PointNSP: Autoregressive 3D Point Cloud Generation with Next-Scale Level-of-Detail Prediction

• URL: http://arxiv.org/abs/2510.05613v1
• Date: Tue, 07 Oct 2025 06:31:02 GMT
• Title: PointNSP: Autoregressive 3D Point Cloud Generation with Next-Scale Level-of-Detail Prediction
• Authors: Ziqiao Meng, Qichao Wang, Zhiyang Dou, Zixing Song, Zhipeng Zhou, Irwin King, Peilin Zhao,
• Abstract summary: 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.
• Score: 87.33016661440202
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Autoregressive point cloud generation has long lagged behind diffusion-based approaches in quality. The performance gap stems from the fact that autoregressive models impose an artificial ordering on inherently unordered point sets, forcing shape generation to proceed as a sequence of local predictions. This sequential bias emphasizes short-range continuity but undermines the model's capacity to capture long-range dependencies, hindering its ability to enforce global structural properties such as symmetry, consistent topology, and large-scale geometric regularities. Inspired by the level-of-detail (LOD) principle in shape modeling, we propose PointNSP, a coarse-to-fine generative framework that preserves global shape structure at low resolutions and progressively refines fine-grained geometry at higher scales through a next-scale prediction paradigm. This multi-scale factorization aligns the autoregressive objective with the permutation-invariant nature of point sets, enabling rich intra-scale interactions while avoiding brittle fixed orderings. Experiments on ShapeNet show that PointNSP establishes state-of-the-art (SOTA) generation quality for the first time within the autoregressive paradigm. In addition, it surpasses strong diffusion-based baselines in parameter, training, and inference efficiency. Finally, in dense generation with 8,192 points, PointNSP's advantages become even more pronounced, underscoring its scalability potential.

Related papers

• Variational Bayesian Flow Network for Graph Generation [54.94088904387278]
  We propose Variational Bayesian Flow Network (VBFN) for graph generation.<n>VBFN performs variational lifting to a tractable joint Gaussian variational belief family governed by structured precisions.<n>On synthetic and molecular graph datasets, VBFN improves fidelity and diversity, and surpasses baseline methods.
  arXiv  Detail & Related papers  (2026-01-30T03:59:38Z)
• Lotus-2: Advancing Geometric Dense Prediction with Powerful Image Generative Model [32.831576387973875]
  We propose a two-stage deterministic framework for stable, accurate and fine-grained geometric dense prediction.<n>Specifically, in the first stage, the core predictor employs a single-step deterministic formulation with a clean-data objective.<n>In the second stage, the detail sharpener performs a constrained multi-step rectified-flow refinement within the manifold defined by the core predictor.
  arXiv  Detail & Related papers  (2025-11-30T18:57:25Z)
• Simba: Towards High-Fidelity and Geometrically-Consistent Point Cloud Completion via Transformation Diffusion [31.34032485865941]
  We introduce Simba, a novel framework that reformulates point-wise transformation regression as a distribution learning problem.<n>Our approach integrates symmetry priors with the powerful generative capabilities of diffusion models, avoiding instance-specific memorization.
  arXiv  Detail & Related papers  (2025-11-20T09:02:42Z)
• Barycentric Neural Networks and Length-Weighted Persistent Entropy Loss: A Green Geometric and Topological Framework for Function Approximation [0.0]
  A new type of small shallow neural network, called the Barycentric Neural Network (BNN), is proposed.<n>Our framework, which combines the BNN with a loss function based on our LWPE, aims to provide flexible and geometrically interpretable approximations of nonlinear continuous functions.
  arXiv  Detail & Related papers  (2025-09-08T13:47:21Z)
• Towards Efficient General Feature Prediction in Masked Skeleton Modeling [59.46799426434277]
  We propose a novel General Feature Prediction framework (GFP) for efficient mask skeleton modeling.<n>Our key innovation is replacing conventional low-level reconstruction with high-level feature prediction that spans from local motion patterns to global semantic representations.
  arXiv  Detail & Related papers  (2025-09-03T18:05:02Z)
• 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)
• Mitigating Barren Plateaus in Quantum Neural Networks via an AI-Driven Submartingale-Based Framework [3.0617189749929348]
  We propose AdaInit to mitigate barren plateaus (BPs) in quantum neural networks (QNNs)<n>AdaInit iteratively synthesizes initial parameters for QNNs that yield non-negligible gradient variance, thereby mitigating BPs.<n>We provide rigorous theoretical analyses of the submartingale-based process and empirically validate that AdaInit consistently outperforms existing methods in maintaining higher gradient variance across various QNN scales.
  arXiv  Detail & Related papers  (2025-02-17T05:57:15Z)
• Geometric Neural Process Fields [58.77241763774756]
  Geometric Neural Process Fields (G-NPF) is a probabilistic framework for neural radiance fields that explicitly captures uncertainty.<n>Building on these bases, we design a hierarchical latent variable model, allowing G-NPF to integrate structural information across multiple spatial levels.<n> Experiments on novel-view synthesis for 3D scenes, as well as 2D image and 1D signal regression, demonstrate the effectiveness of our method.
  arXiv  Detail & Related papers  (2025-02-04T14:17:18Z)
• Point Cloud Pre-training with Diffusion Models [62.12279263217138]
  We propose a novel pre-training method called Point cloud Diffusion pre-training (PointDif) PointDif achieves substantial improvement across various real-world datasets for diverse downstream tasks such as classification, segmentation and detection.
  arXiv  Detail & Related papers  (2023-11-25T08:10:05Z)
• Second-order regression models exhibit progressive sharpening to the edge of stability [30.92413051155244]
  We show that for quadratic objectives in two dimensions, a second-order regression model exhibits progressive sharpening towards a value that differs slightly from the edge of stability. In higher dimensions, the model generically shows similar behavior, even without the specific structure of a neural network.
  arXiv  Detail & Related papers  (2022-10-10T17:21:20Z)
• On the Impact of Stable Ranks in Deep Nets [3.307203784120635]
  We show that stable ranks appear layerwise essentially as linear factors whose effect accumulates exponentially depthwise. Our results imply that stable ranks appear layerwise essentially as linear factors whose effect accumulates exponentially depthwise.
  arXiv  Detail & Related papers  (2021-10-05T20:04:41Z)
• PU-Flow: a Point Cloud Upsampling Networkwith Normalizing Flows [58.96306192736593]
  We present PU-Flow, which incorporates normalizing flows and feature techniques to produce dense points uniformly distributed on the underlying surface. Specifically, we formulate the upsampling process as point in a latent space, where the weights are adaptively learned from local geometric context. We show that our method outperforms state-of-the-art deep learning-based approaches in terms of reconstruction quality, proximity-to-surface accuracy, and computation efficiency.
  arXiv  Detail & Related papers  (2021-07-13T07:45:48Z)

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.