3D Shape Modeling and Analysis

Últimos artículos

• POCI-Diff: Position Objects Consistently and Interactively with 3D-Layout Guided Diffusion

  Andrea Rigo, Luca Stornaiuolo, Weijie Wang, Mauro Martino, Bruno Lepri, Nicu Sebe · 21 de enero de 2026

  We propose a diffusion-based approach for Text-to-Image (T2I) generation with consistent and interactive 3D layout control and editing. While prior methods improve spatial adherence using 2D cues or iterative copy-warp-paste strategies, they often distort object geometry and fail to preserve consist…

• Proc3D: Procedural 3D Generation and Parametric Editing of 3D Shapes with Large Language Models

  Fadlullah Raji, Stefano Petrangeli, Matheus Gadelha, Yu Shen, Uttaran Bhattacharya, Gang Wu · 21 de enero de 2026

  Generating 3D models has traditionally been a complex task requiring specialized expertise. While recent advances in generative AI have sought to automate this process, existing methods produce non-editable representation, such as meshes or point clouds, limiting their adaptability for iterative des…

• Autoregressive deep learning for real-time simulation of soft tissue dynamics during virtual neurosurgery

  Fabian Greifeneder, Wolfgang Fenz, Benedikt Alkin, Johannes Brandstetter, Michael Giretzlehner, Philipp Moser · 21 de enero de 2026

  Accurate simulation of brain deformation is a key component for developing realistic, interactive neurosurgical simulators, as complex nonlinear deformations must be captured to ensure realistic tool-tissue interactions. However, traditional numerical solvers often fall short in meeting real-time pe…

• ShapeR: Robust Conditional 3D Shape Generation from Casual Captures

  Yawar Siddiqui, Duncan Frost, Samir Aroudj, Armen Avetisyan, Henry Howard-Jenkins, Daniel DeTone, Pierre Moulon, Qirui Wu, Zhengqin Li, Julian Straub, Richard Newcombe, Jakob Engel · 19 de enero de 2026

  Recent advances in 3D shape generation have achieved impressive results, but most existing methods rely on clean, unoccluded, and well-segmented inputs. Such conditions are rarely met in real-world scenarios. We present ShapeR, a novel approach for conditional 3D object shape generation from casuall…

• X-SAM: Boosting Sharpness-Aware Minimization with Dominant-Eigenvector Gradient Correction

  Hongru Duan, Yongle Chen, Lei Guan · 16 de enero de 2026

  Sharpness-Aware Minimization (SAM) aims to improve generalization by minimizing a worst-case perturbed loss over a small neighborhood of model parameters. However, during training, its optimization behavior does not always align with theoretical expectations, since both sharp and flat regions may yi…

• LayerGS: Decomposition and Inpainting of Layered 3D Human Avatars via 2D Gaussian Splatting

  Yinghan Xu, John Dingliana · 12 de enero de 2026

  We propose a novel framework for decomposing arbitrarily posed humans into animatable multi-layered 3D human avatars, separating the body and garments. Conventional single-layer reconstruction methods lock clothing to one identity, while prior multi-layer approaches struggle with occluded regions. W…

• Rethinking Multimodal Few-Shot 3D Point Cloud Segmentation: From Fused Refinement to Decoupled Arbitration

  Wentao Bian, Fenglei Xu · 6 de enero de 2026

  In this paper, we revisit multimodal few-shot 3D point cloud semantic segmentation (FS-PCS), identifying a conflict in "Fuse-then-Refine" paradigms: the "Plasticity-Stability Dilemma." In addition, CLIP's inter-class confusion can result in semantic blindness. To address these issues, we present the…

• Federated Customization of Large Models: Approaches, Experiments, and Insights

  Yuchuan Ye, Ming Ding, Youjia Chen, Peng Cheng, Dusit Niyato · 5 de enero de 2026

  In this article, we explore federated customization of large models and highlight the key challenges it poses within the federated learning framework. We review several popular large model customization techniques, including full fine-tuning, efficient fine-tuning, prompt engineering, prefix-tuning,…

• Memorization in 3D Shape Generation: An Empirical Study

  Shu Pu, Boya Zeng, Kaichen Zhou, Mengyu Wang, Zhuang Liu · 30 de diciembre de 2025

  Generative models are increasingly used in 3D vision to synthesize novel shapes, yet it remains unclear whether their generation relies on memorizing training shapes. Understanding their memorization could help prevent training data leakage and improve the diversity of generated results. In this pap…

• HLS4PC: A Parametrizable Framework For Accelerating Point-Based 3D Point Cloud Models on FPGA

  Amur Saqib Pal, Muhammad Mohsin Ghaffar, Faisal Shafait, Christian Weis, Norbert Wehn · 30 de diciembre de 2025

  Point-based 3D point cloud models employ computation and memory intensive mapping functions alongside NN layers for classification/segmentation, and are executed on server-grade GPUs. The sparse, and unstructured nature of 3D point cloud data leads to high memory and computational demand, hindering …

• A Three-Level Alignment Framework for Large-Scale 3D Retrieval and Controlled 4D Generation

  Philip Xu, David Elizondo, Raouf Hamzaoui · 30 de diciembre de 2025

  We introduce Uni4D, a unified framework for large scale open vocabulary 3D retrieval and controlled 4D generation based on structured three level alignment across text, 3D models, and image modalities. Built upon the Align3D 130 dataset, Uni4D employs a 3D text multi head attention and search model …

• CraftMesh: High-Fidelity Generative Mesh Manipulation via Poisson Seamless Fusion

  James Jincheng, Yuxiao Wu, Youcheng Cai, Ligang Liu · 30 de diciembre de 2025

  Controllable, high-fidelity mesh editing remains a significant challenge in 3D content creation. Existing generative methods often struggle with complex geometries and fail to produce detailed results. We propose CraftMesh, a novel framework for high-fidelity generative mesh manipulation via Poisson…

• BertsWin: Resolving Topological Sparsity in 3D Masked Autoencoders via Component-Balanced Structural Optimization

  Evgeny Alves Limarenko, Anastasiia Studenikina · 29 de diciembre de 2025

  The application of self-supervised learning (SSL) and Vision Transformers (ViTs) approaches demonstrates promising results in the field of 2D medical imaging, but the use of these methods on 3D volumetric images is fraught with difficulties. Standard Masked Autoencoders (MAE), which are state-of-the…

• Learning to Solve PDEs on Neural Shape Representations

  Lilian Welschinger, Yilin Liu, Zican Wang, Niloy Mitra · 25 de diciembre de 2025

  Solving partial differential equations (PDEs) on shapes underpins many shape analysis and engineering tasks; yet, prevailing PDE solvers operate on polygonal/triangle meshes while modern 3D assets increasingly live as neural representations. This mismatch leaves no suitable method to solve surface P…

• Discovering Lie Groups with Flow Matching

  Jung Yeon Park, Yuxuan Chen, Floor Eijkelboom, Jan-Willem van de Meent, Lawson L. S. Wong, Robin Walters · 24 de diciembre de 2025

  Symmetry is fundamental to understanding physical systems, and at the same time, can improve performance and sample efficiency in machine learning. Both pursuits require knowledge of the underlying symmetries in data. To address this, we propose learning symmetries directly from data via flow matchi…

• From Theory to Throughput: CUDA-Optimized APML for Large-Batch 3D Learning

  Sasan Sharifipour, Constantino \'Alvarez Casado, Manuel Lage Ca\~nellas, Miguel Bordallo L\'opez · 24 de diciembre de 2025

  Loss functions are fundamental to learning accurate 3D point cloud models, yet common choices trade geometric fidelity for computational cost. Chamfer Distance is efficient but permits many-to-one correspondences, while Earth Mover Distance better reflects one-to-one transport at high computational …

• GraphCompNet: A Position-Aware Model for Predicting and Compensating Shape Deviations in 3D Printing

  Juheon Lee (Rachel), Lei (Rachel), Chen, Juan Carlos Catana, Hui Wang, Jun Zeng · 22 de diciembre de 2025

  Shape deviation modeling and compensation in additive manufacturing are pivotal for achieving high geometric accuracy and enabling industrial-scale production. Critical challenges persist, including generalizability across complex geometries and adaptability to position-dependent variations in batch…

• ClothHMR: 3D Mesh Recovery of Humans in Diverse Clothing from Single Image

  Yunqi Gao, Leyuan Liu, Yuhan Li, Changxin Gao, Yuanyuan Liu, Jingying Chen · 22 de diciembre de 2025

  With 3D data rapidly emerging as an important form of multimedia information, 3D human mesh recovery technology has also advanced accordingly. However, current methods mainly focus on handling humans wearing tight clothing and perform poorly when estimating body shapes and poses under diverse clothi…

• Hierarchical Neural Surfaces for 3D Mesh Compression

  Sai Karthikey Pentapati, Gregoire Phillips, Alan Bovik · 19 de diciembre de 2025

  Implicit Neural Representations (INRs) have been demonstrated to achieve state-of-the-art compression of a broad range of modalities such as images, videos, 3D surfaces, and audio. Most studies have focused on building neural counterparts of traditional implicit representations of 3D geometries, suc…

• Mat\'ern Kernels for Tunable Implicit Surface Reconstruction

  Maximilian Weiherer, Bernhard Egger · 19 de diciembre de 2025

  We propose to use the family of Mat\'ern kernels for implicit surface reconstruction, building upon the recent success of kernel methods for 3D reconstruction of oriented point clouds. As we show from a theoretical and practical perspective, Mat\'ern kernels have some appealing properties which make…

• GFLAN: Generative Functional Layouts

  Mohamed Abouagour, Eleftherios Garyfallidis · 19 de diciembre de 2025

  Automated floor plan generation lies at the intersection of combinatorial search, geometric constraint satisfaction, and functional design requirements -- a confluence that has historically resisted a unified computational treatment. While recent deep learning approaches have improved the state of t…

• Rigid-Deformation Decomposition AI Framework for 3D Spatio-Temporal Prediction of Vehicle Collision Dynamics

  Sanghyuk Kim, Minsik Seo, Sunwoong Yang, Namwoo Kang · 18 de diciembre de 2025

  This study presents a rigid-deformation decomposition framework for vehicle collision dynamics that mitigates the spectral bias of implicit neural representations, that is, coordinate-based neural networks that directly map spatio-temporal coordinates to physical fields. We introduce a hierarchical …

• Native and Compact Structured Latents for 3D Generation

  Jianfeng Xiang, Xiaoxue Chen, Sicheng Xu, Ruicheng Wang, Zelong Lv, Yu Deng, Hongyuan Zhu, Yue Dong, Hao Zhao, Nicholas Jing Yuan, Jiaolong Yang · 17 de diciembre de 2025

  Recent advancements in 3D generative modeling have significantly improved the generation realism, yet the field is still hampered by existing representations, which struggle to capture assets with complex topologies and detailed appearance. This paper present an approach for learning a structured la…

• FractalCloud: A Fractal-Inspired Architecture for Efficient Large-Scale Point Cloud Processing

  Yuzhe Fu, Changchun Zhou, Hancheng Ye, Bowen Duan, Qiyu Huang, Chiyue Wei, Cong Guo, Hai "Helen'' Li, Yiran Chen · 16 de diciembre de 2025

  Three-dimensional (3D) point clouds are increasingly used in applications such as autonomous driving, robotics, and virtual reality (VR). Point-based neural networks (PNNs) have demonstrated strong performance in point cloud analysis, originally targeting small-scale inputs. However, as PNNs evolve …

• VoroLight: Learning Quality Volumetric Voronoi Meshes from General Inputs

  Jiayin Lu, Ying Jiang, Yin Yang, Chenfanfu Jiang · 16 de diciembre de 2025

  We present VoroLight, a differentiable framework for 3D shape reconstruction based on Voronoi meshing. Our approach generates smooth, watertight surfaces and topologically consistent volumetric meshes directly from diverse inputs, including images, implicit shape level-set fields, point clouds and m…