Point Cloud Completion

Benchmarks archive 2025-07-28

3 leaderboard tables shown for this task, 3 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

5 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

1 subtask in the archive's task tree.

Parent tasks archive 2025-07-28

Most implemented papers archive 2025-07-28

30 shown of 97 papers with code (174 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• Pointer Networks
  9 Jun 2015 21 repositories listed Syntology ran 9 of 23 samples · 14 unverified · 7 pointer-only (licence)
  It differs from the previous attention attempts in that, instead of using attention to blend hidden units of an encoder to a context vector at each decoder step, it uses attention as a pointer to select a member of the…
• PCN: Point Completion Network
  2 Aug 2018 5 repositories listed Syntology ran 1 of 10 samples · 9 unverified
  Shape completion, the problem of estimating the complete geometry of objects from partial observations, lies at the core of many vision and robotics applications.
• SPCNet: Stepwise Point Cloud Completion Network
  5 Sep 2022 4 repositories listed
  We propose a novel stepwise point cloud completion network (SPCNet) for various 3D models with large missings.
• AtlasNet: A Papier-Mâché Approach to Learning 3D Surface Generation
  15 Feb 2018 3 repositories listed Syntology ran 3 of 3 samples · 0 unverified · 3 pointer-only (licence)
  We introduce a method for learning to generate the surface of 3D shapes.
• Efficient and Scalable Point Cloud Generation with Sparse Point-Voxel Diffusion Models
  12 Aug 2024 2 repositories listed
  Our fastest variant outperforms all non-diffusion generative approaches on unconditional shape generation, the most popular benchmark for evaluating point cloud generative models, while our largest model achieves…
• Learning Geometric Transformation for Point Cloud Completion
  8 Jun 2023 2 repositories listed
  It exploits the repetitive geometric structures in common 3D objects to recover the complete shapes, which contains three sub-networks: geometric patch network, structure transformation network, and detail refinement…
• 3DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Models
  26 Jan 2023 2 repositories listed Syntology ran 8 of 11 samples · 3 unverified
  We introduce 3DShape2VecSet, a novel shape representation for neural fields designed for generative diffusion models.
• Multi-View Partial (MVP) Point Cloud Challenge 2021 on Completion and Registration: Methods and Results
  22 Dec 2021 2 repositories listed Syntology ran 5 of 16 samples · 11 unverified
  Based on the MVP dataset, this paper reports methods and results in the Multi-View Partial Point Cloud Challenge 2021 on Completion and Registration.
• KTNet: Knowledge Transfer for Unpaired 3D Shape Completion
  23 Nov 2021 2 repositories listed
  The student network takes the incomplete one as input and restores the corresponding complete shape.
• SnowflakeNet: Point Cloud Completion by Snowflake Point Deconvolution with Skip-Transformer
  10 Aug 2021 2 repositories listed Syntology ran 8 of 16 samples · 8 unverified
  However, previous methods usually suffered from discrete nature of point cloud and unstructured prediction of points in local regions, which makes it hard to reveal fine local geometric details on the complete shape.
• Refinement of Predicted Missing Parts Enhance Point Cloud Completion
  8 Oct 2020 2 repositories listed
  This paper proposes an end-to-end neural network architecture that focuses on computing the missing geometry and merging the known input and the predicted point cloud.
• PF-Net: Point Fractal Network for 3D Point Cloud Completion
  1 Mar 2020 2 repositories listed Syntology ran 3 of 4 samples · 1 unverified
  Unlike existing point cloud completion networks, which generate the overall shape of the point cloud from the incomplete point cloud and always change existing points and encounter noise and geometrical loss, PF-Net…
• Morphing and Sampling Network for Dense Point Cloud Completion
  30 Nov 2019 2 repositories listed Syntology ran 2 of 6 samples · 4 unverified
  3D point cloud completion, the task of inferring the complete geometric shape from a partial point cloud, has been attracting attention in the community.
• Unpaired Point Cloud Completion on Real Scans using Adversarial Training
  29 Mar 2019 2 repositories listed Syntology ran 1 of 1 samples · 0 unverified · 1 pointer-only (licence)
  As 3D scanning solutions become increasingly popular, several deep learning setups have been developed geared towards that task of scan completion, i.
• Leveraging Automatic CAD Annotations for Supervised Learning in 3D Scene Understanding
  18 Apr 2025 1 repository listed
  High-level 3D scene understanding is essential in many applications.
• SymmCompletion: High-Fidelity and High-Consistency Point Cloud Completion with Symmetry Guidance
  23 Mar 2025 1 repository listed
  Second, SGFormer leverages the geometric features of partial-missing pairs as the explicit symmetric guidance that can constrain the refinement process for initial point clouds.
• Parametric Point Cloud Completion for Polygonal Surface Reconstruction
  11 Mar 2025 1 repository listed Syntology ran 1 of 18 samples · 17 unverified
  Existing polygonal surface reconstruction methods heavily depend on input completeness and struggle with incomplete point clouds.
• DDEQs: Distributional Deep Equilibrium Models through Wasserstein Gradient Flows
  3 Mar 2025 1 repository listed
  Deep Equilibrium Models (DEQs) are a class of implicit neural networks that solve for a fixed point of a neural network in their forward pass.
• PointSea: Point Cloud Completion via Self-structure Augmentation
  24 Feb 2025 1 repository listed
  To reconstruct a compact global shape from the cross-modal input, we incorporate a feature fusion module to fuse features at both intra-view and inter-view levels.
• DAPoinTr: Domain Adaptive Point Transformer for Point Cloud Completion
  26 Dec 2024 1 repository listed
  To this end, we propose a pioneering Domain Adaptive Point Transformer (DAPoinTr) framework for point cloud completion.
• Digging into Intrinsic Contextual Information for High-fidelity 3D Point Cloud Completion
  11 Dec 2024 1 repository listed
  Existing PCC methods typically produce complete point clouds from partial point clouds in a coarse-to-fine paradigm, with the coarse stage generating entire shapes and the fine stage improving texture details.
• PointCFormer: a Relation-based Progressive Feature Extraction Network for Point Cloud Completion
  11 Dec 2024 1 repository listed
  Starting with a denser sampling of points as input, it iteratively queries long-distance global dependencies and local neighborhood relationships.
• SPAC-Net: Rethinking Point Cloud Completion with Structural Prior
  22 Nov 2024 1 repository listed
  Point cloud completion aims to infer a complete shape from its partial observation.
• PocoLoco: A Point Cloud Diffusion Model of Human Shape in Loose Clothing
  6 Nov 2024 1 repository listed
  We motivate our work by noting that most methods require a parametric model of the human body to ground pose-dependent deformations.
• CF-PRNet: Coarse-to-Fine Prototype Refining Network for Point Cloud Completion and Reconstruction
  13 Sep 2024 1 repository listed
  In modern agriculture, precise monitoring of plants and fruits is crucial for tasks such as high-throughput phenotyping and automated harvesting.
• Loss Distillation via Gradient Matching for Point Cloud Completion with Weighted Chamfer Distance
  10 Sep 2024 1 repository listed Syntology ran 8 of 10 samples · 2 unverified
  To this end, we propose a search scheme, {\em Loss Distillation via Gradient Matching}, to find good candidate loss functions by mimicking the learning behavior in backpropagation between HyperCD and weighted CD.
• GeoFormer: Learning Point Cloud Completion with Tri-Plane Integrated Transformer
  13 Aug 2024 1 repository listed
  In this paper, we introduce a GeoFormer that simultaneously enhances the global geometric structure of the points and improves the local details.
• Self-supervised 3D Point Cloud Completion via Multi-view Adversarial Learning
  13 Jul 2024 1 repository listed
  Additionally, we render the reconstructed complete shape into multi-view depth maps and design an adversarial learning module to learn the geometry of the target shape from category-specific single-view depth images.
• T-CorresNet: Template Guided 3D Point Cloud Completion with Correspondence Pooling Query Generation Strategy
  6 Jul 2024 1 repository listed
  Finally, we generate the complete point cloud with a FoldingNet following the coarse-to-fine paradigm, according to the fine template and the predicted point proxies.
• Explicitly Guided Information Interaction Network for Cross-modal Point Cloud Completion
  3 Jul 2024 1 repository listed Syntology ran 5 of 10 samples · 5 unverified
  In this paper, we explore a novel framework, EGIInet (Explicitly Guided Information Interaction Network), a model for View-guided Point cloud Completion (ViPC) task, which aims to restore a complete point cloud from a…

Syntology lines on 12 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.