3D Shape Modeling and Analysis

Últimos artículos

• Particulate: Feed-Forward 3D Object Articulation

  Ruining Li, Yuxin Yao, Chuanxia Zheng, Christian Rupprecht, Joan Lasenby, Shangzhe Wu, Andrea Vedaldi · 15 de diciembre de 2025

  We present Particulate, a feed-forward approach that, given a single static 3D mesh of an everyday object, directly infers all attributes of the underlying articulated structure, including its 3D parts, kinematic structure, and motion constraints. At its core is a transformer network, Part Articulat…

• DOS: Distilling Observable Softmaps of Zipfian Prototypes for Self-Supervised Point Representation

  Mohamed Abdelsamad, Michael Ulrich, Bin Yang, Miao Zhang, Yakov Miron, Abhinav Valada · 15 de diciembre de 2025

  Recent advances in self-supervised learning (SSL) have shown tremendous potential for learning 3D point cloud representations without human annotations. However, SSL for 3D point clouds still faces critical challenges due to irregular geometry, shortcut-prone reconstruction, and unbalanced semantics…

• CADKnitter: Compositional CAD Generation from Text and Geometry Guidance

  Tri Le, Khang Nguyen, Baoru Huang, Tung D. Ta, Anh Nguyen · 15 de diciembre de 2025

  Crafting computer-aided design (CAD) models has long been a painstaking and time-intensive task, demanding both precision and expertise from designers. With the emergence of 3D generation, this task has undergone a transformative impact, shifting not only from visual fidelity to functional utility b…

• Are We Ready for RL in Text-to-3D Generation? A Progressive Investigation

  Yiwen Tang, Zoey Guo, Kaixin Zhu, Ray Zhang, Qizhi Chen, Dongzhi Jiang, Junli Liu, Bohan Zeng, Haoming Song, Delin Qu, Tianyi Bai, Dan Xu, Wentao Zhang, Bin Zhao · 12 de diciembre de 2025

  Reinforcement learning (RL), earlier proven to be effective in large language and multi-modal models, has been successfully extended to enhance 2D image generation recently. However, applying RL to 3D generation remains largely unexplored due to the higher spatial complexity of 3D objects, which req…

• SceneMaker: Open-set 3D Scene Generation with Decoupled De-occlusion and Pose Estimation Model

  Yukai Shi, Weiyu Li, Zihao Wang, Hongyang Li, Xingyu Chen, Ping Tan, Lei Zhang · 12 de diciembre de 2025

  We propose a decoupled 3D scene generation framework called SceneMaker in this work. Due to the lack of sufficient open-set de-occlusion and pose estimation priors, existing methods struggle to simultaneously produce high-quality geometry and accurate poses under severe occlusion and open-set settin…

• Learning Generalizable Shape Completion with SIM(3) Equivariance

  Yuqing Wang, Zhaiyu Chen, Xiao Xiang Zhu · 12 de diciembre de 2025

  3D shape completion methods typically assume scans are pre-aligned to a canonical frame. This leaks pose and scale cues that networks may exploit to memorize absolute positions rather than inferring intrinsic geometry. When such alignment is absent in real data, performance collapses. We argue that …

• WonderZoom: Multi-Scale 3D World Generation

  Jin Cao, Hong-Xing Yu, Jiajun Wu · 11 de diciembre de 2025

  We present WonderZoom, a novel approach to generating 3D scenes with contents across multiple spatial scales from a single image. Existing 3D world generation models remain limited to single-scale synthesis and cannot produce coherent scene contents at varying granularities. The fundamental challeng…

• mini-vec2vec: Scaling Universal Geometry Alignment with Linear Transformations

  Guy Dar · 9 de diciembre de 2025

  We build upon vec2vec, a procedure designed to align text embedding spaces without parallel data. vec2vec finds a near-perfect alignment, but it is expensive and unstable. We present mini-vec2vec, a simple and efficient alternative that requires substantially lower computational cost and is highly r…

• SpaceControl: Introducing Test-Time Spatial Control to 3D Generative Modeling

  Elisabetta Fedele, Francis Engelmann, Ian Huang, Or Litany, Marc Pollefeys, Leonidas Guibas · 8 de diciembre de 2025

  Generative methods for 3D assets have recently achieved remarkable progress, yet providing intuitive and precise control over the object geometry remains a key challenge. Existing approaches predominantly rely on text or image prompts, which often fall short in geometric specificity: language can be…

• KeyPointDiffuser: Unsupervised 3D Keypoint Learning via Latent Diffusion Models

  Rhys Newbury, Juyan Zhang, Tin Tran, Hanna Kurniawati, Dana Kuli\'c · 4 de diciembre de 2025

  Understanding and representing the structure of 3D objects in an unsupervised manner remains a core challenge in computer vision and graphics. Most existing unsupervised keypoint methods are not designed for unconditional generative settings, restricting their use in modern 3D generative pipelines; …

• EGGS: Exchangeable 2D/3D Gaussian Splatting for Geometry-Appearance Balanced Novel View Synthesis

  Yancheng Zhang, Guangyu Sun, Chen Chen · 3 de diciembre de 2025

  Novel view synthesis (NVS) is crucial in computer vision and graphics, with wide applications in AR, VR, and autonomous driving. While 3D Gaussian Splatting (3DGS) enables real-time rendering with high appearance fidelity, it suffers from multi-view inconsistencies, limiting geometric accuracy. In c…

• HouseLayout3D: A Benchmark and Training-Free Baseline for 3D Layout Estimation in the Wild

  Valentin Bieri, Marie-Julie Rakotosaona, Keisuke Tateno, Francis Engelmann, Leonidas Guibas · 3 de diciembre de 2025

  Current 3D layout estimation models are primarily trained on synthetic datasets containing simple single room or single floor environments. As a consequence, they cannot natively handle large multi floor buildings and require scenes to be split into individual floors before processing, which removes…

• Rendering-Aware Reinforcement Learning for Vector Graphics Generation

  Juan A. Rodriguez, Haotian Zhang, Abhay Puri, Aarash Feizi, Rishav Pramanik, Pascal Wichmann, Arnab Mondal, Mohammad Reza Samsami, Rabiul Awal, Perouz Taslakian, Spandana Gella, Sai Rajeswar, David Vazquez, Christopher Pal, Marco Pedersoli · 2 de diciembre de 2025

  Scalable Vector Graphics (SVG) offer a powerful format for representing visual designs as interpretable code. Recent advances in vision-language models (VLMs) have enabled high-quality SVG generation by framing the problem as a code generation task and leveraging large-scale pretraining. VLMs are pa…

• Rethinking Multimodal Point Cloud Completion: A Completion-by-Correction Perspective

  Wang Luo, Di Wu, Hengyuan Na, Yinlin Zhu, Miao Hu, Guocong Quan · 2 de diciembre de 2025

  Point cloud completion aims to reconstruct complete 3D shapes from partial observations, which is a challenging problem due to severe occlusions and missing geometry. Despite recent advances in multimodal techniques that leverage complementary RGB images to compensate for missing geometry, most meth…

• SDFs from Unoriented Point Clouds using Neural Variational Heat Distances

  Samuel Weidemaier, Florine Hartwig, Josua Sassen, Sergio Conti, Mirela Ben-Chen, Martin Rumpf · 1 de diciembre de 2025

  We propose a novel variational approach for computing neural Signed Distance Fields (SDF) from unoriented point clouds. To this end, we replace the commonly used eikonal equation with the heat method, carrying over to the neural domain what has long been standard practice for computing distances on …

• PointMapPolicy: Structured Point Cloud Processing for Multi-Modal Imitation Learning

  Xiaogang Jia, Qian Wang, Anrui Wang, Han A. Wang, Bal\'azs Gyenes, Emiliyan Gospodinov, Xinkai Jiang, Ge Li, Hongyi Zhou, Weiran Liao, Xi Huang, Maximilian Beck, Moritz Reuss, Rudolf Lioutikov, Gerhard Neumann · 1 de diciembre de 2025

  Robotic manipulation systems benefit from complementary sensing modalities, where each provides unique environmental information. Point clouds capture detailed geometric structure, while RGB images provide rich semantic context. Current point cloud methods struggle to capture fine-grained detail, es…

• Yo'City: Personalized and Boundless 3D Realistic City Scene Generation via Self-Critic Expansion

  Keyang Lu, Sifan Zhou, Hongbin Xu, Gang Xu, Zhifei Yang, Yikai Wang, Zhen Xiao, Jieyi Long, Ming Li · 1 de diciembre de 2025

  Realistic 3D city generation is fundamental to a wide range of applications, including virtual reality and digital twins. However, most existing methods rely on training a single diffusion model, which limits their ability to generate personalized and boundless city-scale scenes. In this paper, we p…

• DensiCrafter: Physically-Constrained Generation and Fabrication of Self-Supporting Hollow Structures

  Shengqi Dang, Fu Chai, Jiaxin Li, Chao Yuan, Wei Ye, Nan Cao · 27 de noviembre de 2025

  The rise of 3D generative models has enabled automatic 3D geometry and texture synthesis from multimodal inputs (e.g., text or images). However, these methods often ignore physical constraints and manufacturability considerations. In this work, we address the challenge of producing 3D designs that a…

• PointNSP: Autoregressive 3D Point Cloud Generation with Next-Scale Level-of-Detail Prediction

  Ziqiao Meng, Qichao Wang, Zhiyang Dou, Zixing Song, Zhipeng Zhou, Irwin King, Peilin Zhao · 27 de noviembre de 2025

  Autoregressive point cloud generation has long lagged behind diffusion-based approaches in quality. The performance gap stems from the fact that autoregressive models impose an artificial ordering on inherently unordered point sets, forcing shape generation to proceed as a sequence of local predicti…

• $\Delta$-NeRF: Incremental Refinement of Neural Radiance Fields through Residual Control and Knowledge Transfer

  Kriti Ghosh, Devjyoti Chakraborty, Lakshmish Ramaswamy, Suchendra M. Bhandarkar, In Kee Kim, Nancy O'Hare, Deepak Mishra · 27 de noviembre de 2025

  Neural Radiance Fields (NeRFs) have demonstrated remarkable capabilities in 3D reconstruction and novel view synthesis. However, most existing NeRF frameworks require complete retraining when new views are introduced incrementally, limiting their applicability in domains where data arrives sequentia…

• Accelerating Sparse Convolutions in Voxel-Based Point Cloud Networks

  Dionysios Adamopoulos, Anastasia Poulopoulou, Georgios Goumas, Christina Giannoula · 27 de noviembre de 2025

  Sparse Convolution (SpC) powers 3D point cloud networks widely used in autonomous driving and AR/VR. 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 coordinates. Our work id…

• Foundry: Distilling 3D Foundation Models for the Edge

  Guillaume Letellier (IIT Delhi), Siddharth Srivastava (IIT Delhi), Fr\'ed\'eric Jurie (IIT Kanpur), Gaurav Sharma (IIT Kanpur) · 27 de noviembre de 2025

  Foundation models pre-trained with self-supervised learning (SSL) on large-scale datasets have become powerful general-purpose feature extractors. However, their immense size and computational cost make them prohibitive for deployment on edge devices such as robots and AR/VR headsets. Existing compr…

• VibraVerse: A Large-Scale Geometry-Acoustics Alignment Dataset for Physically-Consistent Multimodal Learning

  Bo Pang, Chenxi Xu, Jierui Ren, Guoping Wang, Sheng Li · 26 de noviembre de 2025

  Understanding the physical world requires perceptual models grounded in physical laws rather than mere statistical correlations. However, existing multimodal learning frameworks, focused on vision and language, lack physical consistency and overlook the intrinsic causal relationships among an object…

• MFM-point: Multi-scale Flow Matching for Point Cloud Generation

  Petr Molodyk, Jaemoo Choi, David W. Romero, Ming-Yu Liu, Yongxin Chen · 26 de noviembre de 2025

  In recent years, point cloud generation has gained significant attention in 3D generative modeling. Among existing approaches, point-based methods directly generate point clouds without relying on other representations such as latent features, meshes, or voxels. These methods offer low training cost…

• MeshSplat: Generalizable Sparse-View Surface Reconstruction via Gaussian Splatting

  Hanzhi Chang, Ruijie Zhu, Wenjie Chang, Mulin Yu, Yanzhe Liang, Jiahao Lu, Zhuoyuan Li, Tianzhu Zhang · 26 de noviembre de 2025

  Surface reconstruction has been widely studied in computer vision and graphics. However, existing surface reconstruction works struggle to recover accurate scene geometry when the input views are extremely sparse. To address this issue, we propose MeshSplat, a generalizable sparse-view surface recon…