Manifold-Aware Point Cloud Completion via Geodesic-Attentive Hierarchical Feature Learning

• URL: http://arxiv.org/abs/2512.05710v1
• Date: Fri, 05 Dec 2025 13:38:35 GMT
• Title: Manifold-Aware Point Cloud Completion via Geodesic-Attentive Hierarchical Feature Learning
• Authors: Jianan Sun, Dongzhihan Wang, Mingyu Fan,
• Abstract summary: We present a manifold-aware point cloud completion framework that explicitly incorporates nonlinear geometry information throughout the feature learning pipeline.<n>Our approach consistently outperforms state-of-the-art methods in reconstruction quality.
• Score: 3.214168764374659
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Point cloud completion seeks to recover geometrically consistent shapes from partial or sparse 3D observations. Although recent methods have achieved reasonable global shape reconstruction, they often rely on Euclidean proximity and overlook the intrinsic nonlinear geometric structure of point clouds, resulting in suboptimal geometric consistency and semantic ambiguity. In this paper, we present a manifold-aware point cloud completion framework that explicitly incorporates nonlinear geometry information throughout the feature learning pipeline. Our approach introduces two key modules: a Geodesic Distance Approximator (GDA), which estimates geodesic distances between points to capture the latent manifold topology, and a Manifold-Aware Feature Extractor (MAFE), which utilizes geodesic-based $k$-NN groupings and a geodesic-relational attention mechanism to guide the hierarchical feature extraction process. By integrating geodesic-aware relational attention, our method promotes semantic coherence and structural fidelity in the reconstructed point clouds. Extensive experiments on benchmark datasets demonstrate that our approach consistently outperforms state-of-the-art methods in reconstruction quality.

Related papers

• Thinking with Geometry: Active Geometry Integration for Spatial Reasoning [68.59084007360615]
  We propose GeoThinker, a framework that shifts paradigm passive fusion to active perception.<n>Instead of feature mixing, GeoThinker enables the model to selectively retrieve geometric evidence conditioned on its internal reasoning demands.<n>Our results indicate that the ability to actively integrate spatial structures is essential for next-generation spatial intelligence.
  arXiv  Detail & Related papers  (2026-02-05T18:59:32Z)
• GeoGNN: Quantifying and Mitigating Semantic Drift in Text-Attributed Graphs [59.61242815508687]
  Graph neural networks (GNNs) on text--attributed graphs (TAGs) encode node texts using pretrained language models (PLMs) and propagate these embeddings through linear neighborhood aggregation.<n>This work introduces a local PCA-based metric that measures the degree of semantic drift and provides the first quantitative framework to analyze how different aggregation mechanisms affect manifold structure.
  arXiv  Detail & Related papers  (2025-11-12T06:48:43Z)
• DFG-PCN: Point Cloud Completion with Degree-Flexible Point Graph [17.079595595415466]
  This paper proposes a point cloud completion framework called Degree-Flexible Point Graph Completion Network (DFG-PCN)<n>It adaptively assigns node degrees using a detail-aware metric that combines feature variation and curvature, focusing on structurally important regions.
  arXiv  Detail & Related papers  (2025-09-28T07:28:42Z)
• Preserving Topological and Geometric Embeddings for Point Cloud Recovery [43.26116605528137]
  We propose an end-to-end architecture named textbfTopGeoFormer, which maintains these critical properties throughout the sampling and restoration phases.<n>In experiments, we comprehensively analyze the circumstances using the conventional and learning-based sampling/up/recovery algorithms.
  arXiv  Detail & Related papers  (2025-07-25T09:58:41Z)
• Latent Manifold Reconstruction and Representation with Topological and Geometrical Regularization [1.8335627278682702]
  We present an AutoEncoder-based method that integrates a manifold reconstruction layer, which uncovers latent manifold structures from noisy point clouds.<n>Experiments on point cloud datasets demonstrate that our method outperforms baselines like t-SNE, UMAP, and Topological AutoEncoders.
  arXiv  Detail & Related papers  (2025-05-07T13:47:22Z)
• (Deep) Generative Geodesics [57.635187092922976]
  We introduce a newian metric to assess the similarity between any two data points. Our metric leads to the conceptual definition of generative distances and generative geodesics. Their approximations are proven to converge to their true values under mild conditions.
  arXiv  Detail & Related papers  (2024-07-15T21:14:02Z)
• DeepBranchTracer: A Generally-Applicable Approach to Curvilinear Structure Reconstruction Using Multi-Feature Learning [12.047523258256088]
  We introduce DeepBranchTracer, a novel method that learns both external image features and internal geometric characteristics to reconstruct curvilinear structures. We extensively evaluated our model on both 2D and 3D datasets, demonstrating its superior performance over existing segmentation and reconstruction methods.
  arXiv  Detail & Related papers  (2024-02-02T07:13:07Z)
• Human as Points: Explicit Point-based 3D Human Reconstruction from Single-view RGB Images [71.91424164693422]
  We introduce an explicit point-based human reconstruction framework called HaP.<n>Our approach is featured by fully-explicit point cloud estimation, manipulation, generation, and refinement in the 3D geometric space.<n>Our results may indicate a paradigm rollback to the fully-explicit and geometry-centric algorithm design.
  arXiv  Detail & Related papers  (2023-11-06T05:52:29Z)
• Exploring Data Geometry for Continual Learning [64.4358878435983]
  We study continual learning from a novel perspective by exploring data geometry for the non-stationary stream of data. Our method dynamically expands the geometry of the underlying space to match growing geometric structures induced by new data. Experiments show that our method achieves better performance than baseline methods designed in Euclidean space.
  arXiv  Detail & Related papers  (2023-04-08T06:35:25Z)
• GeoUDF: Surface Reconstruction from 3D Point Clouds via Geometry-guided Distance Representation [73.77505964222632]
  We present a learning-based method, namely GeoUDF, to tackle the problem of reconstructing a discrete surface from a sparse point cloud. To be specific, we propose a geometry-guided learning method for UDF and its gradient estimation. To extract triangle meshes from the predicted UDF, we propose a customized edge-based marching cube module.
  arXiv  Detail & Related papers  (2022-11-30T06:02:01Z)
• Improving Semantic Analysis on Point Clouds via Auxiliary Supervision of Local Geometric Priors [34.4685487625487]
  This paper is the first attempt to propose a unique multi-task geometric learning network to improve semantic analysis by auxiliary geometric learning with local shape properties. The proposed geometric self-supervised and privileged learning algorithms can achieve superior performance to their backbones and other state-of-the-art methods.
  arXiv  Detail & Related papers  (2020-01-14T14:33:31Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.