3D Shape Modeling and Analysis

Latest papers

• ERGO: Excess-Risk-Guided Optimization for High-Fidelity Monocular 3D Gaussian Splatting

  Zehua Ma, Hanhui Li, Zhenyu Xie, Xiaonan Luo, Michael Kampffmeyer, Feng Gao, Xiaodan Liang · 12 February 2026

  Generating 3D content from a single image remains a fundamentally challenging and ill-posed problem due to the inherent absence of geometric and textural information in occluded regions. While state-of-the-art generative models can synthesize auxiliary views to provide additional supervision, these …

• LighthouseGS: Indoor Structure-aware 3D Gaussian Splatting for Panorama-Style Mobile Captures

  Seungoh Han, Jaehoon Jang, Hyunsu Kim, Jaeheung Surh, Junhyung Kwak, Hyowon Ha, Kyungdon Joo · 12 February 2026

  We introduce LighthouseGS, a practical novel view synthesis framework based on 3D Gaussian Splatting that utilizes simple panorama-style captures from a single mobile device. While convenient, this rotation-dominant motion and narrow baseline make accurate camera pose and 3D point estimation challen…

• Learning on the Manifold: Unlocking Standard Diffusion Transformers with Representation Encoders

  Amandeep Kumar, Vishal M. Patel · 11 February 2026

  Leveraging representation encoders for generative modeling offers a path for efficient, high-fidelity synthesis. However, standard diffusion transformers fail to converge on these representations directly. While recent work attributes this to a capacity bottleneck proposing computationally expensive…

• Free-Boundary Quasiconformal Maps via a Least-squares Operator in Diffeomorphism Optimization

  Zhehao Xu, Lok Ming Lui · 11 February 2026

  Free-boundary diffeomorphism optimization, an important and widely occurring task in geometric modeling, computer graphics, and biological imaging, requires simultaneously determining a planar target domain and a locally bijective map with well-controlled distortion. We formulate this task through t…

• Analysis of Converged 3D Gaussian Splatting Solutions: Density Effects and Prediction Limit

  Zhendong Wang, Cihan Ruan, Jingchuan Xiao, Chuqing Shi, Wei Jiang, Wei Wang, Wenjie Liu, Nam Ling · 10 February 2026

  We investigate what structure emerges in 3D Gaussian Splatting (3DGS) solutions from standard multi-view optimization. We term these Rendering-Optimal References (RORs) and analyze their statistical properties, revealing stable patterns: mixture-structured scales and bimodal radiance across diverse …

• Scalable Adaptation of 3D Geometric Foundation Models via Weak Supervision from Internet Video

  Zihui Gao, Ke Liu, Donny Y. Chen, Duochao Shi, Guosheng Lin, Hao Chen, Chunhua Shen · 10 February 2026

  Geometric foundation models show promise in 3D reconstruction, yet their progress is severely constrained by the scarcity of diverse, large-scale 3D annotations. While Internet videos offer virtually unlimited raw data, utilizing them as a scaling source for geometric learning is challenging due to …

• Brep2Shape: Boundary and Shape Representation Alignment via Self-Supervised Transformers

  Yuanxu Sun, Yuezhou Ma, Haixu Wu, Guanyang Zeng, Muye Chen, Jianmin Wang, Mingsheng Long · 10 February 2026

  Boundary representation (B-rep) is the industry standard for computer-aided design (CAD). While deep learning shows promise in processing B-rep models, existing methods suffer from a representation gap: continuous approaches offer analytical precision but are visually abstract, whereas discrete meth…

• Picasso: Holistic Scene Reconstruction with Physics-Constrained Sampling

  Xihang Yu, Rajat Talak, Lorenzo Shaikewitz, Luca Carlone · 10 February 2026

  In the presence of occlusions and measurement noise, geometrically accurate scene reconstructions -- which fit the sensor data -- can still be physically incorrect. For instance, when estimating the poses and shapes of objects in the scene and importing the resulting estimates into a simulator, smal…

• Approximating Signed Distance Fields With Sparse Ellipsoidal Radial Basis Function Networks: A Dynamic Multi-Objective Optimization Strategy

  Bobo Lian, Zidong Wang, Dandan Wang, Chenjian Wu, Minxin Chen · 10 February 2026

  Accurate and compact representation of signed distance functions (SDFs) of implicit surfaces is crucial for efficient storage, computation, and downstream processing of 3D geometry. In this work, we propose a general learning method for approximating precomputed SDF fields of implicit surfaces by a …

• VecSet-Edit: Unleashing Pre-trained LRM for Mesh Editing from Single Image

  Teng-Fang Hsiao, Bo-Kai Ruan, Yu-Lun Liu, Hong-Han Shuai · 5 February 2026

  3D editing has emerged as a critical research area to provide users with flexible control over 3D assets. While current editing approaches predominantly focus on 3D Gaussian Splatting or multi-view images, the direct editing of 3D meshes remains underexplored. Prior attempts, such as VoxHammer, rely…

• Two-chart Beltrami Optimization for Distortion-Controlled Spherical Bijection with Application to Brain Surface Registration

  Zhehao Xu, Lok Ming Lui · 5 February 2026

  Many genus-0 surface mapping tasks such as landmark alignment, feature matching, and image-driven registration, can be reduced (via an initial spherical conformal map) to optimizing a spherical self-homeomorphism with controlled distortion. However, existing works lack efficient mechanisms to contro…

• SkeletonGaussian: Editable 4D Generation through Gaussian Skeletonization

  Lifan Wu, Ruijie Zhu, Yubo Ai, Tianzhu Zhang · 5 February 2026

  4D generation has made remarkable progress in synthesizing dynamic 3D objects from input text, images, or videos. However, existing methods often represent motion as an implicit deformation field, which limits direct control and editability. To address this issue, we propose SkeletonGaussian, a nove…

• Skin Tokens: A Learned Compact Representation for Unified Autoregressive Rigging

  Jia-peng Zhang, Cheng-Feng Pu, Meng-Hao Guo, Yan-Pei Cao, Shi-Min Hu · 5 February 2026

  The rapid proliferation of generative 3D models has created a critical bottleneck in animation pipelines: rigging. Existing automated methods are fundamentally limited by their approach to skinning, treating it as an ill-posed, high-dimensional regression task that is inefficient to optimize and is …

• HY3D-Bench: Generation of 3D Assets

  Team Hunyuan3D, :, Bowen Zhang, Chunchao Guo, Dongyuan Guo, Haolin Liu, Hongyu Yan, Huiwen Shi, Jiaao Yu, Jiachen Xu, Jingwei Huang, Kunhong Li, Lifu Wang, Linus, Penghao Wang, Qingxiang Lin, Ruining Tang, Xianghui Yang, Yang Li, Yirui Guan, Yunfei Zhao, Yunhan Yang, Zeqiang Lai, Zhihao Liang, Zibo Zhao · 5 February 2026

  While recent advances in neural representations and generative models have revolutionized 3D content creation, the field remains constrained by significant data processing bottlenecks. To address this, we introduce HY3D-Bench, an open-source ecosystem designed to establish a unified, high-quality fo…

• Clarify Before You Draw: Proactive Agents for Robust Text-to-CAD Generation

  Bo Yuan, Zelin Zhao, Petr Molodyk, Bin Hu, Yongxin Chen · 4 February 2026

  Large language models have recently enabled text-to-CAD systems that synthesize parametric CAD programs (e.g., CadQuery) from natural language prompts. In practice, however, geometric descriptions can be under-specified or internally inconsistent: critical dimensions may be missing and constraints m…

• Riemannian Neural Optimal Transport

  Alessandro Micheli, Yueqi Cao, Anthea Monod, Samir Bhatt · 4 February 2026

  Computational optimal transport (OT) offers a principled framework for generative modeling. Neural OT methods, which use neural networks to learn an OT map (or potential) from data in an amortized way, can be evaluated out of sample after training, but existing approaches are tailored to Euclidean g…

• NPNet: A Non-Parametric Network with Adaptive Gaussian-Fourier Positional Encoding for 3D Classification and Segmentation

  Mohammad Saeid, Amir Salarpour, Pedram MohajerAnsari, Mert D. Pes\'e · 3 February 2026

  We present NPNet, a fully non-parametric approach for 3D point-cloud classification and part segmentation. NPNet contains no learned weights; instead, it builds point features using deterministic operators such as farthest point sampling, k-nearest neighbors, and pooling. Our key idea is an adaptive…

• CloDS: Visual-Only Unsupervised Cloth Dynamics Learning in Unknown Conditions

  Yuliang Zhan, Jian Li, Wenbing Huang, Wenbing Huang, Yang Liu, Hao Sun · 3 February 2026

  Deep learning has demonstrated remarkable capabilities in simulating complex dynamic systems. However, existing methods require known physical properties as supervision or inputs, limiting their applicability under unknown conditions. To explore this challenge, we introduce Cloth Dynamics Grounding …

• Genus-0 Surface Parameterization using Spherical Beltrami Differentials

  Zhehao Xu, Lok Ming Lui · 3 February 2026

  Spherical surface parameterization is a fundamental tool in geometry processing and imaging science. For a genus-0 closed surface, many efficient algorithms can map the surface to the sphere; consequently, a broad class of task-driven genus-0 mapping problems can be reduced to constructing a high-qu…

• Implicit neural representation of textures

  Albert Kwok, Zheyuan Hu, Dounia Hammou · 3 February 2026

  Implicit neural representation (INR) has proven to be accurate and efficient in various domains. In this work, we explore how different neural networks can be designed as a new texture INR, which operates in a continuous manner rather than a discrete one over the input UV coordinate space. Through t…

• SurfSplat: Conquering Feedforward 2D Gaussian Splatting with Surface Continuity Priors

  Bing He, Jingnan Gao, Yunuo Chen, Ning Cao, Gang Chen, Zhengxue Cheng, Li Song, Wenjun Zhang · 3 February 2026

  Reconstructing 3D scenes from sparse images remains a challenging task due to the difficulty of recovering accurate geometry and texture without optimization. Recent approaches leverage generalizable models to generate 3D scenes using 3D Gaussian Splatting (3DGS) primitive. However, they often fail …

• VideoGPA: Distilling Geometry Priors for 3D-Consistent Video Generation

  Hongyang Du, Junjie Ye, Xiaoyan Cong, Runhao Li, Jingcheng Ni, Aman Agarwal, Zeqi Zhou, Zekun Li, Randall Balestriero, Yue Wang · 2 February 2026

  While recent video diffusion models (VDMs) produce visually impressive results, they fundamentally struggle to maintain 3D structural consistency, often resulting in object deformation or spatial drift. We hypothesize that these failures arise because standard denoising objectives lack explicit ince…

• Disentangling perception and reasoning for improving data efficiency in learning cloth manipulation without demonstrations

  Donatien Delehelle, Fei Chen, Darwin Caldwell · 30 January 2026

  Cloth manipulation is a ubiquitous task in everyday life, but it remains an open challenge for robotics. The difficulties in developing cloth manipulation policies are attributed to the high-dimensional state space, complex dynamics, and high propensity to self-occlusion exhibited by fabrics. As ana…

• Geodesic Calculus on Implicitly Defined Latent Manifolds

  Florine Hartwig, Josua Sassen, Juliane Braunsmann, Martin Rumpf, Benedikt Wirth · 30 January 2026

  Latent manifolds of autoencoders provide low-dimensional representations of data, which can be studied from a geometric perspective. We propose to describe these latent manifolds as implicit submanifolds of some ambient latent space. Based on this, we develop tools for a discrete Riemannian calculus…

• Equivariant Flow Matching for Point Cloud Assembly

  Ziming Wang, Nan Xue, Rebecka J\"ornsten · 27 January 2026

  The goal of point cloud assembly is to reconstruct a complete 3D shape by aligning multiple point cloud pieces. This work presents a novel equivariant solver for assembly tasks based on flow matching models. We first theoretically show that the key to learning equivariant distributions via flow matc…