3D Shape Modeling and Analysis

Neueste Paper

• Denoising-GS: Gaussian Splatting with Spatial-aware Denoising

  Qingyuan Zhou, Xinyi Liu, Weidong Yang, Ning Wang, Shuquan Ye, Ben Fei, Ying He, Wanli Ouyang · 15. Mai 2026

  Recent advances in 3D Gaussian Splatting (3DGS) have achieved remarkable success in high-fidelity Novel View Synthesis (NVS), yet the optimization process inevitably introduces noisy Gaussian primitives due to the sparse and incomplete initialization from Structure-from-Motion (SfM) point clouds. Mo…

• R-DMesh: Video-Guided 3D Animation via Rectified Dynamic Mesh Flow

  Zijie Wu, Lixin Xu, Puhua Jiang, Sicong Liu, Chunchao Guo, Xiang Bai · 14. Mai 2026

  Video-guided 3D animation holds immense potential for content creation, offering intuitive and precise control over dynamic assets. However, practical deployment faces a critical yet frequently overlooked hurdle: the pose misalignment dilemma. In real-world scenarios, the initial pose of a user-prov…

• EvObj: Learning Evolving Object-centric Representations for 3D Instance Segmentation without Scene Supervision

  Jiahao Chen, Zihui Zhang, Yafei Yang, Jinxi Li, Shenxing Wei, Zhixuan Sun, Bo Yang · 14. Mai 2026

  We introduce EvObj for unsupervised 3D instance segmentation that bridges the geometric domain gap between synthetic pretraining data and real-world point clouds. Current methods suffer from structural discrepancies when transferring object priors from synthetic datasets (e.g., ShapeNet) to real sca…

• NFR: Neural Feature-Guided Non-Rigid Shape Registration

  Zhangquan Chen, Puhua Jiang, Mingze Sun, Ruqi Huang · 14. Mai 2026

  In this paper, we propose a novel learning-based framework for 3D shape registration, which overcomes the challenges of significant non-rigid deformation and partiality undergoing among input shapes, and, remarkably, requires no correspondence annotation during training. Our key insight is to incorp…

• HetScene: Heterogeneity-Aware Diffusion for Dense Indoor Scene Generation

  Zini Chen, Junming Huang, Rong Zhang, Jiamin Xu, Cheng Peng, Chi Wang, Weiwei Xu · 14. Mai 2026

  Generating controllable and physically plausible indoor scenes is a pivotal prerequisite for constructing high-fidelity simulation environments for embodied AI. However, existing deeplearning-based methods usually treat all objects as homogeneous instances within a unified generation process. While …

• Min Generalized Sliced Gromov Wasserstein: A Scalable Path to Gromov Wasserstein

  Ashkan Shahbazi, Xinran Liu, Ping He, Soheil Kolouri · 14. Mai 2026

  We propose min Generalized Sliced Gromov--Wasserstein (min-GSGW), a sliced formulation for the Gromov--Wasserstein (GW) problem using expressive generalized slicers. The key idea is to learn coupled nonlinear slicers that assign compatible push-forward values to both input measures, so that monotone…

• A nonlinear extension of parametric model embedding for dimensionality reduction in parametric shape design

  Andrea Serani, Giorgio Palma, Matteo Diez · 13. Mai 2026

  Dimensionality reduction is essential in simulation-based shape design, where high-dimensional parameterizations hinder optimization, surrogate modeling, and systematic design-space exploration. Parametric Model Embedding (PME) addresses this issue by constructing reduced variables from geometric in…

• When and How to Canonize: A Generalization Perspective

  Yonatan Sverdlov, Benjamin Friedman, Snir Hordan, Nadav Dym · 13. Mai 2026

  While invariant architectures are standard for processing symmetric data, there is growing interest in achieving invariance by applying group averaging or canonization to non-invariant backbones. However, the theoretical generalization properties of these alternative strategies remain poorly underst…

• EndoVGGT: GNN-Enhanced Depth Estimation for Surgical 3D Reconstruction

  Falong Fan, Yi Xie, Arnis Lektauers, Bo Liu, Jerzy Rozenblit · 13. Mai 2026

  Accurate 3D reconstruction of deformable soft tissues is essential for surgical robotic perception. However, low-texture surfaces, specular highlights, and instrument occlusions often fragment geometric continuity, posing a challenge for existing fixed-topology approaches. To address this, we propos…

• Fused Gromov-Wasserstein Distance with Feature Selection

  Harlin Lee, Ying Yu, Mingxin Li, Ranthony Clark · 13. Mai 2026

  Fused Gromov-Wasserstein (FGW) distances provide a principled framework for comparing objects by jointly aligning structure and node features. However, existing FGW formulations treat all features uniformly, which limits interpretability and robustness in high-dimensional settings where many feature…

• PointGS: Semantic-Consistent Unsupervised 3D Point Cloud Segmentation with 3D Gaussian Splatting

  Yixiao Song, Qingyong Li, Wen Wang, Zhicheng Yan · 13. Mai 2026

  Unsupervised point cloud segmentation is critical for embodied artificial intelligence and autonomous driving, as it mitigates the prohibitive cost of dense point-level annotations required by fully supervised methods. While integrating 2D pre-trained models such as the Segment Anything Model (SAM) …

• Curvature-Aware Captioning:Leveraging Geodesic Attention for 3D Scene Understanding

  Ziyao He, Yingjie Liu, ZhangYangRui, Mingsong Chen, Xuan Tang, Xian Wei · 12. Mai 2026

  Accurate 3D scene description is fundamental to robotic navigation and augmented reality, yet current dense captioning methods face significant limitations in processing sparse point cloud data. % Existing approaches that apply Euclidean embedding spaces struggle to simultaneously preserve fine-grai…

• Extrusion Segmentation Strategy to improve CAD Reconstruction from Point Cloud

  Said Harb, Mehdi Maboudi, Markus Gerke · 12. Mai 2026

  Computer-Aided Design is ubiquitous in todays world, as almost every manufactured object begins as a digital model across industries. At the same time, advances in 3D sensing have made point clouds a dominant form of raw 3D data. Recovering the CAD model of a physical object from its point cloud sca…

• MeshFIM: Local Low-Poly Mesh Editing via Fill-in-the-Middle Autoregressive Generation

  Dingdong Yang, Jian Liu, Biwen Lei, Haohan Weng, Zhuo Chen, Song Guo, Hao Richard Zhang, Ali Mahdavi Amiri, Chunchao Guo · 12. Mai 2026

  Autoregressive (AR) models can generate high-quality low-poly meshes from point clouds, but they still operate in an all-or-nothing manner: when a local region is unsatisfactory, the entire mesh must be regenerated, wasting computation and destroying satisfactory mesh structure elsewhere. We introdu…

• RigidFormer: Learning Rigid Dynamics using Transformers

  Zhiyang Dou, Minghao Guo, Haixu Wu, Doug Roble, Tuur Stuyck, Wojciech Matusik · 12. Mai 2026

  Learning-based simulation of multi-object rigid-body dynamics remains difficult because contact is discontinuous and errors compound over long horizons. Most existing methods remain tied to mesh connectivity and vertex-level message passing, which limits their applicability to mesh-free inputs such …

• Text-to-CAD Evaluation with CADTests

  Dimitrios Mallis, Marco Wang, Ahmet Serdar Karadeniz, Elisa Ricci, Anis Kacem, Djamila Aouada · 11. Mai 2026

  Text-to-CAD has recently emerged as an important task with the potential to substantially accelerate design workflows. Despite its significance, there has been surprisingly little work on Text-to-CAD evaluation, and assessing CAD model generation performance remains a considerable challenge. In this…

• R$^3$L: Reasoning 3D Layouts from Relative Spatial Relations

  Zhifeng Gu, Yuqi Wang, Bing Wang · 11. Mai 2026

  Relative spatial relations provide a compact representation of spatial structure and are fundamental to relative spatial reasoning in 3D layout generation. Recent works leverage Multimodal Large Language Models (MLLMs) to infer such relations, but the inferred relations are often unreliable and are …

• SAM 3D Animal: Promptable Animal 3D Reconstruction from Images in the Wild

  Xuyi Hu, Jin Lyu, Jiuming Liu, Yebin Liu, Silvia Zuffi, Liang An, Stefan Goetz · 11. Mai 2026

  3D animal reconstruction in the wild remains challenging due to large species variation, frequent occlusions, and the prevalence of multi-animal scenes, while existing methods predominantly focus on single-animal settings. We present SAM 3D Animal, the first promptable framework for multi-animal 3D …

• A Bayesian Approach for Task-Specific Next-Best-View Selection with Uncertain Geometry

  Jingsen Zhu, Silvia Sell\'an, Alexander Terenin · 7. Mai 2026

  We develop a framework for task-specific active next-best-view selection in 3D reconstruction from point clouds, by casting the problem in the language of Bayesian decision theory. Our framework works by (a) placing a prior distribution over the space of implicit surfaces, (b) using recently-develop…

• Parametrizing Convex Sets Using Sublinear Neural Networks

  Eloi Martinet · 6. Mai 2026

  We propose a neural parameterization of convex sets by learning sublinear (positively homogeneous and convex) functions. Our networks implicitly represent both the support and gauge functions of a convex body. We prove a universal approximation theorem for convex sets under this parametrization. Emp…

• Orchestrating Spatial Semantics via a Zone-Graph Paradigm for Intricate Indoor Scene Generation

  Meisheng Zhang, Shizhao Sun, Yang Zhao, Ziyuan Liu, Zhijun Gao, Jiang Bian · 6. Mai 2026

  Autonomous 3D indoor scene synthesis breaks down in non-convex rooms with tightly coupled spatial constraints. Data-driven generators lack topological priors for long-horizon planning, while iterative agents fragment semantics and become geometrically brittle. We present ZoneMaestro, a unified frame…

• Self-Supervised Learning for Multimodal Non-Rigid 3D Shape Matching

  Dongliang Cao, Florian Bernard · 6. Mai 2026

  The matching of 3D shapes has been extensively studied for shapes represented as surface meshes, as well as for shapes represented as point clouds. While point clouds are a common representation of raw real-world 3D data (e.g. from laser scanners), meshes encode rich and expressive topological infor…

• Unsupervised Learning of Robust Spectral Shape Matching

  Dongliang Cao, Paul Roetzer, Florian Bernard · 6. Mai 2026

  We propose a novel learning-based approach for robust 3D shape matching. Our method builds upon deep functional maps and can be trained in a fully unsupervised manner. Previous deep functional map methods mainly focus on predicting optimised functional maps alone, and then rely on off-the-shelf post…

• SplAttN: Bridging 2D and 3D with Gaussian Soft Splatting and Attention for Point Cloud Completion

  Zhaoyang Li, Zhichao You, Tianrui Li · 5. Mai 2026

  Although multi-modal learning has advanced point cloud completion, the theoretical mechanisms remain unclear. Recent works attribute success to the connection between modalities, yet we identify that standard hard projection severs this connection: projecting a sparse point cloud onto the image plan…

• Learning to Place Objects with Programs and Iterative Self Training

  Adrian Chang, Kai Wang, Yuanbo Li, Manolis Savva, Angel X. Chang, Daniel Ritchie · 5. Mai 2026

  In this work we study indoor scene object placement. Given a 3D indoor scene and an object, the task is to predict placement locations within the scene. Empirical observations of data-driven approaches to the problem show their tendency to miss placement modes. We introduce a system which helps to a…