3D Shape Modeling and Analysis

Últimos artículos

• Learning Hierarchical Orthogonal Prototypes for Generalized Few-Shot 3D Point Cloud Segmentation

  Yifei Zhao, Fanyu Zhao, Zhongyuan Zhang, Shengtang Wu, Yixuan Lin, Yinsheng Li · 23 de marzo de 2026

  Generalized few-shot 3D point cloud segmentation aims to adapt to novel classes from only a few annotations while maintaining strong performance on base classes, but this remains challenging due to the inherent stability-plasticity trade-off: adapting to novel classes can interfere with shared repre…

• Uncertainty-aware Prototype Learning with Variational Inference for Few-shot Point Cloud Segmentation

  Yifei Zhao, Fanyu Zhao, Yinsheng Li · 23 de marzo de 2026

  Few-shot 3D semantic segmentation aims to generate accurate semantic masks for query point clouds with only a few annotated support examples. Existing prototype-based methods typically construct compact and deterministic prototypes from the support set to guide query segmentation. However, such rigi…

• OT-MeanFlow3D: Bridging Optimal Transport and Meanflow for Efficient 3D Point Cloud Generation

  Elaheh Akbari, Shansita Sharma, Ping He, Ahmadreza Moradipari, Kyungtae Han, Hamed Pirsiavash, Yikun Bai, Soheil Kolouri · 20 de marzo de 2026

  Flow-matching models have recently emerged as a powerful framework for continuous generative modeling, including 3D point cloud synthesis. However, their deployment is limited by the need for multiple sequential sampling steps at inference time. MeanFlow enables single-step generation and significan…

• DreamPartGen: Semantically Grounded Part-Level 3D Generation via Collaborative Latent Denoising

  Tianjiao Yu, Xinzhuo Li, Muntasir Wahed, Jerry Xiong, Yifan Shen, Ying Shen, Ismini Lourentzou · 20 de marzo de 2026

  Understanding and generating 3D objects as compositions of meaningful parts is fundamental to human perception and reasoning. However, most text-to-3D methods overlook the semantic and functional structure of parts. While recent part-aware approaches introduce decomposition, they remain largely geom…

• Points-to-3D: Structure-Aware 3D Generation with Point Cloud Priors

  Jiatong Xia, Zicheng Duan, Anton van den Hengel, Lingqiao Liu · 20 de marzo de 2026

  Recent progress in 3D generation has been driven largely by models conditioned on images or text, while readily available 3D priors are still underused. In many real-world scenarios, the visible-region point cloud are easy to obtain from active sensors such as LiDAR or from feed-forward predictors l…

• LoST: Level of Semantics Tokenization for 3D Shapes

  Niladri Shekhar Dutt, Zifan Shi, Paul Guerrero, Chun-Hao Paul Huang, Duygu Ceylan, Niloy J. Mitra, Xuelin Chen · 19 de marzo de 2026

  Tokenization is a fundamental technique in the generative modeling of various modalities. In particular, it plays a critical role in autoregressive (AR) models, which have recently emerged as a compelling option for 3D generation. However, optimal tokenization of 3D shapes remains an open question. …

• GATS: Gaussian Aware Temporal Scaling Transformer for Invariant 4D Spatio-Temporal Point Cloud Representation

  Jiayi Tian, Jiaze Wang · 18 de marzo de 2026

  Understanding 4D point cloud videos is essential for enabling intelligent agents to perceive dynamic environments. However, temporal scale bias across varying frame rates and distributional uncertainty in irregular point clouds make it highly challenging to design a unified and robust 4D backbone. E…

• SOMA: Unifying Parametric Human Body Models

  Jun Saito, Jiefeng Li, Michael de Ruyter, Miguel Guerrero, Edy Lim, Ehsan Hassani, Roger Blanco Ribera, Hyejin Moon, Magdalena Dadela, Marco Di Lucca, Qiao Wang, Xueting Li, Jan Kautz, Simon Yuen, Umar Iqbal · 18 de marzo de 2026

  Parametric human body models are foundational to human reconstruction, animation, and simulation, yet they remain mutually incompatible: SMPL, SMPL-X, MHR, Anny, and related models each diverge in mesh topology, skeletal structure, shape parameterization, and unit convention, making it impractical t…

• Parallelised Differentiable Straightest Geodesics for 3D Meshes

  Hippolyte Verninas, Caner Korkmaz, Stefanos Zafeiriou, Tolga Birdal, Simone Foti · 18 de marzo de 2026

  Machine learning has been progressively generalised to operate within non-Euclidean domains, but geometrically accurate methods for learning on surfaces are still falling behind. The lack of closed-form Riemannian operators, the non-differentiability of their discrete counterparts, and poor parallel…

• Interact3D: Compositional 3D Generation of Interactive Objects

  Hui Shan, Keyang Luo, Ming Li, Sizhe Zheng, Yanwei Fu, Zhen Chen, Xiangru Huang · 18 de marzo de 2026

  Recent breakthroughs in 3D generation have enabled the synthesis of high-fidelity individual assets. However, generating 3D compositional objects from single images--particularly under occlusions--remains challenging. Existing methods often degrade geometric details in hidden regions and fail to pre…

• Training-Free Global Geometric Association for 4D LiDAR Panoptic Segmentation

  Gyeongrok Oh, Youngdong Jang, Jonghyun Choi, Suk-Ju Kang, Guang Lin, Sangpil Kim · 17 de marzo de 2026

  Dominant paradigms for 4D LiDAR panoptic segmentation are usually required to train deep neural networks with large superimposed point clouds or design dedicated modules for instance association. However, these approaches perform redundant point processing and consequently become computationally exp…

• Design-MLLM: A Reinforcement Alignment Framework for Verifiable and Aesthetic Interior Design

  Yuxuan Yang, Xiaotong Mao, Jingyao Wang, Fuchun Sun · 17 de marzo de 2026

  Interior design is a requirements-to-visual-plan generation process that must simultaneously satisfy verifiable spatial feasibility and comparative aesthetic preferences. While recent multimodal large language models (MLLMs) offer a unified foundation for interpreting user intent and producing desig…

• CLIPoint3D: Language-Grounded Few-Shot Unsupervised 3D Point Cloud Domain Adaptation

  Mainak Singha, Sarthak Mehrotra, Paolo Casari, Subhasis Chaudhuri, Elisa Ricci, Biplab Banerjee · 17 de marzo de 2026

  Recent vision-language models (VLMs) such as CLIP demonstrate impressive cross-modal reasoning, extending beyond images to 3D perception. Yet, these models remain fragile under domain shifts, especially when adapting from synthetic to real-world point clouds. Conventional 3D domain adaptation approa…

• Unsupervised Point Cloud Pre-Training via Contrasting and Clustering

  Guofeng Mei, Xiaoshui Huang, Juan Liu, Jian Zhang, Qiang Wu · 17 de marzo de 2026

  Annotating large-scale point clouds is highly time-consuming and often infeasible for many complex real-world tasks. Point cloud pre-training has therefore become a promising strategy for learning discriminative representations without labeled data. In this paper, we propose a general unsupervised p…

• EI-Part: Explode for Completion and Implode for Refinement

  Wanhu Sun, Zhongjin Luo, Heliang Zheng, Jiahao Chang, Chongjie Ye, Huiang He, Shengchu Zhao, Rongfei Jia, Xiaoguang Han · 17 de marzo de 2026

  Part-level 3D generation is crucial for various downstream applications, including gaming, film production, and industrial design. However, decomposing a 3D shape into geometrically plausible and meaningful components remains a significant challenge. Previous part-based generation methods often stru…

• Exploring Low-Dimensional Subspaces in Diffusion Models for Controllable Image Editing

  Siyi Chen, Huijie Zhang, Minzhe Guo, Yifu Lu, Peng Wang, Qing Qu · 17 de marzo de 2026

  Recently, diffusion models have emerged as a powerful class of generative models. Despite their success, there is still limited understanding of their semantic spaces. This makes it challenging to achieve precise and disentangled image generation without additional training, especially in an unsuper…

• Design-Specification Tiling for ICL-based CAD Code Generation

  Yali Du, San-Zhuo Xi, Hui Sun, Ming Li · 16 de marzo de 2026

  Large language models (LLMs) have demonstrated remarkable capabilities in code generation, yet they underperform on domain-specific tasks such as Computer-Aided Design (CAD) code generation due to scarce training data. In-Context Learning (ICL) offers a training-free alternative through task-specifi…

• Sobolev--Ricci Curvature

  Kyoichi Iwasaki, Tam Le, Hideitsu Hino · 16 de marzo de 2026

  Ricci curvature is a fundamental concept in differential geometry for encoding local geometric structure, and its graph-based analogues have recently gained prominence as practical tools for reweighting, pruning, and reshaping network geometry. We propose Sobolev-Ricci Curvature (SRC), a graph Ricci…

• CMHANet: A Cross-Modal Hybrid Attention Network for Point Cloud Registration

  Dongxu Zhang, Yingsen Wang, Yiding Sun, Haoran Xu, Peilin Fan, Jihua Zhu · 16 de marzo de 2026

  Robust point cloud registration is a fundamental task in 3D computer vision and geometric deep learning, essential for applications such as large-scale 3D reconstruction, augmented reality, and scene understanding. However, the performance of established learning-based methods often degrades in comp…

• Shape-of-You: Fused Gromov-Wasserstein Optimal Transport for Semantic Correspondence in-the-Wild

  Jiin Im, Sisung Liu, Je Hyeong Hong · 13 de marzo de 2026

  Semantic correspondence is essential for handling diverse in-the-wild images lacking explicit correspondence annotations. While recent 2D foundation models offer powerful features, adapting them for unsupervised learning via nearest-neighbor pseudo-labels has key limitations: it operates locally, ig…

• MVCustom: Multi-View Customized Diffusion via Geometric Latent Rendering and Completion

  Minjung Shin, Hyunin Cho, Sooyeon Go, Jin-Hwa Kim, Youngjung Uh · 12 de marzo de 2026

  Multi-view generation with camera pose control and prompt-based customization are both essential elements for achieving controllable generative models. However, existing multi-view generation models do not support customization with geometric consistency, whereas customization models lack explicit v…

• Pointy - A Lightweight Transformer for Point Cloud Foundation Models

  Konrad Szafer, Marek Kraft, Dominik Belter · 12 de marzo de 2026

  Foundation models for point cloud data have recently grown in capability, often leveraging extensive representation learning from language or vision. In this work, we take a more controlled approach by introducing a lightweight transformer-based point cloud architecture. In contrast to the heavy rel…

• DenoiseSplat: Feed-Forward Gaussian Splatting for Noisy 3D Scene Reconstruction

  Fuzhen Jiang, Zhuoran Li, Yinlin Zhang · 11 de marzo de 2026

  3D scene reconstruction and novel-view synthesis are fundamental for VR, robotics, and content creation. However, most NeRF and 3D Gaussian Splatting pipelines assume clean inputs and degrade under real noise and artifacts. We therefore propose DenoiseSplat, a feed-forward 3D Gaussian splatting meth…

• Learning From Design Procedure To Generate CAD Programs for Data Augmentation

  Yan-Ying Chen, Dule Shu, Matthew Hong, Andrew Taber, Jonathan Li, Matthew Klenk · 10 de marzo de 2026

  Large Language Models (LLMs) have demonstrated impressive capabilities in a wide range of code generation tasks. However, generating code for certain domains remains challenging. One such domain is Computer-Aided Design (CAD) program, where the goal is to produce scripted parametric models that defi…

• SLNet: A Super-Lightweight Geometry-Adaptive Network for 3D Point Cloud Recognition

  Mohammad Saeid, Amir Salarpour, Pedram MohajerAnsari, Mert D. Pes\'e · 10 de marzo de 2026

  We present SLNet, a lightweight backbone for 3D point cloud recognition designed to achieve strong performance without the computational cost of many recent attention, graph, and deep MLP based models. The model is built on two simple ideas: NAPE (Nonparametric Adaptive Point Embedding), which captu…