

  71. [71]

    Bin Tan, Nan Xue, Tianfu Wu, and Gui-Song Xia. 2023. NOPE-SAC: Neural One- Plane RANSAC for Sparse-View Planar 3D Reconstruction.���� ������������ �� ������� �������� ��� ������� ������������45 (2023). doi:10.1109/TPAMI.2023. 3314745

    doi:10.1109/tpami.2023 2023

  72. [72]

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

    2024

  73. [73]

    Jiaxiang Tang, Zhaoshuo Li, Zekun Hao, Xian Liu, Gang Zeng, Ming-Yu Liu, and Qinsheng Zhang. 2024. EdgeRunner: Auto-regressive Auto-encoder for Artistic Mesh Generation. arXiv:2409.18114 [cs.CV] https://arxiv.org/abs/2409.18114

    Pith/arXiv arXiv 2024

  74. [74]

    Jiaxiang Tang, Ruijie Lu, Zhaoshuo Li, Zekun Hao, Xuan Li, Fangyin Wei, Shuran Song, Gang Zeng, Ming-Yu Liu, and Tsung-Yi Lin. 2025. Efficient Part-level ACM Trans. Graph., Vol. 1, No. 1, Article . Publication date: April 2026. 10�Huang et al. 3D Object Generation via Dual Volume Packing. arXiv:2506.09980 [cs.CV] https://arxiv.org/abs/2506.09980

    Pith/arXiv arXiv 2025

  75. [75]

    Junshu Tang, Tengfei Wang, Bo Zhang, Ting Zhang, Ran Yi, Lizhuang Ma, and Dong Chen. 2023. Make-it-3d: High-fidelity 3d creation from a single image with diffusion prior. In����������� �� ��� �������� ������������� ���������� �� �������� ������. 22819–22829

    2023

  76. [76]

    Shengji Tang, Weicai Ye, Peng Ye, Weihao Lin, Yang Zhou, Tao Chen, and Wanli Ouyang. 2024. HiSplat: Hierarchical 3D Gaussian Splatting for Generalizable Sparse-View Reconstruction.����� �������� ����������������(2024)

    2024

  77. [77]

    Arash Vahdat, Francis Williams, Zan Gojcic, Or Litany, Sanja Fidler, Karsten Kreis, et al. 2022. Lion: Latent point diffusion models for 3d shape generation. �������� �� ������ ����������� ���������� �������35 (2022), 10021–10039

    2022

  78. [78]

    Vikram Voleti, Chun-Han Yao, Mark Boss, Adam Letts, David Pankratz, Dmitry Tochilkin, Christian Laforte, Robin Rombach, and Varun Jampani. 2024. Sv3d: Novel multi-view synthesis and 3d generation from a single image using latent video diffusion. In�������� ���������� �� �������� ������. Springer, 439–457

    2024

  79. [79]

    Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, and Marc Pollefeys. 2021. PatchmatchNet: Learned Multi-View Patchmatch Stereo. In���� �������� �� ��� �������� ���������� �� �������� ������ ��� ������� ����������� ������. 14194–14203

    2021

  80. [80]

    Jianyuan Wang, Minghao Chen, Nikita Karaev, Andrea Vedaldi, Christian Rup- precht, and David Novotny. 2025. VGGT: Visual geometry grounded transformer. In�������� ���������� �� �������� ������ ��� ������� �����������. 5294–5306

    2025

Showing first 80 references.