Pith. sign in

REVIEW 1 major objections 1 minor 38 references

Reviewed by Pith at T0; open to challenge.

T0 means a machine referee read the full paper against a public rubric. The mark states how deep the mechanical check went, never who wrote it. the ladder, T0–T4 →

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

T0 review · grok-4.3

Flow matching with point transformers completes medical point clouds competitively with deterministic models while using fewer sampling steps than diffusion.

2026-06-26 00:21 UTC pith:KTBWSHKP

load-bearing objection PCFM pairs flow matching with PTv3 for medical point cloud completion and reports clear sampling and throughput gains over diffusion on the three tested datasets. the 1 major comments →

arxiv 2606.24433 v1 pith:KTBWSHKP submitted 2026-06-23 cs.CV cs.AIcs.LG

MedPCFM: Improving Medical Point Cloud Completion by Integrating Point Transformers and Flow Matching

Kamil Kwarciak , Marek Wodzinski This is my paper
classification cs.CV cs.AIcs.LG
keywords medical point cloud completionflow matchingpoint transformergenerative modelingskull reconstructionmandibular defect
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.

The paper investigates continuous-time generative modeling for medical point cloud completion and introduces PCFM, a model that integrates Point Transformer v3 (PTv3) as the backbone for flow matching. It constructs baselines consisting of a deterministic PTv3 encoder-decoder and diffusion-based completion models instantiated with both PVCNN and PTv3. Evaluations across SkullFix, SkullBreak, and the Mandibular Defect dataset show that PCFM with PTv3 matches the deterministic baseline in quality, delivers state-of-the-art generative results, and requires substantially fewer sampling steps than diffusion while gaining up to 7× throughput from the PTv3 backbone. Scaling experiments further reveal consistent gains at higher point resolutions alongside model-size trade-offs.

Core claim

PCFM, a PTv3-backed flow matching approach for medical point cloud completion, is competitive with the deterministic PTv3 baseline and achieves state-of-the-art generative performance across SkullFix, SkullBreak, and Mandibular Defect datasets, while requiring substantially fewer sampling steps than diffusion and providing clear throughput gains with the PTv3 backbone.

What carries the argument

PCFM, the PTv3-backed continuous-time flow matching model, which performs generative point cloud completion by learning a velocity field instead of a noise schedule.

Load-bearing premise

The performance advantage of flow matching over diffusion and the throughput advantage of PTv3 over PVCNN will persist on new clinical datasets whose distribution differs from SkullFix, SkullBreak, and the Mandibular Defect collection.

What would settle it

A head-to-head run on an unseen clinical point cloud dataset in which PCFM with PTv3 requires more sampling steps than the diffusion baseline or falls below the deterministic PTv3 baseline on completion metrics.

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

If this is right

  • PCFM with PTv3 matches deterministic PTv3 completion quality while adding generative capabilities.
  • PCFM achieves state-of-the-art generative performance on the three evaluated medical datasets.
  • PCFM requires substantially fewer sampling steps than diffusion-based PCDiff models.
  • PTv3 delivers up to 7× throughput improvement for PCFM relative to a PVCNN backbone.
  • Higher point cardinality yields consistent performance gains with informative model-size trade-offs.

Where Pith is reading between the lines

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

  • The reduced sampling steps could enable faster generation of multiple anatomical reconstructions when uncertainty is clinically relevant.
  • The observed scaling behavior suggests that further increases in point resolution may improve fine anatomical detail without proportional compute cost.
  • Efficiency gains from PTv3 might extend to other 3D medical completion tasks that currently rely on slower backbones.
  • Model-size trade-offs could inform deployment choices on hardware with different memory or latency constraints.

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

1 major / 1 minor

Summary. The manuscript introduces PCFM, a continuous-time generative model using flow matching and Point Transformer v3 (PTv3) for medical point cloud completion. It builds baselines including a deterministic PTv3 encoder-decoder and diffusion models (PCDiff) with PVCNN and PTv3, evaluates on SkullFix, SkullBreak, and Mandibular Defect datasets, and claims that PCFM+PTv3 is competitive with the deterministic baseline, achieves SOTA generative performance, requires fewer sampling steps than diffusion, and provides up to 7× throughput gains with PTv3, along with scaling trends.

Significance. If the empirical results hold, the paper contributes to generative modeling in medical imaging by demonstrating the practical advantages of flow matching over diffusion for point cloud tasks and the efficiency of PTv3 backbones. The multi-dataset evaluation and scaling analysis are positive elements that could inform future work in anatomical reconstruction.

major comments (1)
  1. [Experiments] Experiments section: The performance advantages and SOTA generative claims for PCFM with PTv3 are demonstrated only on SkullFix, SkullBreak, and Mandibular Defect without cross-site, cross-modality, or external-validation experiments on datasets with distribution shifts (e.g., different scanners, resolutions, or patient demographics), which directly bears on the applicability of the efficiency and performance edges to clinical use.
minor comments (1)
  1. [Abstract] Abstract: The description of baselines and claims is clear but omits any quantitative metrics, error bars, or statistical details, which reduces immediate assessability of the reported gains.

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for highlighting the importance of broader validation for clinical applicability. We address the concern regarding the scope of our experiments below.

read point-by-point responses

  1. Referee: [Experiments] Experiments section: The performance advantages and SOTA generative claims for PCFM with PTv3 are demonstrated only on SkullFix, SkullBreak, and Mandibular Defect without cross-site, cross-modality, or external-validation experiments on datasets with distribution shifts (e.g., different scanners, resolutions, or patient demographics), which directly bears on the applicability of the efficiency and performance edges to clinical use.

    Authors: We agree that the current evaluation is confined to the standard public benchmarks SkullFix, SkullBreak, and Mandibular Defect, which do not include explicit cross-site, cross-modality, or external validation under distribution shifts. These datasets are the primary resources used in prior work on skull and mandible completion and contain variations in defect morphology and patient anatomy, but they originate from limited acquisition settings. We acknowledge that this limits direct claims about robustness in diverse clinical environments. In the revised manuscript we will add a dedicated paragraph in the Discussion section that explicitly states this limitation, discusses potential impacts on clinical translation, and outlines future work on multi-center validation. We cannot perform new cross-site experiments within the scope of this revision, as that would require access to additional private clinical datasets not available to the authors. revision: partial

Circularity Check

0 steps flagged

No significant circularity in derivation or claims

full rationale

The paper introduces PCFM as a flow-matching model backed by PTv3 for medical point cloud completion and reports empirical performance on held-out test portions of SkullFix, SkullBreak, and Mandibular Defect. No equations, fitted parameters, or self-citations are shown to reduce the reported metrics (completion quality, sampling steps, throughput) to quantities defined by construction inside the paper. Baselines are instantiated separately (deterministic PTv3 encoder-decoder and PCDiff variants), and results are measured directly rather than derived tautologically from inputs. The derivation chain is therefore self-contained against external benchmarks.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

The central claim rests on standard assumptions of supervised point-cloud learning (i.i.d. train/test splits, Chamfer or similar distance as proxy for anatomical fidelity) plus the usual deep-learning hyper-parameters. No new physical entities or ad-hoc mathematical axioms are introduced.

pith-pipeline@v0.9.1-grok · 5722 in / 1134 out tokens · 14870 ms · 2026-06-26T00:21:41.668808+00:00 · methodology

0 comments
read the original abstract

Medical point cloud completion is important for anatomical reconstruction and downstream clinical workflows, yet generative modeling in this setting remains insufficiently studied. We investigate completion through continuous-time generative modeling and introduce PCFM, a PTv3-backed flow matching approach for medical point cloud completion. We evaluate on SkullFix and SkullBreak, and additionally on the more recent Mandibular Defect dataset. We build strong baselines by adapting PTv3 to a deterministic encoder-decoder completion model and by instantiating diffusion completion (PCDiff) with both PVCNN and PTv3 denoisers. PCFM with PTv3 is competitive with the deterministic PTv3 baseline and achieves state-of-the-art generative performance across datasets, while requiring substantially fewer sampling steps than diffusion. At the best operating points, PTv3 also yields clear throughput gains, providing up to a 7$\times$ speed-up for PCFM compared to a PVCNN backbone. Finally, we study empirical scaling trends by varying model size and point cardinality, showing consistent gains with higher point resolution and informative trade-offs across model scales.

Figures

Figures reproduced from arXiv: 2606.24433 by Kamil Kwarciak, Marek Wodzinski.

Figure 1
Figure 1. Figure 1: Comparison of all methods evaluated in this study across all datasets using Chamfer Distance (CD) [mm], plotted on an inversely scaled radial axis so that lower CD indicates better performance while higher radial values improve visual interpretabil￾ity. Recent progress in point cloud modeling has been driven by transformer backbones, with PointTransformerV3 (PTv3) [32] emerging as a state-of-the￾art archit… view at source ↗
Figure 2
Figure 2. Figure 2: Overview of our pipeline. In the deterministic regime, the model maps the defective input X to a completion Yˆ . In the generative regime, we model the missing part through a time-dependent state Yt conditioned on X: diffusion predicts ϵθ(Yt, t, X), while flow matching predicts a velocity field vθ(Yt, t, X) and generates Yˆ by ODE integration. Dashed arrows indicate components used only in the generative r… view at source ↗
Figure 3
Figure 3. Figure 3: Scaling trends for PCFM on SkullBreak. Left: Chamfer Distance [mm] versus input point cardinality NX. Right: Chamfer Distance [mm] versus model size (param￾eter count). Lower is better [PITH_FULL_IMAGE:figures/full_fig_p011_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Qualitative comparison across datasets. Top: SkullBreak, middle: SkullFix, bottom: Mandibular Defect. For the volumetric baselines, point clouds are obtained by extracting surfaces and sampling points using Poisson surface sampling followed by farthest point sampling (FPS), consistent with the preprocessing used for point-based methods. 5 Discussion We introduced PCFM with a PTv3 backbone as a flow-matchin… view at source ↗
Figure 5
Figure 5. Figure 5: Qualitative effect of repulsion in the deterministic PTv3 encoder-decoder Skull￾Fix (Small, 2048/2048). Mild repulsion (λ = 30) yields a visually similar completion to λ = 0, whereas strong repulsion (λ = 300) can produce degenerate point distributions with large voids and concentrated point islands [PITH_FULL_IMAGE:figures/full_fig_p020_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: Multi-sample variability for PCFM-PTv3 on a fixed input. We show several generated implant samples, their mean completion, and a variance map. The global implant geometry remains stable across samples, while higher variance appears near the defect boundary, indicating localized uncertainty in ambiguous regions. D Multi-Sample Generative Variability A practical advantage of generative completion is that the… view at source ↗
Figure 7
Figure 7. Figure 7: Inference pipeline for the multi-iterative setup. We sample a dense point cloud from the surface and run the model N times on independently resampled (FPS + jitter) inputs. The predicted implant point sets are then aggregated by concatenation to form a denser completion, which is converted to a mesh for downstream fabrication/3D printing and optionally voxelized for volumetric evaluation. We report the eff… view at source ↗
Figure 8
Figure 8. Figure 8: Effect of the multi-iterative aggregation on SkullFix for PCFM–PTv3 (Linear). We run inference on N ∈ {1, 8, 32, 128} independently resampled inputs and concate￾nate the resulting implant point clouds. Increasing N consistently improves voxel-space metrics (DSC/BDSC ↑) and reduces HD95 ↓; the dashed line indicates the single-pass (N = 1) baseline [PITH_FULL_IMAGE:figures/full_fig_p022_8.png] view at source ↗
Figure 9
Figure 9. Figure 9: Additional qualitative comparisons across datasets and methods. Rows 1-3: SkullBreak, rows 4-6: SkullFix, rows 7-9: Mandibular Defect. For volumetric baselines, point clouds are obtained by extracting surfaces and sampling points using Poisson surface sampling followed by farthest point sampling (FPS), consistent with the pre￾processing used for point-based methods [PITH_FULL_IMAGE:figures/full_fig_p025_9.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

38 extracted references · 5 canonical work pages · 4 internal anchors

  1. [1]

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

    Chen, A., Zhang, K., Zhang, R., Wang, Z., Lu, Y., Guo, Y., Zhang, S.: Pimae: Point cloud and image interactive masked autoencoders for 3d object detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 5291–5301 (2023)

    2023

  2. [2]

    In: International conference on medical image computing and computer-assisted intervention

    Çiçek, Ö., Abdulkadir, A., Lienkamp, S.S., Brox, T., Ronneberger, O.: 3d u-net: learning dense volumetric segmentation from sparse annotation. In: International conference on medical image computing and computer-assisted intervention. pp. 424–432. Springer (2016)

    2016

  3. [3]

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

    De Vries, M., Naidoo, R., Fourkioti, O., Dent, L.G., Curry, N., Dunsby, C., Bakal, C.: Interpretable point cloud classification using multiple instance learning. In: Proceedings of the IEEE/CVF International Conference on Computer Vision. pp. 22209–22220 (2025)

    2025

  4. [4]

    In: Proceedings of the Computer Vision and Pattern Recognition Conference

    Du, Y., Zhao, Z., Su, S., Golluri, S., Zheng, H., Yao, R., Wang, C.: Superpc: a single diffusion model for point cloud completion, upsampling, denoising, and coloriza- tion. In: Proceedings of the Computer Vision and Pattern Recognition Conference. pp. 16953–16964 (2025)

    2025

  5. [5]

    In: International conference on medical image computing and computer-assisted intervention

    Friedrich, P., Wolleb, J., Bieder, F., Thieringer, F.M., Cattin, P.C.: Point cloud diffusion models for automatic implant generation. In: International conference on medical image computing and computer-assisted intervention. pp. 112–122. Springer (2023)

    2023

  6. [6]

    Advances in neural information processing systems33, 6840–6851 (2020)

    Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. Advances in neural information processing systems33, 6840–6851 (2020)

    2020

  7. [7]

    Adam: A Method for Stochastic Optimization

    Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)

    work page internal anchor Pith review Pith/arXiv arXiv 2014

  8. [8]

    Data in Brief35, 106902 (2021)

    Kodym, O., Li, J., Pepe, A., Gsaxner, C., Chilamkurthy, S., Egger, J., Španěl, M.: Skullbreak/skullfix–dataset for automatic cranial implant design and a benchmark for volumetric shape learning tasks. Data in Brief35, 106902 (2021)

    2021

  9. [9]

    Advances in Neural Information Process- ing Systems37, 104180–104204 (2024)

    Kornilov,N.,Mokrov,P.,Gasnikov,A.,Korotin,A.:Optimalflowmatching:Learn- ing straight trajectories in just one step. Advances in Neural Information Process- ing Systems37, 104180–104204 (2024)

    2024

  10. [10]

    In: Proceedings of the IEEE/CVF International Con- ference on Computer Vision

    Kwarciak, K., Wodziński, M.: Deep generative networks for heterogeneous aug- mentation of cranial defects. In: Proceedings of the IEEE/CVF International Con- ference on Computer Vision. pp. 1066–1074 (2023)

    2023

  11. [11]

    Medical Image Analysis88, 102865 (2023)

    Li, J., Ellis, D.G., Kodym, O., Rauschenbach, L., Rieß, C., Sure, U., Wrede, K.H., Alvarez, C.M., Wodzinski, M., Daniol, M., et al.: Towards clinical applicability and computational efficiency in automatic cranial implant design: An overview of the autoimplant 2021 cranial implant design challenge. Medical Image Analysis88, 102865 (2023)

    2021

  12. [12]

    Flow Matching for Generative Modeling

    Lipman, Y., Chen, R.T., Ben-Hamu, H., Nickel, M., Le, M.: Flow matching for generative modeling. arXiv preprint arXiv:2210.02747 (2022)

    work page internal anchor Pith review Pith/arXiv arXiv 2022

  13. [13]

    Flow Matching Guide and Code

    Lipman, Y., Havasi, M., Holderrieth, P., Shaul, N., Le, M., Karrer, B., Chen, R.T., Lopez-Paz, D., Ben-Hamu, H., Gat, I.: Flow matching guide and code. arXiv preprint arXiv:2412.06264 (2024)

    work page internal anchor Pith review Pith/arXiv arXiv 2024

  14. [14]

    Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow

    Liu, X., Gong, C., Liu, Q.: Flow straight and fast: Learning to generate and transfer data with rectified flow. arXiv preprint arXiv:2209.03003 (2022)

    work page internal anchor Pith review Pith/arXiv arXiv 2022

  15. [15]

    Advances in neural information processing systems32(2019) 16 K.Kwarciak and M

    Liu, Z., Tang, H., Lin, Y., Han, S.: Point-voxel cnn for efficient 3d deep learning. Advances in neural information processing systems32(2019) 16 K.Kwarciak and M. Wodzinski

    2019

  16. [16]

    In: Proceedings of the IEEE/CVF conference on computer vision and pattern recog- nition

    Luo, S., Hu, W.: Diffusion probabilistic models for 3d point cloud generation. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recog- nition. pp. 2837–2845 (2021)

    2021

  17. [17]

    In: European Conference on Computer Vision

    Ma, N., Goldstein, M., Albergo, M.S., Boffi, N.M., Vanden-Eijnden, E., Xie, S.: Sit: Exploring flow and diffusion-based generative models with scalable interpolant transformers. In: European Conference on Computer Vision. pp. 23–40. Springer (2024)

    2024

  18. [18]

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

    Melas-Kyriazi, L., Rupprecht, C., Vedaldi, A.: Pc2: Projection-conditioned point cloud diffusion for single-image 3d reconstruction. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. pp. 12923– 12932 (2023)

    2023

  19. [19]

    In: 2016 fourth international confer- ence on 3D vision (3DV)

    Milletari, F., Navab, N., Ahmadi, S.A.: V-net: Fully convolutional neural networks for volumetric medical image segmentation. In: 2016 fourth international confer- ence on 3D vision (3DV). pp. 565–571. Ieee (2016)

    2016

  20. [20]

    In: Eu- ropean Conference on Computer Vision

    Noroozi, M., Hadji, I., Martinez, B., Bulat, A., Tzimiropoulos, G.: You only need one step: Fast super-resolution with stable diffusion via scale distillation. In: Eu- ropean Conference on Computer Vision. pp. 145–161. Springer (2024)

    2024

  21. [21]

    Advances in Neural Information Processing Systems34, 13032–13044 (2021)

    Peng, S., Jiang, C., Liao, Y., Niemeyer, M., Pollefeys, M., Geiger, A.: Shape as points: A differentiable poisson solver. Advances in Neural Information Processing Systems34, 13032–13044 (2021)

    2021

  22. [22]

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

    Qi, C.R., Su, H., Mo, K., Guibas, L.J.: Pointnet: Deep learning on point sets for 3d classification and segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 652–660 (2017)

    2017

  23. [23]

    Advances in neural information processing systems30(2017)

    Qi, C.R., Yi, L., Su, H., Guibas, L.J.: Pointnet++: Deep hierarchical feature learn- ing on point sets in a metric space. Advances in neural information processing systems30(2017)

    2017

  24. [24]

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

    Stoica, G., Ramanujan, V., Fan, X., Farhadi, A., Krishna, R., Hoffman, J.: Con- trastive flow matching. In: Proceedings of the IEEE/CVF International Conference on Computer Vision. pp. 1185–1194 (2025)

    2025

  25. [25]

    In: 2022 44th Annual Interna- tionalConferenceoftheIEEEEngineeringinMedicine&BiologySociety(EMBC)

    Sulakhe, H., Li, J., Egger, J., Goyal, P.: Crangan: Adversarial point cloud recon- struction for patient-specific cranial implant design. In: 2022 44th Annual Interna- tionalConferenceoftheIEEEEngineeringinMedicine&BiologySociety(EMBC). pp. 603–608. IEEE (2022)

    2022

  26. [26]

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

    Vu, T., Kim, K., Luu, T.M., Nguyen, T., Yoo, C.D.: Softgroup for 3d instance segmentation on point clouds. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. pp. 2708–2717 (2022)

    2022

  27. [27]

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

    Wang, W., Yu, R., Huang, Q., Neumann, U.: Sgpn: Similarity group proposal network for 3d point cloud instance segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 2569–2578 (2018)

    2018

  28. [28]

    in 2022 ieee

    Wang,Y.,Ye,T.,Cao,L.,Huang,W.,Sun,F.,He,F.,Tao,D.:Bridgedtransformer for vision and point cloud 3d object detection. in 2022 ieee. In: CVF Conference on Computer Vision and Pattern Recognition (CVPR). pp. 12104–12113 (2022)

    2022

  29. [29]

    In: International conference on medical image computing and computer- assisted intervention

    Wodzinski, M., Daniol, M., Hemmerling, D., Socha, M.: High-resolution cranial defect reconstruction by iterative, low-resolution, point cloud completion trans- formers. In: International conference on medical image computing and computer- assisted intervention. pp. 333–343. Springer (2023)

    2023

  30. [30]

    Scientific Data12(1), 1763 (2025) MedPCFM: Medical Point Cloud Completion 17

    Wu, J., Jiang, L., Shao, L., Wang, W., Xu, X., Zhou, Y., Wang, X., Wang, J., Wu, J., Chen, X., et al.: A mandibular defect dataset for autonomous reconstruction planning in oral and maxillofacial surgery. Scientific Data12(1), 1763 (2025) MedPCFM: Medical Point Cloud Completion 17

    2025

  31. [31]

    In: Proceedings of the AAAI Conference on Artificial Intelligence

    Wu, P., Chai, B., Li, H., Zheng, M., Peng, Y., Wang, Z., Nie, X., Zhang, Y., Sun, X.: Spiking point transformer for point cloud classification. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol. 39, pp. 21563–21571 (2025)

    2025

  32. [32]

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

    Wu, X., Jiang, L., Wang, P.S., Liu, Z., Liu, X., Qiao, Y., Ouyang, W., He, T., Zhao, H.: Point transformer v3: Simpler faster stronger. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. pp. 4840–4851 (2024)

    2024

  33. [33]

    Advances in Neural Information Processing Systems35, 33330–33342 (2022)

    Wu, X., Lao, Y., Jiang, L., Liu, X., Zhao, H.: Point transformer v2: Grouped vector attention and partition-based pooling. Advances in Neural Information Processing Systems35, 33330–33342 (2022)

    2022

  34. [34]

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

    You, W., Zhang, M., Zhang, L., Zhou, X., Shi, K., Gu, S.: Consistency trajec- tory matching for one-step generative super-resolution. In: Proceedings of the IEEE/CVF International Conference on Computer Vision. pp. 12747–12756 (2025)

    2025

  35. [35]

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

    Yu,L.,Li,X.,Fu,C.W.,Cohen-Or,D.,Heng,P.A.:Pu-net:Pointcloudupsampling network. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 2790–2799 (2018)

    2018

  36. [36]

    In: The Thirteenth International Conference on Learning Representations (2025)

    Yushi, L., Zhou, S., Lyu, Z., Hong, F., Yang, S., Dai, B., Pan, X., Loy, C.C.: Gaussiananything: Interactive point cloud flow matching for 3d generation. In: The Thirteenth International Conference on Learning Representations (2025)

    2025

  37. [37]

    In: Proceed- ings of the IEEE/CVF international conference on computer vision

    Zhao, H., Jiang, L., Jia, J., Torr, P.H., Koltun, V.: Point transformer. In: Proceed- ings of the IEEE/CVF international conference on computer vision. pp. 16259– 16268 (2021)

    2021

  38. [38]

    In: Proceedings of the IEEE/CVF international conference on computer vision

    Zhou, L., Du, Y., Wu, J.: 3d shape generation and completion through point-voxel diffusion. In: Proceedings of the IEEE/CVF international conference on computer vision. pp. 5826–5835 (2021) 18 K.Kwarciak and M. Wodzinski A Architectures and Training Details Table 4 reports the PTv3 architectural configurations used in this work together with the associate...

    work page arXiv 2021