arXiv:2510.05613v2 Announce Type: replace-cross 
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.

تم تقديم PointNSP كإطار عمل مبتكر للتوليد التلقائي لنقاط السحابة ثلاثية الأبعاد، حيث يعالج القيود التي تواجه النماذج التقليدية التي تكافح لالتقاط الاعتماديات طويلة المدى والخصائص الهيكلية العالمية. تعتمد هذه الطريقة نهجًا من الخشن إلى الدقيق، مما يحسن جودة توليد نقاط السحابة من خلال تحسين الهندسة بشكل تدريجي عند دقة أعلى.

PointNSP se ha presentado como un marco autoregresivo innovador para la generación de nubes de puntos 3D, abordando las limitaciones de los modelos tradicionales que luchan por capturar dependencias a largo plazo y propiedades estructurales globales. Este método emplea un enfoque de grueso a fino, mejorando la calidad de la generación de nubes de puntos al refinar progresivamente la geometría a resoluciones más altas.

PointNSP a été introduit comme un cadre autoregressif innovant pour la génération de nuages de points 3D, abordant les limitations des modèles traditionnels qui peinent à capturer les dépendances à long terme et les propriétés structurelles globales. Cette méthode adopte une approche grossière à fine, améliorant la qualité de la génération de nuages de points en affinant progressivement la géométrie à des résolutions plus élevées.

PointNSP has been introduced as an innovative autoregressive framework for generating 3D point clouds, addressing the limitations of traditional models that struggle with capturing long-range dependencies and global structural properties. This method employs a coarse-to-fine approach, enhancing the quality of point cloud generation by progressively refining geometry at higher resolutions.

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

arXiv:2503.08594v3 Announce Type: replace-cross 
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.

تم تقديم PointNSP كإطار عمل ذاتي الانحدار لتوليد سحب النقاط ثلاثية الأبعاد، حيث يعالج القيود التي تواجه النماذج التقليدية التي تكافح لالتقاط الاعتماديات على المدى الطويل والخصائص الهيكلية العالمية. تستخدم هذه الطريقة المبتكرة إطارًا توليديًا من الخشن إلى الدقيق يحافظ على الهيكل العام للشكل عند الدقة المنخفضة بينما يقوم بتحسين الهندسة الدقيقة عند المقاييس الأعلى.

PointNSP se ha introducido como un marco autorregresivo para la generación de nubes de puntos 3D, abordando las limitaciones de los modelos tradicionales que luchan por capturar dependencias a largo plazo y propiedades estructurales globales. Este enfoque innovador emplea un marco generativo de grueso a fino que preserva la estructura global de la forma a bajas resoluciones mientras refina la geometría detallada a escalas más altas.

PointNSP a été introduit comme un cadre autorégressif pour la génération de nuages de points 3D, abordant les limitations des modèles traditionnels qui peinent à capturer les dépendances à long terme et les propriétés structurelles globales. Cette approche innovante utilise un cadre génératif de grossier à fin qui préserve la structure globale de la forme à basse résolution tout en affinant la géométrie détaillée à des échelles plus élevées.

PointNSP has been introduced as an autoregressive framework for generating 3D point clouds, addressing the limitations of traditional models that struggle with capturing long-range dependencies and global structural properties. This innovative approach employs a coarse-to-fine generative framework that preserves global shape structure at low resolutions while refining fine-grained geometry at higher scales.

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

Was this article worth reading? Share it

Graphite Note

Pixo.art

Blunge