3D Shape Modeling and Analysis

Latest papers

• Resolution-free neural surrogates for geometric parameterization and mapping with spatially varying fields

  Yanwen Huang, Lok Ming Lui, Gary P. T. Choi · 28 May 2026

  Many imaging problems require computing spatial transformations induced by spatially varying intensity, feature, or density fields. Canonical examples include distortion correction, deformable image registration, atlas-based segmentation, and deformation-driven image analysis. These tasks can be for…

• MUSE: Benchmarking Manufacturable, Functional, and Assemblable Text-to-CAD Generation

  Xiaoyu Dong, Zhi Li, Xiao-Ming Wu · 28 May 2026

  Large language models (LLMs) have recently advanced text-driven 3D generation, yet Text-to-CAD remains far from supporting industrial product design. Existing benchmarks focus primarily on generating single-part CAD models and evaluate them using geometric similarity metrics that fail to capture fun…

• CubePart: An Open-Vocabulary Part-Controllable 3D Generator

  Yiheng Zhu, Kangle Deng, Jean-Philippe Fauconnier, Inaki Navarro, Daiqing Li, Ava Pun, Yinan Zhang, Peiye Zhuang, Xiaoxia Sun, Maneesh Agrawala, Kiran Bhat, Tinghui Zhou · 28 May 2026

  Interactive 3D assets used in games and simulation are typically decomposed into specific semantic parts to support animation, physics, and scripted behaviors, yet most generative 3D models produce either monolithic meshes or arbitrary part decompositions that cannot be aligned with application-spec…

• BrickAnything: Geometry-Conditioned Buildable Brick Generation with Structure-Aware Tokenization

  Zhengyang Ni, Feng Yan, Yu Guo, Fei Wang · 27 May 2026

  Generating physically buildable brick structures from 3D shapes requires more than geometric reconstruction: the output must also satisfy discrete part constraints and structural stability. Existing brick generation methods either rely on heuristic optimization, which can break down when the target …

• Learning Laplacian Eigenspace with Mass-Aware Neural Operators on Point Clouds

  Zherui Yang, Tao Du, Ligang Liu · 26 May 2026

  The eigendecomposition of the Laplace--Beltrami Operator (LBO) is fundamental to geometric analysis, yet computing its low-frequency eigenmodes remains a significant bottleneck due to the high cost of iterative solvers on large-scale data. To amortize this cost, we introduce the Neural Eigenspace Op…

• GIBLy: Improving 3D Semantic Segmentation through an Architecture-Agnostic Lightweight Geometric Inductive Bias Layer

  Diogo Lavado, Alessandra Micheletti, Cl\`audia Soares · 26 May 2026

  In 3D scene understanding, deep learning models rely on large models and extensive training to capture basic geometric structures that are present in the 3D data. However, existing methods lack explicit mechanisms to incorporate geometric information, such as learnable primitive shapes, often necess…

• PQDT: Pseudo-Query Dual Transformer for Robust Point Cloud Restoration

  Haoqing Wu, Alexa Nawotki, Jochen Garcke · 26 May 2026

  Point clouds are a fundamental 3D representation in computer vision, enabling a wide range of perception tasks. However, real-world point clouds often suffer from degradations such as incompleteness, noise, outliers, and irregular density, caused by sensor limitations or occlusions. Recovering clean…

• Good Token Hunting: A Hitchhiker's Guide to Token Selection for Visual Geometry Transformers

  Shuhong Zheng, Michael Oechsle, Erik Sandstr\"om, Marie-Julie Rakotosaona, Federico Tombari, Igor Gilitschenski · 25 May 2026

  Visual geometry transformers have become powerful architectures for multi-view 3D reconstruction, enabling joint prediction of multiple 3D attributes in a feed-forward manner. However, their computational cost grows quadratically with the input sequence length due to the global attention layers insi…

• Good Token Hunting: A Hitchhiker's Guide to Token Selection for Visual Geometry Transformers

  Shuhong Zheng, Michael Oechsle, Erik Sandstr\"om, Marie-Julie Rakotosaona, Federico Tombari, Igor Gilitschenski · 25 May 2026

  Visual geometry transformers have become powerful architectures for multi-view 3D reconstruction, enabling joint prediction of multiple 3D attributes in a feed-forward manner. However, their computational cost grows quadratically with the input sequence length due to the global attention layers insi…

• Learning Structural Latent Points for Efficient Visual Representations in Robotic Manipulation

  Yicheng Jiang, Jiaxu Wang, Junhao He, Zesen Gan, Junhao Li, Qiang Zhang, Jingkai Sun, Jiahang Cao, Mingyuan Sun, Xiangyu Yue, Qiming Shao · 22 May 2026

  Current 3D-aware pretraining methods for embodied perception and manipulation are largely built on differentiable rendering frameworks, producing either fully implicit neural fields or fully explicit geometric primitives. Implicit representations, while expressive, lack explicit structural cues, whe…

• Tool-Augmented Agent for Closed-loop Optimization,Simulation,and Modeling Orchestration

  Liyuan Deng, Shujian Deng, Yongkang Chen, Yongkang Dai, Zhihang Zhong, Linyang Li, Xiao Sun, Yilei Shi, Huaxi Huang · 22 May 2026

  Iterative industrial design-simulation optimization is bottlenecked by the CAD-CAE semantic gap: translating simulation feedback into valid geometric edits under diverse, coupled constraints. To fill this gap, we propose COSMO-Agent (Closed-loop Optimization, Simulation, and Modeling Orchestration),…

• PolycubeNet: A Dual-latent Diffusion Model for Polycube-Based Hexahedral Mesh Generation

  Lu He, Qitao Deng, Junjiang Deng, Liangbin Deng, Yanjun Liang, Wenting Yang, Guoqiang Wang, Na Lei · 22 May 2026

  Hexahedral meshes are widely used in simulation pipelines, yet automatic generation remains challenging for complex CAD geometries. Polycube-based hexahedral meshing is a representative approach due to its regular, parameterization-friendly structure, but existing polycube construction methods often…

• VGGT-Edit: Feed-forward Native 3D Scene Editing with Residual Field Prediction

  Kaixin Zhu, Yiwen Tang, Yifan Yang, Renrui Zhang, Bohan Zeng, Ziyu Guo, Ruichuan An, Zhou Liu, Qizhi Chen, Delin Qu, Jaehong Yoon, Wentao Zhang · 20 May 2026

  High-quality 3D scene reconstruction has recently advanced toward generalizable feed-forward architectures, enabling the generation of complex environments in a single forward pass. However, despite their strong performance in static scene perception, these models remain limited in responding to dyn…

• Mat\'ern Noise for Triangulation-Agnostic Flow Matching on Meshes

  Tianshu Kuai, Arman Maesumi, Daniel Ritchie, Noam Aigerman · 20 May 2026

  This paper tackles the task of learning to generate signals over triangle meshes in a triangulation-agnostic manner, meaning the trained model can be applied to different meshes and triangulations effectively. Practically, the paper adapts the flow matching (FM) paradigm to a mesh-based, triangulati…

• SceneCode: Executable World Programs for Editable Indoor Scenes with Articulated Objects

  Puyi Wang, Yuhao Wang, Linjie Li, Zhengyuan Yang, Kevin Qinghong Lin, Yangguang Li, Yu Cheng · 20 May 2026

  Indoor scene synthesis underpins embodied AI, robotic manipulation, and simulation-based policy evaluation, where a useful scene must specify not only what the environment looks like, but also how its objects are structured. Existing pipelines, however, typically represent generated content as stati…

• CompoSE: Compositional Synthesis and Editing of 3D Shapes via Part-Aware Control

  Habib Slim, Shariq Farooq Bhat, Mohamed Elhoseiny, Yifan Wang, Mike Roberts · 20 May 2026

  Creating and editing high-quality 3D content remains a central challenge in computer graphics. We address this challenge by introducing CompoSE, a novel method for Compositional Synthesis and Editing of 3D shapes via part-aware control. Our method takes as input a set of coarse geometric primitives …

• Patchwork: A compact representation for 3D polygonal shapes

  Ruichen Zheng, Biao Zhang, Michael Birsak, Mikhail Skopenkov, Peter Wonka · 19 May 2026

  We introduce Patchwork, a new general-purpose shape representation capable of modeling 2D and 3D geometry with a small number of parameters. Patchwork is grounded in a rigorous mathematical framework, providing provable complexity bounds and the ability to approximate arbitrary shapes with arbitrary…

• Dynamic robotic cloth folding with efficient Koopman operator-based model predictive control

  Edoardo Caldarelli, Franco Coltraro, Adri\`a Colom\'e, Lorenzo Rosasco, Carme Torras · 19 May 2026

  Robotic cloth folding is a challenging task, particularly when considering dynamic folding tasks, which aim at folding cloth by fast motions that leverage its dynamics. When subject to such fast motions, the complexity of cloth dynamics hinders both system identification and planning of folding traj…

• Text2CAD-Bench: A Benchmark for LLM-based Text-to-Parametric CAD Generation

  Liang Wang, Heng Meng, Zekai Xiang, Jin Liu, Pingyi Zhou, Litao Chen, Yongqiang Tang · 19 May 2026

  Text-to-CAD generation aims to create parametric CAD models from natural language, enabling rapid prototyping and intuitive design workflows. However, existing benchmarks focus on basic primitives and simple sketch-extrude sequences, lacking advanced features essential for real-world applications an…

• Predicting 3D structure by latent posterior sampling

  Azmi Haider, Dan Rosenbaum · 19 May 2026

  The remarkable achievements of both generative models of 2D images and neural field representations for 3D scenes present a compelling opportunity to integrate the strengths of both approaches. In this work, we propose a methodology that combines a NeRF-based representation of 3D scenes with probabi…

• A Systematic Survey on Deep Learning Architectures for Point Cloud Classification and Segmentation

  Minhas Kamal, Hiranya Garbha Kumar, Balakrishnan Prabhakaran · 19 May 2026

  Point cloud stands as the most widely adopted format for representing 3D shapes and scenes due to its simplicity and geometric fidelity. However, its inherent unordered and irregular nature, exacerbated by sensor noise and occlusions, introduces unique challenges for machine learning based methodolo…

• Robust Prior-Guided Segmentation for Editable 3D Gaussian Splatting

  Raushan Joshi, Jean-Yves Guillemaut · 18 May 2026

  3D Gaussian Splatting (3D-GS) enables real-time 3D scene reconstruction but lacks robust segmentation for editing tasks such as object removal, extraction, and recoloring. Existing approaches that lift 2D segmentations to the 3D domain suffer from view inconsistencies and coarse masks. In this paper…

• IVGT: Implicit Visual Geometry Transformer for Neural Scene Representation

  Yuqi Wu, Tianyu Hu, Wenzhao Zheng, Yuanhui Huang, Haowen Sun, Jie Zhou, Jiwen Lu · 18 May 2026

  Reconstructing coherent 3D geometry and appearance from unposed multi-view images is a fundamental yet challenging problem in computer vision. Most existing visual geometry foundation models predict explicit geometry by regressing pixel-aligned pointmaps, often suffering from redundancy and limited …

• Discretizing Group-Convolutional Neural Networks for 3D Geometry in Feature Space

  Daniel Franzen, Jean Philip Filling, Michael Wand · 18 May 2026

  Group-convolutional neural networks (GCNNs) are among the most important methods for introducing symmetry as an inductive bias in deep learning: In each linear layer, GCNNs sample a transformation group $G$ densely and correlate data and filters in different poses (with suitable anti-aliasing for st…

• CM-EVS: Sparse Panoramic RGB-D-Pose Data for Complete Scene Coverage

  Jiale Liu, Jungang Li, Jieming Yu, Xinglin Yu, Zihao Dongfang, Zongjian Ding, Kaifeng Ding, Yi Yang, Lidong Chen, Yang Zou, Shunwen Bai, Jiahuan Zhang, Haoran Huang, Shan Huang, Yudong Gao, Mingjun Cheng · 18 May 2026

  Modern 3D visual learning relies on observations sampled from metric 3D assets, yet existing scans, meshes, point clouds, simulations, and reconstructions do not directly provide a sparse, comparable, and geometry-consistent panoramic training interface. Dense trajectories duplicate nearby views, so…