3D Shape Modeling and Analysis

Últimos artículos

• NEXUS: Neural Energy Fields for Physically Consistent Contact-Rich 3D Object Dynamics

  Qizhen Ying, Guangming Wang, Yangchen Pan, Victor Adrian Prisacariu, Yixiong Jing · 16 de junio de 2026

  Physics-grounded video generation requires controllable 3D object dynamics that remain physically consistent under contact, deformation, and external forcing. Existing trajectory-based methods often model isolated physical effects, making it difficult to compose conservative and non-conservative dyn…

• SceneConductor: 3D Scene Generation from a Single Image with Multi-Agent Orchestration

  Jeonghwan Kim, Yushi Lan, Yongwei Chen, Hieu Trung Nguyen, Chuanyu Pan, Xingang Pan · 16 de junio de 2026

  Generating complete 3D scenes from a single image requires inferring globally consistent geometry, object relationships, and environmental context from inherently ambiguous visual evidence. Despite recent progress in joint layout-and-mesh generation, existing methods often rely on holistic or weakly…

• EgoPhys: Learning Generalizable Physics Models of Deformable Objects from Egocentric Video

  Hyunjin Kim, Ri-Zhao Qiu, Guangqi Jiang, Xiaolong Wang · 16 de junio de 2026

  Humans naturally understand object physics through everyday interactions, but faithfully predicting complex deformable dynamics, such as elastic materials and fabrics, remains a major challenge for computer vision and robotics. We present EgoPhys, a framework that constructs deformable physical digi…

• DeepJEB++: Foundation Model-Driven Large-Scale 3D Engineering Dataset via 2D Latent Space Augmentation

  Soyoung Yoo, Leekyo Jeong, Jinsu Ra, Dongeon Lee, Sunwoong Yang, Hyogu Jeong, Namwoo Kang · 15 de junio de 2026

  Data-driven engineering design is constrained by the lack of large-scale 3D datasets that pair geometry with physics-based performance labels. In particular, existing 3D data augmentation techniques have limitations in preserving subtle and diverse geometric variations, and it remains difficult to a…

• IterCAD: An Iterative Multimodal Agent for Visually-Grounded CAD Generation and Editing

  Tao Hu, Jiaxin Ai, Licheng Wen, Xueheng Li, Shu Zou, Siqi Li, Nianchen Deng, Xinyu Cai, Hongbin Zhou, Pinlong Cai, Daocheng Fu, Yu Yang, Hairong Zhang, Botian Shi, Xuemeng Yang · 12 de junio de 2026

  Computer-Aided Design is pivotal in modern manufacturing, yet existing automated methods predominantly rely on open-loop, one-shot generation, creating a mismatch with iterative real-world practices. In this paper, we present IterCAD, a unified multimodal agent framework for closed-loop, interactive…

• Transformer-Guided Graph Attention for Direct Cardiac Mesh Reconstruction: A Structural Digital Twin Framework

  Abhishek H S, Akash Ganamukhi, Abhimanyu Suresh, Aditya G Hiremath, Prasad B Honnavalli, Adithya Balasubramanyam · 12 de junio de 2026

  Building patient-specific cardiac models sits at the heart of precision cardiology, yet getting those models into clinical use keeps running into the same wall: mesh generation is slow, messy, and frustrating. The standard workflow -- segmenting the image, running Marching Cubes, and then manually c…

• nD-RoPE: A Generalized RoPE for n-Dimensional Position Embedding

  Boyang Li, Yulin Wu, Sizhe Xu, Nuoxian Huang, Zhonghang Yuan, Shangyi Guo, Shu Yang, Takahiro Yabe · 11 de junio de 2026

  Rotary Position Embedding (RoPE) is widely adopted in Transformer models, yet its extension to high-dimensional domains lacks a unified theoretical formulation. Most existing approaches either apply rotations independently along each axis or empirically mix frequencies, which limits cross-dimensiona…

• Generalized-CVO: Fast and Correspondence-Free Local Point Cloud Registration with Second Order Riemannian Optimization

  Ray Zhang, Marcus Greiff, Thomas Lew, John Subosits · 10 de junio de 2026

  We propose a fast and correspondence-free local point cloud registration method that leverages geometric surface structure and reproducing kernel Hilbert space (RKHS) embeddings. The method represents point clouds as continuous functions with point-wise anisotropic kernels that encode local geometry…

• Compositional Generative Modeling from Decentralized Data

  Mashrur M. Morshed, Vishnu Naresh Boddeti · 10 de junio de 2026

  Learning the compositional nature of the physical world requires joint observation of interacting factors. However, because practical data is often decentralized, these factors are fragmented across isolated silos. Existing decentralized generative approaches focus only on modeling the union of silo…

• Architect-Ant: Editable Automatic Furnishing of Architectural Floor Plans

  Fedor Rodionov, Aleksandar Cvejic, Michael Birsak, John Femiani, Peter Wonka · 10 de junio de 2026

  Furnished floor plans are fundamental to real estate visualization, interior design, and architectural workflows. However, progress in automatic furniture arrangement has been limited by the lack of real, professionally designed floor-plan datasets with object-level furniture annotations. To address…

• SceneConductor: 3D Scene Generation from Single Image with Multi-Agent Orchestration

  Jeonghwan Kim, Yushi Lan, Yongwei Chen, Hieu Trung Nguyen, Chuanyu Pan, Xingang Pan · 9 de junio de 2026

  Generating complete 3D scenes from a single image requires inferring globally consistent geometry, object relationships, and environmental context from inherently ambiguous visual evidence. Despite recent progress in joint layout-and-mesh generation, existing methods often rely on holistic or weakly…

• Liquid Neural Networks as a Drop-in Continuous-Time Deformation Field for Dynamic 3D Gaussian Splatting

  Mingzhao Li, Arghya Pal, Guan Yuan Tan · 9 de junio de 2026

  Deformable 3D Gaussian Splatting (D-3DGS) re-constructs dynamic scenes from monocular video by deforming a canonical set of 3D Gaussians through a positional-encoded MLP of frame time t. Although fitted to a continuous variable, the MLP couples no two values of t in its architecture and effectively …

• GVC-Seg: Training-Free 3D Instance Segmentation via Geometric Visual Correspondence

  Liang Xu, Fangjing Wang, Jinyu Yang, Feng Zheng · 9 de junio de 2026

  Accurate 3D instance segmentation in point cloud data is critical for machine vision applications. Recent advancements leverage multiple pre-trained foundation models to generate 3D proposals, followed by the application of proposal aggregation methods, which significantly enhance performance. Howev…

• Native3D: End-to-End 3D Scene Generation via Unified Mesh-Texture Modeling and Semantic Alignment

  Yibo Liu, Ziwei Zhang, Haozhou Pang, Menghao Li, Lanshan He, Gan Qi · 8 de junio de 2026

  This paper presents Native3D, the first end-to-end 3D scene generation framework that completely bypasses 2D intermediate representations. Traditional approaches typically require adapting 3D representations to the 2D domain to leverage pre-trained diffusion models, which inevitably introduces domai…

• HomeWorld: A Unified Floorplan-to-Furnished Framework for Generating Controllable, Densely Interactive Whole-Home Scenes

  Wenbo Li, Xiaoliang Ju, Zipeng Qin, Rongyao Fang, Hongsheng Li · 5 de junio de 2026

  Indoor scene generation is crucial for robot simulation and modern interior design. However, complex layouts together with scarce 3D scene data make learning-based generation challenging. Existing methods often rely on hand-crafted rules or focus on isolated sub-tasks (e.g., floorplan synthesis or s…

• Geometry Gaussians: Decoupling Appearance and Geometry in Gaussian Splatting

  Hongyu Zhou, Zorah L\"ahner · 4 de junio de 2026

  After the success of 3D Gaussian Splatting (3DGS) for novel view synthesis, many works have explored how to also use it for geometric surface representation. However, extracting accurate geometric information directly from 3DGS remains challenging and can often reduce the appearance rendering qualit…

• SymTRELLIS: Symmetry-Enforced Voxel Latents for 3D Generation

  Guangda Ji, Qimin Chen, Qinchan Li, Mingrui Zhao, Kai Wang, Hao Zhang · 4 de junio de 2026

  Single-view 3D generative models have achieved impressive visual quality, yet they are not designed to satisfy structural or functional requirements, and in practice, often fall short. Symmetry is one such requirement: violations, even subtle ones, on symmetry can render a model physically unusable.…

• UniCAD: A Unified Benchmark and Universal Model for Multi-Modal Multi-Task CAD

  Jingyuan Chen, Sheng Jin, Haopeng Sun, Wentao Liu, Chen Qian · 4 de junio de 2026

  Computer-Aided Design (CAD) underpins modern engineering and manufacturing by enabling the creation of precise, editable 3D models. However, CAD research typically studies tasks in isolation, and multi-modal, multi-task learning for CAD is hindered by the absence of a unified benchmark. To address t…

• MidSurfNet: Learnable Face Pairing and Interference Implicit Fields for Generalized Mid-surface Abstraction

  Li Ye, Xinhang Zhou, Xingyu Yang, Ruofeng Tong, Hailong Li, Peng Du, Min Tang · 2 de junio de 2026

  Mid-surface abstraction is essential for finite element analysis of thin-walled CAD models. Existing face pairing-based methods rely on handcrafted geometric heuristics, yet real-world industrial models frequently exhibit multi-wall-thickness regions, self-matching face configurations, and demand fo…

• 3DCodeBench: Benchmarking Agentic Procedural 3D Modeling Via Code

  Yipeng Gao, Lei Shu, Genzhi Ye, Xi Xiong, Ameesh Makadia, Meiqi Guo, Laurent Itti, Jindong Chen · 2 de junio de 2026

  Procedural 3D modeling through code is emerging as a versatile paradigm, offering deterministic, engine-ready, and precisely editable assets that neural 3D generators inherently lack. Authoring such procedural content, however, demands deep expertise in 3D software APIs, parametric design, and code-…

• Fast and Lightweight Novel View Synthesis with Differentiable Multiplane Image

  Kaidi Zhang, Guanxu Zhu · 2 de junio de 2026

  Recently, novel view synthesis has witnessed remarkable progress, with mainstream methods such as Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS) delivering impressive results. However, these approaches often struggle to balance rendering speed and model size, and their optimization-b…

• ShapeLib: Designing a library of programmatic 3D shape abstractions with Large Language Models

  R. Kenny Jones, Paul Guerrero, Niloy J. Mitra, Daniel Ritchie · 2 de junio de 2026

  We present ShapeLib, the first method that uses the priors of Large Language Models (LLMs) to design libraries of programmatic 3D shape abstractions. Our system accepts two forms of user-provided design intent: high-level text descriptions of functions to include in the output library and a small se…

• Rethinking Amortized Neural Representations for High-Resolution Terrain Elevation Data

  Haoan Feng, Xin Xu, Leila De Floriani · 2 de junio de 2026

  Implicit neural representations (INRs) model a signal as a continuous coordinate-to-value function. For terrain elevation data, this supports analytic derivatives, arbitrary-resolution decoding, and a smooth surface model of the underlying heightfield. However, fitting and storing a separate INR for…

• City-Mesh3R: Simulation-Ready City-Scale 3D Mesh Reconstruction from Multi-View Images

  Sayan Paul, Sourav Ghosh, Siddharth Katageri, Soumyadip Maity, Sanjana Sinha, Brojeshwar Bhowmick · 29 de mayo de 2026

  City-scale 3D surface reconstruction from multiview images for downstream 3D simulation, poses highly challenging problems due to the scale and complexity of urban scenes. Existing city-scale 3D reconstruction methods based on NeRF, Gaussian Splatting etc. often fail to recover 3D meshes ready for s…

• TriSearch: Learning to Optimize Triangulations via Bistellar Flips

  Yiran Wang, Guido Mont\'ufar · 29 de mayo de 2026

  We introduce TriSearch, a reinforcement learning framework for optimizing objectives over triangulations of a polytope via bistellar flips. The key idea is a circuit-supported subtriangulation action representation: feasible flips are encoded by their supporting circuit and realized local subtriangu…