arXiv:2511.16161v1 Announce Type: new 
Abstract: Point cloud completion is a fundamental task in 3D vision. A persistent challenge in this field is simultaneously preserving fine-grained details present in the input while ensuring the global structural integrity of the completed shape. While recent works leveraging local symmetry transformations via direct regression have significantly improved the preservation of geometric structure details, these methods suffer from two major limitations: (1) These regression-based methods are prone to overfitting which tend to memorize instant-specific transformations instead of learning a generalizable geometric prior. (2) Their reliance on point-wise transformation regression lead to high sensitivity to input noise, severely degrading their robustness and generalization. To address these challenges, we introduce Simba, a novel framework that reformulates point-wise transformation regression as a distribution learning problem. Our approach integrates symmetry priors with the powerful generative capabilities of diffusion models, avoiding instance-specific memorization while capturing robust geometric structures. Additionally, we introduce a hierarchical Mamba-based architecture to achieve high-fidelity upsampling. Extensive experiments across the PCN, ShapeNet, and KITTI benchmarks validate our method's state-of-the-art (SOTA) performance.

سيمبا هو إطار جديد يهدف إلى تحسين إكمال سحب النقاط في الرؤية ثلاثية الأبعاد. يتناول التحدي المتمثل في الحفاظ على التفاصيل الدقيقة مع ضمان سلامة الهيكل العام للشكل المكتمل. عانت الأساليب السابقة المعتمدة على الانحدار من مشكلات الإفراط في التكيف والحساسية للضوضاء المدخلة. يعيد سيمبا صياغة انحدار التحويل النقاطي كمشكلة تعلم توزيع، مما يعزز المتانة والتعميم في مهام إكمال سحب النقاط.

Simba es un nuevo marco destinado a mejorar la completación de nubes de puntos en visión 3D. Aborda el desafío de mantener detalles finos mientras asegura la integridad estructural de la forma completada. Los métodos anteriores basados en regresión enfrentaron problemas de sobreajuste y sensibilidad al ruido de entrada. Simba reformula la regresión de transformación punto por punto como un problema de aprendizaje de distribución, mejorando la robustez y la generalización en tareas de completación de nubes de puntos.

Simba est un nouveau cadre visant à améliorer la complétion des nuages de points dans la vision 3D. Il s'attaque au défi de maintenir les détails fins tout en garantissant l'intégrité structurelle de la forme globale. Les méthodes précédentes basées sur la régression ont rencontré des problèmes de surajustement et de sensibilité au bruit d'entrée. Simba reformule la régression de transformation point par point comme un problème d'apprentissage de distribution, améliorant la robustesse et la généralisation dans les tâches de complétion de nuages de points.

Simba is a new framework aimed at improving point cloud completion in 3D vision. It addresses the challenge of maintaining fine details while ensuring the overall shape's structural integrity. Previous regression-based methods struggled with overfitting and sensitivity to input noise. Simba reformulates point-wise transformation regression as a distribution learning problem, enhancing robustness and generalization in point cloud completion tasks.

Simba: Towards High-Fidelity and Geometrically-Consistent Point Cloud Completion via Transformation Diffusion

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.

Simba: Towards High-Fidelity and Geometrically-Consistent Point Cloud Completion via Transformation Diffusion

Was this article worth reading? Share it

Mapfit

Zemith-3bda3b

Deptho.ai