Beyond Defenses: Manifold-Aligned Regularization for Intrinsic 3D Point Cloud Robustness

• URL: http://arxiv.org/abs/2605.07590v1
• Date: Fri, 08 May 2026 11:02:53 GMT
• Title: Beyond Defenses: Manifold-Aligned Regularization for Intrinsic 3D Point Cloud Robustness
• Abstract summary: We develop a geometric interpretation of 3D robustness that links classical adversarial theory to the intrinsic structure of point clouds.<n>Motivated by this analysis, we introduce Manifold-Aligned Point Recognition (MAPR), a framework that regularizes the latent geometry by aligning predictions across intrinsic perturbations.
• Score: 7.747242279123295
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Despite extensive progress in point cloud robustness, existing methods primarily improve performance through augmentation or defense mechanisms, while overlooking the geometric root cause of adversarial fragility. We hypothesize that adversarial vulnerability in 3D networks arises from a manifold misalignment between the latent geometry learned by the model and the intrinsic geometry of the underlying surface. Small, geometry-preserving perturbations along the input manifold often induce disproportionate distortions in feature space, revealing a misalignment between latent and intrinsic geometries. We formalize this phenomenon by developing a geometric interpretation of 3D robustness that links classical adversarial theory to the intrinsic structure of point clouds. Motivated by this analysis, we introduce Manifold-Aligned Point Recognition (MAPR), a framework that regularizes the latent geometry by aligning predictions across intrinsic perturbations. MAPR augments each point cloud with intrinsic features capturing local curvature and diffusion structure, and applies a consistency loss that preserves invariance to intrinsic, geometry-preserving perturbations. Without relying on adversarial training or additional data, MAPR consistently improves robustness across multiple adversarial attacks on both the ModelNet40 and ScanObjectNN datasets, achieving average robustness gains of +20.02% and +8.58% on ModelNet40 and ScanObjectNN, respectively.

Related papers

• Reliability-Aware 3D Geometric Injection for Universal Person Re-identification [47.874819213762926]
  We propose a Universal Monocular 3D-Enhanced ReID framework driven by a Consistency-Aware Reliability Gate and Dual-Stream Residual Fusion.<n>Our method improves challenging, structure-sensitive scenarios while preserving competitive performance on clean domains.
  arXiv  Detail & Related papers  (2026-07-21T08:54:25Z)
• HYPERPOSE: Hyperbolic Kinematic Phase-Space Attention for 3D Human Pose Estimation [0.0]
  HYPERPOSE is a novel 3D human pose estimation framework.<n>It performs Loren-temporal reasoning entirely within the hierarchical tree of the human skeleton.
  arXiv  Detail & Related papers  (2026-05-11T07:17:32Z)
• SpatialEvo: Self-Evolving Spatial Intelligence via Deterministic Geometric Environments [75.60795462502949]
  SpatialEvo is a self-evolving framework for 3D spatial reasoning.<n>It formalizes 16 spatial reasoning task categories under explicit geometric validation rules.<n>It converts unannotated 3D scenes into zero-noise interactive oracles, replacing model consensus with objective physical feedback.
  arXiv  Detail & Related papers  (2026-04-15T17:59:12Z)
• Topo-ADV: Generating Topology-Driven Imperceptible Adversarial Point Clouds [2.475488961586926]
  We introduce the first topology-driven adversarial attack for point cloud deep learning.<n>Our key insight is that the homological structure of a 3D object constitutes a previously unexplored vulnerability surface.<n> Experiments demonstrate that subtle topology-driven perturbations consistently achieve up to 100% attack success rates.
  arXiv  Detail & Related papers  (2026-04-10T20:13:45Z)
• The Geometry of Robustness: Optimizing Loss Landscape Curvature and Feature Manifold Alignment for Robust Finetuning of Vision-Language Models [33.10473765967503]
  Generalization-preserving methods retain ID/OOD performance but leave models vulnerable to adversarial attacks.<n>Our key insight is that the robustness trade-off stems from two geometric failures: sharp, anisotropic minima in parameter space and unstable feature representations that deform under perturbation.<n>We propose GRACE, a unified fine-tuning framework that jointly regularizes the parameter-space curvature and feature-space invariance for VLMs.
  arXiv  Detail & Related papers  (2026-03-28T05:22:00Z)
• 3D-ANC: Adaptive Neural Collapse for Robust 3D Point Cloud Recognition [21.95358957900039]
  We present 3D-ANC, a novel approach that capitalizes on the Neural Collapse (NC) mechanism to orchestrate discriminative feature learning.<n>We show that 3D-ANC significantly improves the robustness of models with various structures on two datasets.
  arXiv  Detail & Related papers  (2025-11-10T12:37:00Z)
• PointNSP: Autoregressive 3D Point Cloud Generation with Next-Scale Level-of-Detail Prediction [87.33016661440202]
  Autoregressive point cloud generation has long lagged behind diffusion-based approaches in quality.<n>We propose PointNSP, a coarse-to-fine generative framework that preserves global shape structure at low resolutions.<n> Experiments on ShapeNet show that PointNSP establishes state-of-the-art (SOTA) generation quality for the first time within the autoregressive paradigm.
  arXiv  Detail & Related papers  (2025-10-07T06:31:02Z)
• Adaptive Point-Prompt Tuning: Fine-Tuning Heterogeneous Foundation Models for 3D Point Cloud Analysis [51.37795317716487]
  We propose the Adaptive Point-Prompt Tuning (APPT) method, which fine-tunes pre-trained models with a modest number of parameters.<n>We convert raw point clouds into point embeddings by aggregating local geometry to capture spatial features followed by linear layers.<n>To calibrate self-attention across source domains of any modality to 3D, we introduce a prompt generator that shares weights with the point embedding module.
  arXiv  Detail & Related papers  (2025-08-30T06:02:21Z)
• Adaptive Dual Uncertainty Optimization: Boosting Monocular 3D Object Detection under Test-Time Shifts [80.32933059529135]
  Test-Time Adaptation (TTA) methods have emerged to adapt to target distributions during inference.<n>We propose Dual Uncertainty Optimization (DUO), the first TTA framework designed to jointly minimize both uncertainties for robust M3OD.<n>In parallel, we design a semantic-aware normal field constraint that preserves geometric coherence in regions with clear semantic cues.
  arXiv  Detail & Related papers  (2025-08-28T07:09:21Z)
• GUPNet++: Geometry Uncertainty Propagation Network for Monocular 3D Object Detection [92.41859045360532]
  We propose a novel Geometry Uncertainty Propagation Network (GUPNet++)<n>It models the uncertainty propagation relationship of the geometry projection during training, improving the stability and efficiency of the end-to-end model learning.<n> Experiments show that the proposed approach not only obtains (state-of-the-art) SOTA performance in image-based monocular 3D detection but also demonstrates superiority in efficacy with a simplified framework.
  arXiv  Detail & Related papers  (2023-10-24T08:45:15Z)
• Ada3Diff: Defending against 3D Adversarial Point Clouds via Adaptive Diffusion [70.60038549155485]
  Deep 3D point cloud models are sensitive to adversarial attacks, which poses threats to safety-critical applications such as autonomous driving. This paper introduces a novel distortion-aware defense framework that can rebuild the pristine data distribution with a tailored intensity estimator and a diffusion model.
  arXiv  Detail & Related papers  (2022-11-29T14:32:43Z)

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.