Self-Supervised Implicit Attention Priors for Point Cloud Reconstruction

• URL: http://arxiv.org/abs/2511.04864v2
• Date: Thu, 13 Nov 2025 01:57:06 GMT
• Title: Self-Supervised Implicit Attention Priors for Point Cloud Reconstruction
• Authors: Kyle Fogarty, Chenyue Cai, Jing Yang, Zhilin Guo, Cengiz Öztireli,
• Abstract summary: We introduce an implicit self-prior approach that distills a shape-specific prior directly from the input point cloud itself.<n>We show this hybrid strategy preserves fine geometric details in the input data, while leveraging the learned prior to regularize sparse regions.
• Score: 7.652381699040464
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recovering high-quality surfaces from irregular point cloud is ill-posed unless strong geometric priors are available. We introduce an implicit self-prior approach that distills a shape-specific prior directly from the input point cloud itself and embeds it within an implicit neural representation. This is achieved by jointly training a small dictionary of learnable embeddings with an implicit distance field; at every query location, the field attends to the dictionary via cross-attention, enabling the network to capture and reuse repeating structures and long-range correlations inherent to the shape. Optimized solely with self-supervised point cloud reconstruction losses, our approach requires no external training data. To effectively integrate this learned prior while preserving input fidelity, the trained field is then sampled to extract densely distributed points and analytic normals via automatic differentiation. We integrate the resulting dense point cloud and corresponding normals into a robust implicit moving least squares (RIMLS) formulation. We show this hybrid strategy preserves fine geometric details in the input data, while leveraging the learned prior to regularize sparse regions. Experiments show that our method outperforms both classical and learning-based approaches in generating high-fidelity surfaces with superior detail preservation and robustness to common data degradations.

Related papers

• DiffCom: Decoupled Sparse Priors Guided Diffusion Compression for Point Clouds [54.96190721255167]
  Lossy compression relies on an autoencoder to transform a point cloud into latent points for storage.<n>We propose a diffusion-based framework guided by sparse priors that achieves high reconstruction quality, especially at lows.
  arXiv  Detail & Related papers  (2024-11-21T05:41:35Z)
• Deep Loss Convexification for Learning Iterative Models [11.36644967267829]
  Iterative methods such as iterative closest point (ICP) for point cloud registration often suffer from bad local optimality. We propose learning to form a convex landscape around each ground truth.
  arXiv  Detail & Related papers  (2024-11-16T01:13:04Z)
• Robustifying Generalizable Implicit Shape Networks with a Tunable Non-Parametric Model [10.316008740970037]
  Generalizable models for implicit shape reconstruction from unoriented point cloud suffer from generalization issues. We propose here an efficient mechanism to remedy some of these limitations at test time. We demonstrate the improvement obtained through our method with respect to baselines and the state-of-the-art using synthetic and real data.
  arXiv  Detail & Related papers  (2023-11-21T20:12:29Z)
• Unsupervised Inference of Signed Distance Functions from Single Sparse Point Clouds without Learning Priors [54.966603013209685]
  It is vital to infer signed distance functions (SDFs) from 3D point clouds. We present a neural network to directly infer SDFs from single sparse point clouds.
  arXiv  Detail & Related papers  (2023-03-25T15:56:50Z)
• Self-Supervised Arbitrary-Scale Point Clouds Upsampling via Implicit Neural Representation [79.60988242843437]
  We propose a novel approach that achieves self-supervised and magnification-flexible point clouds upsampling simultaneously. Experimental results demonstrate that our self-supervised learning based scheme achieves competitive or even better performance than supervised learning based state-of-the-art methods.
  arXiv  Detail & Related papers  (2022-04-18T07:18:25Z)
• Upsampling Autoencoder for Self-Supervised Point Cloud Learning [11.19408173558718]
  We propose a self-supervised pretraining model for point cloud learning without human annotations. Upsampling operation encourages the network to capture both high-level semantic information and low-level geometric information of the point cloud. We find that our UAE outperforms previous state-of-the-art methods in shape classification, part segmentation and point cloud upsampling tasks.
  arXiv  Detail & Related papers  (2022-03-21T07:20:37Z)
• SPU-Net: Self-Supervised Point Cloud Upsampling by Coarse-to-Fine Reconstruction with Self-Projection Optimization [52.20602782690776]
  It is expensive and tedious to obtain large scale paired sparse-canned point sets for training from real scanned sparse data. We propose a self-supervised point cloud upsampling network, named SPU-Net, to capture the inherent upsampling patterns of points lying on the underlying object surface. We conduct various experiments on both synthetic and real-scanned datasets, and the results demonstrate that we achieve comparable performance to the state-of-the-art supervised methods.
  arXiv  Detail & Related papers  (2020-12-08T14:14:09Z)
• Deep Magnification-Flexible Upsampling over 3D Point Clouds [103.09504572409449]
  We propose a novel end-to-end learning-based framework to generate dense point clouds. We first formulate the problem explicitly, which boils down to determining the weights and high-order approximation errors. Then, we design a lightweight neural network to adaptively learn unified and sorted weights as well as the high-order refinements.
  arXiv  Detail & Related papers  (2020-11-25T14:00:18Z)
• Meshing Point Clouds with Predicted Intrinsic-Extrinsic Ratio Guidance [30.863194319818223]
  We propose to leverage the input point cloud as much as possible, by only adding connectivity information to existing points. Our key innovation is a surrogate of local connectivity, calculated by comparing the intrinsic/extrinsic metrics. We demonstrate that our method can not only preserve details, handle ambiguous structures, but also possess strong generalizability to unseen categories.
  arXiv  Detail & Related papers  (2020-07-17T22:36:00Z)
• Point2Mesh: A Self-Prior for Deformable Meshes [83.31236364265403]
  We introduce Point2Mesh, a technique for reconstructing a surface mesh from an input point cloud. The self-prior encapsulates reoccurring geometric repetitions from a single shape within the weights of a deep neural network. We show that Point2Mesh converges to a desirable solution; compared to a prescribed smoothness prior, which often becomes trapped in undesirable local minima.
  arXiv  Detail & Related papers  (2020-05-22T10:01:04Z)

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.