3D Shape Modeling and Analysis

Latest papers

• InpaintSLat: Inpainting Structured 3D Latents via Initial Noise Optimization

  Jaeyoung Chung, Suyoung Lee, Kyoung Mu Lee · 4 May 2026

  We present a training-free approach for controllable 3D inpainting based on initial noise optimization. In the structured 3D latent diffusion framework, we observe that the underlying geometric structure is established during the early stages of the diffusion process and exhibits high sensitivity to…

• Faster 3D Gaussian Splatting Convergence via Structure-Aware Densification

  Linjie Lyu, Ayush Tewari, Jianchun Chen, Thomas Leimk\"uhler, Christian Theobalt · 1 May 2026

  3D Gaussian Splatting has emerged as a powerful scene representation for real-time novel-view synthesis. However, its standard adaptive density control relies on screen-space positional gradients, which do not distinguish between geometric misplacement and frequency aliasing, often leading to either…

• Reconstruction by Generation: 3D Multi-Object Scene Reconstruction from Sparse Observations

  Andrii Zadaianchuk, Leonardo Barcellona, Lennard Schuenemann, Christian Gumbsch, Zehao Wang, Muhammad Zubair Irshad, Fabien Despinoy, Rahaf Aljundi, Stratis Gavves, Sergey Zakharov · 1 May 2026

  Accurately reconstructing complex full multi-object scenes from sparse observations remains a core challenge in computer vision and a key step toward scalable and reliable simulation for robotics. In this work, we introduce RecGen, a generative framework for probabilistic joint estimation of object …

• SpatialGrammar: A Domain-Specific Language for LLM-Based 3D Indoor Scene Generation

  Song Tang, Kaiyong Zhao, Yuliang Li, Qingsong Yan, Penglei Sun, Junyi Zou, Qiang Wang, Xiaowen Chu · 1 May 2026

  Automatically generating interactive 3D indoor scenes from natural language is crucial for virtual reality, gaming, and embodied AI. However, existing LLM-based approaches often suffer from spatial errors and collisions, in part because common scene representations-raw coordinates or verbose code-ar…

• Generalizing the Geometry of Model Merging Through Frechet Averages

  Marvin F. da Silva, Mohammed Adnan, Felix Dangel, Sageev Oore · 1 May 2026

  Model merging aims to combine multiple models into one without additional training. Na\"ive parameter-space averaging can be fragile under architectural symmetries, as their geometry does not take them into account. In this work we show that not only the geometry, but also the averaging procedure it…

• Vertex Features for Neural Global Illumination

  Rui Su, Honghao Dong, Haojie Jin, Yisong Chen, Guoping Wang, Sheng Li · 30 April 2026

  Recent research on learnable neural representations has been widely adopted in the field of 3D scene reconstruction and neural rendering applications. However, traditional feature grid representations often suffer from substantial memory footprint, posing a significant bottleneck for modern parallel…

• Co-generation of Layout and Shape from Text via Autoregressive 3D Diffusion

  Zhenggang Tang, Yuehao Wang, Yuchen Fan, Jun-Kun Chen, Yu-Ying Yeh, Kihyuk Sohn, Zhangyang Wang, Qixing Huang, Alexander Schwing, Rakesh Ranjan, Dilin Wang, Zhicheng Yan · 30 April 2026

  Recent text-to-scene generation approaches largely reduced the manual efforts required to create 3D scenes. However, their focus is either to generate a scene layout or to generate objects, and few generate both. The generated scene layout is often simple even with LLM's help. Moreover, the generate…

• PEPS: Positional Encoding Projected Sampling -- Extended

  Guillaume Perez, Janarbek Matai, Takahiro Harada · 28 April 2026

  Implicit neural representations (INRs) are increasingly being used as tools to map coordinates to signals, encompassing applications from neural fields to texture compression, shape representations, and beyond. Most INR methods are based on using high-dimensional projections of the initial coordinat…

• ODE-GS: Latent ODEs for Dynamic Scene Extrapolation with 3D Gaussian Splatting

  Daniel Wang, Patrick Rim, Tian Tian, Dong Lao, Alex Wong, Ganesh Sundaramoorthi · 28 April 2026

  We introduce ODE-GS, a novel approach that integrates 3D Gaussian Splatting with latent neural ordinary differential equations (ODEs) to enable future extrapolation of dynamic 3D scenes. Unlike existing dynamic scene reconstruction methods, which rely on time-conditioned deformation networks and are…

• Shape: A Self-Supervised 3D Geometry Foundation Model for Industrial CAD Analysis

  Bayangmbe Mounmo, Sam Chien, Mile Mitrovic · 28 April 2026

  Industrial CAD workflows require robust, generalizable 3D geometric representations supporting accuracy and explainability. We introduce Shape, a self-supervised foundation model converting surface meshes into dense per-token embeddings. Shape combines a structured 3D latent grid, a multi-scale geom…

• PR-CAD: Progressive Refinement for Unified Controllable and Faithful Text-to-CAD Generation with Large Language Models

  Jiyuan An, Jiachen Zhao, Fan Chen, Liner Yang, Zhenghao Liu, Hongyan Wang, Weihua An, Meishan Zhang, Erhong Yang · 24 April 2026

  The construction of CAD models has traditionally relied on labor-intensive manual operations and specialized expertise. Recent advances in large language models (LLMs) have inspired research into text-to-CAD generation. However, existing approaches typically treat generation and editing as disjoint …

• Medial Axis Aware Learning of Signed Distance Functions

  Samuel Weidemaier, Christoph Norden-Smoch, Martin Rumpf · 21 April 2026

  We propose a novel variational method to compute a highly accurate global signed distance function (SDF) to a given point cloud. To this end, the jump set of the gradient of the SDF, which coincides with the medial axis of the surface, is explicitly taken into account through a higher-order variatio…

• FlashFPS: Efficient Farthest Point Sampling for Large-Scale Point Clouds via Pruning and Caching

  Yuzhe Fu (Helen), Hancheng Ye (Helen), Cong Guo (Helen), Junyao Zhang (Helen), Qinsi Wang (Helen), Yueqian Lin (Helen), Changchun Zhou (Helen), Hai (Helen), Li, Yiran Chen · 21 April 2026

  Point-based Neural Networks (PNNs) have become a key approach for point cloud processing. However, a core operation in these models, Farthest Point Sampling (FPS), often introduces significant inference latency, especially for large-scale processing. Despite existing CUDA- and hardware-level optimiz…

• Spira: Exploiting Voxel Data Structural Properties for Efficient Sparse Convolution in Point Cloud Networks

  Dionysios Adamopoulos, Anastasia Poulopoulou, Georgios Goumas, Christina Giannoula · 20 April 2026

  Sparse Convolution (SpC) powers 3D point cloud networks widely used in autonomous driving and augmented/virtual reality. SpC builds a kernel map that stores mappings between input voxel coordinates, output coordinates, and weight offsets, then uses this map to compute feature vectors for output coor…

• STEP-Parts: Geometric Partitioning of Boundary Representations for Large-Scale CAD Processing

  Shen Fan, Miko{\l}aj Kida, Przemyslaw Musialski · 17 April 2026

  Many CAD learning pipelines discretize Boundary Representations (B-Reps) into triangle meshes, discarding analytic surface structure and topological adjacency and thereby weakening consistent instance-level analysis. We present STEP-Parts, a deterministic CAD-to-supervision toolchain that extracts g…

• Beyond Voxel 3D Editing: Learning from 3D Masks and Self-Constructed Data

  Yizhao Xu, Hongyuan Zhu, Caiyun Liu, Tianfu Wang, Keyu Chen, Sicheng Xu, Jiaolong Yang, Nicholas Jing Yuan, Qi Zhang · 16 April 2026

  3D editing refers to the ability to apply local or global modifications to 3D assets. Effective 3D editing requires maintaining semantic consistency by performing localized changes according to prompts, while also preserving local invariance so that unchanged regions remain consistent with the origi…

• SIM1: Physics-Aligned Simulator as Zero-Shot Data Scaler in Deformable Worlds

  Yunsong Zhou, Hangxu Liu, Xuekun Jiang, Xing Shen, Yuanzhen Zhou, Hui Wang, Baole Fang, Yang Tian, Mulin Yu, Qiaojun Yu, Li Ma, Hengjie Li, Hanqing Wang, Jia Zeng, Jiangmiao Pang · 13 April 2026

  Robotic manipulation with deformable objects represents a data-intensive regime in embodied learning, where shape, contact, and topology co-evolve in ways that far exceed the variability of rigids. Although simulation promises relief from the cost of real-world data acquisition, prevailing sim-to-re…

• Fast Spatial Memory with Elastic Test-Time Training

  Ziqiao Ma, Xueyang Yu, Haoyu Zhen, Yuncong Yang, Joyce Chai, Chuang Gan · 9 April 2026

  Large Chunk Test-Time Training (LaCT) has shown strong performance on long-context 3D reconstruction, but its fully plastic inference-time updates remain vulnerable to catastrophic forgetting and overfitting. As a result, LaCT is typically instantiated with a single large chunk spanning the full inp…

• Part-Level 3D Gaussian Vehicle Generation with Joint and Hinge Axis Estimation

  Shiyao Qian, Yuan Ren, Dongfeng Bai, Bingbing Liu · 8 April 2026

  Simulation is essential for autonomous driving, yet current frameworks often model vehicles as rigid assets and fail to capture part-level articulation. With perception algorithms increasingly leveraging dynamics such as wheel steering or door opening, realistic simulation requires animatable vehicl…

• COSMO-Agent: 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 · 8 April 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),…

• Tokenizing Buildings: A Transformer for Layout Synthesis

  Manuel Ladron de Guevara, Jinmo Rhee, Ardavan Bidgoli, Vaidas Razgaitis, Michael Bergin · 8 April 2026

  We introduce Small Building Model (SBM), a Transformer-based architecture for layout synthesis in Building Information Modeling (BIM) scenes. We address the question of how to tokenize buildings by unifying heterogeneous feature sets of architectural elements into sequences while preserving composit…

• TreeGaussian: Tree-Guided Cascaded Contrastive Learning for Hierarchical Consistent 3D Gaussian Scene Segmentation and Understanding

  Jingbin You, Zehao Li, Hao Jiang, Xinzhu Ma, Shuqin Gao, Honglong Zhao, Congcong Zheng, Tianlu Mao, Feng Dai, Yucheng Zhang, Zhaoqi Wang · 7 April 2026

  3D Gaussian Splatting (3DGS) has emerged as a real-time, differentiable representation for neural scene understanding. However, existing 3DGS-based methods struggle to represent hierarchical 3D semantic structures and capture whole-part relationships in complex scenes. Moreover, dense pairwise compa…

• MAVEN: A Mesh-Aware Volumetric Encoding Network for Simulating 3D Flexible Deformation

  Zhe Feng, Shilong Tao, Haonan Sun, Shaohan Chen, Zhanxing Zhu, Yunhuai Liu · 7 April 2026

  Deep learning-based approaches, particularly graph neural networks (GNNs), have gained prominence in simulating flexible deformations and contacts of solids, due to their ability to handle unstructured physical fields and nonlinear regression on graph structures. However, existing GNNs commonly repr…

• TORA: Topological Representation Alignment for 3D Shape Assembly

  Nahyuk Lee, Zhiang Chen, Marc Pollefeys, Sunghwan Hong · 7 April 2026

  Flow-matching methods for 3D shape assembly learn point-wise velocity fields that transport parts toward assembled configurations, yet they receive no explicit guidance about which cross-part interactions should drive the motion. We introduce TORA, a topology-first representation alignment framework…

• Minimising Willmore Energy via Neural Flow

  Edward Hirst, Henrique N. S\'a Earp, Tom\'as S. R. Silva · 7 April 2026

  The neural Willmore flow of a closed oriented $2$-surface in $\mathbb{R}^3$ is introduced as a natural evolution process to minimise the Willmore energy, which is the squared $L^2$-norm of mean curvature. Neural architectures are used to model maps from topological $2d$ domains to $3d$ Euclidean spa…