3D Shape Modeling and Analysis

Últimos artículos

• SAF3R: Dynamic Sparse Attention for Feed-Forward 3D Reconstruction Transformers

  Jianing Deng, Yuanzhe Li, Jialu Wang, Song Wang, Tianlong Chen, Huanrui Yang, Jingtong Hu · 7 de julio de 2026

  Feed-forward 3D reconstruction (F3R) transformers have recently achieved remarkable success. However, scaling them to long image sequences remains challenging, as the quadratic complexity of cross-view global attention quickly becomes the dominant computational bottleneck. While recent efforts attem…

• CGGS: Consistency-Augmented Geometric Gaussian Splatting for Ego-centric 3D Scene Generation

  Zhenyu Sun, Xiaohan Zhang, Qi Liu, Huan Wang · 7 de julio de 2026

  Challenges remain in ego-centric 3D scene generation due to limited view overlap and the dominant influence of individual perspectives on scene interpretation. These factors hinder the creation of viewpoint-consistent and semantically aligned visual content, as well as the construction of accurate g…

• SOV-CAD: Stepwise Orthographic Views Guided CAD Modeling Sequence Reconstruction

  Zhaopeng Feng, Chen Zhi, Xuhong Zhang, Zhengwen Feng, Xinkui Zhao · 7 de julio de 2026

  Reconstructing Computer-Aided Design (CAD) modeling sequences from images is crucial for preserving design intent and supporting parametric editing. However, existing methods typically generate full CAD sequences holistically, overlooking the iterative, feedback-driven nature of human design workflo…

• Text-Driven 3D Indoor Scene Synthesis in Non-Manhattan Environments

  Xianhui Meng, Zirui Song, Yuchen Zhang, Li Zhang, Yongxuan Lv, Xiuying Chen, Kun Wang, Yan Luo, Kai Chen, Hangjun Ye, Long Chen, Jun Liu, Xiaoshuai Hao · 3 de julio de 2026

  Large Language Models (LLMs) have demonstrated remarkable capabilities in 3D indoor synthesis for Manhattan environments. However, existing methods often fail to capture plausible object layout patterns in non-Manhattan settings, primarily because they struggle to model non-orthogonal spatial relati…

• Benchmarking Federated Learning and Knowledge Distillation for Point Cloud Classification

  Aizierjiang Aiersilan · 3 de julio de 2026

  Deploying 3D point cloud analysis in privacy-sensitive, resource-constrained settings faces two barriers: data cannot be centralized, and models must run on limited edge hardware. We present a multi-seed benchmark jointly evaluating federated learning (FL) and knowledge distillation (KD) for 3D poin…

• Learning 3D-Gaussian Simulators from RGB Videos

  Mikel Zhobro, Andreas Ren\'e Geist, Georg Martius · 3 de julio de 2026

  Realistic simulation is critical for applications ranging from robotics to animation. Learned simulators have emerged as a possibility to capture real world physics directly from video data, but very often require privileged information such as depth information, particle tracks and hand-engineered …

• RGB-Pointmap Pretraining for Unified 3D Scene Understanding

  Ye Mao, Weixun Luo, Ranran Huang, Junpeng Jing, Krystian Mikolajczyk · 3 de julio de 2026

  Pretraining 3D encoders through alignment with Contrastive Language-Image Pre-training (CLIP) has emerged as a promising direction for learning generalizable representations for 3D scene understanding. In this paper, we propose UniScene3D, a transformer-based framework that learns unified 3D scene r…

• Group-Equivariant Poincar\'e Convolutional Networks

  Aiden Durrant, Rahul Baburajan, Georgios Leontidis · 2 de julio de 2026

  While recent advancements like the Poincar\'e ResNet have demonstrated the potential of learning visual representations directly in hyperbolic space, their optimisation remains hampered by the computationally intensive nature of Riemannian gradients and the strict boundaries of the manifold. Further…

• Efficient Compression of Structured and Unstructured Volumes via Learned 3D Gaussian Representation

  Landon Dyken, Sharmistha Chakrabarti, Nathan Debardeleben, Steve Petruzza, Qi Wu, Will Usher, Sidharth Kumar · 2 de julio de 2026

  Recent work has shown that implicit neural representations (INRs) can be trained to effectively compress structured and unstructured volume data, allowing for direct data querying with a reduced memory footprint. However, as existing INRs for unstructured volumes do not encode geometry, they require…

• Cross4D-JEPA: Dense Cross-modal Correspondence Distillation for 4D Point Cloud Representation Learning

  Trung Thanh Nguyen, Hai Nguyen-Truong, Tu Vo, Hoang M. Truong, Tuan-Anh Vu · 2 de julio de 2026

  Automatic understanding of dynamic 4D point clouds, the 3D-point sequences captured over time by depth sensors and LiDAR, is central to robotics and embodied perception. Yet annotating them densely is expensive, making self-supervised pretraining the natural route to transferable representations. Ex…

• Improving Sparse-View 3DGS Generalization via Flat Minima Optimization

  Kangmin Seo, Sangeek Hyun, MinKyu Lee, Jae-Pil Heo · 2 de julio de 2026

  Recent advances in neural rendering have established 3D Gaussian Splatting (3DGS) as a highly efficient representation for novel view synthesis, enabling fast training and real-time rendering with strong fidelity. However, when supervision is limited to sparse input views, 3DGS tends to overfit to t…

• DeWorldSG: Depth-Aware 3D Semantic Scene Graph Generation via World-Model Priors

  Seok-Young Kim, Abdelrahman Elskhawy, Taewook Ha, Dooyoung Kim, Eunjae Shin, Benjamin Busam, Woontack Woo · 2 de julio de 2026

  We present DeWorldSG, a novel framework that generates spatio-temporally robust 3D Semantic Scene Graphs from RGB-D sequences. Existing methods often struggle to construct reliable 3D scene graphs due to unstable 3D object representations and missing relations caused by frame-wise inference. DeWorld…

• Group-Equivariant Poincar\'e Convolutional Networks

  Aiden Durrant, Rahul Baburajan, Georgios Leontidis · 2 de julio de 2026

  While recent advancements like the Poincar\'e ResNet have demonstrated the potential of learning visual representations directly in hyperbolic space, their optimisation remains hampered by the computationally intensive nature of Riemannian gradients and the strict boundaries of the manifold. Further…

• Personalization as Inverse Planning: Learning Latent Design Intents for Agentic Slide Generation via Structural Denoising

  Tianci Liu, Zihan Dong, Linjun Zhang, Haoyu Wang, jing Gao, Emre Kiciman, Ranveer Chandra, Wei-Ting Chen · 2 de julio de 2026

  Slide design requires personalizing both deck themes and page layouts. Yet, current AI agent-based methods struggle with fine-grained, page-level design. Solely relying on prespecified templates or user verbose instructions, they fail to capture latent design intents, leaving Page-level Slide Person…

• Mitigating Positional Leakage in 3D Masked Autoencoders for Robust Representation Learning

  Xu Yan, Huiqun Wang, Chen Wang, Lei Ren, Di Huang · 1 de julio de 2026

  Masked autoencoding has emerged as a prominent paradigm for self-supervised learning on 3D point clouds, achieving competitive performance across downstream tasks. Unlike its 2D counterpart, 3D masked autoencoding directly reconstructs spatial coordinates, making it inherently susceptible to positio…

• Robust 3D-Masked Part-level Editing in 3D Gaussian Splatting with Regularized Score Distillation Sampling

  Hayeon Kim, Ji Ha Jang, Se Young Chun · 1 de julio de 2026

  Recent advances in 3D neural representations and instance-level editing models have enabled the efficient creation of high-quality 3D content. However, achieving precise local 3D edits remains challenging, especially for Gaussian Splatting, due to inconsistent multi-view 2D part segmentations and in…

• Scalable and Differentiable Point-Cloud Registration Using Maximum Mean Discrepancy

  Rixon Crane, Fahira Afzal Maken, Nicholas Lawrance, Stanislav Funiak, Kasra Khosoussi, Ming Xu, Russell Tsuchida · 29 de junio de 2026

  We present MMD-Reg, a novel correspondence-free approach to point-cloud registration that is differentiable and has linear computational complexity in the number of points. We model registration as a nonlinear least-squares problem based on the Maximum Mean Discrepancy, approximated using random Fou…

• Home3D 1.0: A High-Fidelity Image-to-3D Asset Generation System for Interior Design

  Yiyun Fei, Guoqiu Li, Jin Song, Chuqiao Wu, Delong Wu, Hong Wu, Ziru Zeng, Haohui Chen, YinDong Kong, Jing Li, Qi Wu, Feng Zhang · 29 de junio de 2026

  We present Home3D 1.0, a modular image-to-3D generation system that produces high-quality 3D assets from a single reference image, targeting interior design and e-commerce applications. Given a photograph of a furniture or decor item, the system outputs a mesh with physically-based rendering (PBR) m…

• CoIn: Comprehensive 2D-3D Inpainting with Gaussian Splatting Guidance

  Hana Kim, Minje Kim, Tae-Kyun Kim · 29 de junio de 2026

  3D scene inpainting is essential for reconstructing areas corrupted by occlusions or limited viewpoints. While recent methods leverage Gaussian Splatting (GS) for efficient 3D editing, they often depend on precise multi-view segmentation masks and are inherently constrained to object removal tasks. …

• Deep Learning Approaches for 3D Medical Scene Completion: From Geometric Modeling to Generative Paradigms

  Afifa Khaled, Said Jadid Abdulkadir, Majdy Mohamed Eltayeb Eltahir · 24 de junio de 2026

  Three-dimensional scene completion has evolved as a major problem in computer vision and robotics, and its applications are diverse, including autonomous navigation and augmented reality. In this study, a systematic review has been conducted to compile the research contributions made in the last ten…

• DreamUV: Unwrap Artist-like UV by End-to-End Flow Matching

  Quanyuan Ruan, Jiabao Lei, Xingyi Du, Xifeng Gao · 23 de junio de 2026

  UV parameterization is a fundamental step in 3D content creation, yet producing production-ready UV layouts remains challenging due to the gap between geometric distortion objectives and the stylistic preferences of professional artists. While classical methods optimize handcrafted energy functions,…

• QueryGaussian: Scalable and Training-Free Open-Vocabulary 3D Instance Retrieval

  Xiuyuan Zhu, Ke Lu, Zijie Yang, Chao Yue, Jian Xue, Dongming Zhang · 19 de junio de 2026

  Efficiently retrieving specific 3D instances from large-scale scenes via natural language prompts remains a formidable challenge in multimedia analysis. Existing approaches predominantly follow a "scene-level embedding" paradigm, which requires distilling high-dimensional semantic features into ever…

• CAOA -- Completion-Assisted Object-CAD Alignment

  Hiranya Garbha Kumar, Minhas Kamal, Balakrishnan Prabhakaran · 18 de junio de 2026

  Accurately aligning CAD models to their corresponding objects in indoor RGB-D scans is a central challenge in 3D semantic reconstruction. The task requires estimating a 9-Degree-of-Freedom (DoF) pose-position, rotation, and scale along three axes-but is hindered by noisy and incomplete scans, as wel…

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

  Minhas Kamal, Hiranya Garbha Kumar, Balakrishnan Prabhakaran · 18 de junio de 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…

• Adaptive Volumetric Mechanical Property Fields Invariant to Resolution

  Rishit Dagli, Donglai Xiang, Vismay Modi, Xuning Yang, Gavriel State, David I. W. Levin, Maria Shugrina · 17 de junio de 2026

  Accurate mechanical properties (or materials) Young's modulus ($E$), Poisson's ratio ($\nu$) and density ($\rho$) are essential for reliable physics simulation of digital worlds, but most 3D assets lack this information. We propose AdaVoMP, a method for predicting accurate dense spatially-varying ($…