3D Shape Generation

Follow this topic Ask about this topic

Momentum

8 papers in the last four weeks, with none the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 76

All topics

Position Forcing: Self-Conditioning 3D Generation
Oct 7, 2026Ziheng Ouyang, Zeqiang Lai, Jiarui Chen +73D Shape Generation 3D Diffusion Models
VCIP, Nankai University · Tencent Hunyuan · MMLab, CUHK +3
AnchorGen: Anchored Optimization for Customizable Generative 3D Design
Oct 5, 2026Hantao Zhang, Oliver Heinimann, Jieke Wu +3Constrained Generative Modeling 3D Shape Editing
CVLab, EPFL, Switzerland
SILSA: Sliding-Window Slice Latents for Topology-Preserving High-Resolution 3D Generation
Oct 1, 2026Tianjiao Yu, Xinzhuo Li, Yifan Shen +43D Shape Generation 3D Representation Learning
University of Illinois Urbana-Champaign
Seg3DParts: Segmentation-Grounded Controllable Part-Level 3D Generation
Sep 29, 2026Jiantao Lin, Meixi Chen, Yingjie Xu +53D Mesh Generation Part-Level 3D Generation
The Hong Kong University of Science and Technology (Guangzhou) · Knowin AI · The Hong Kong University of Science and Technology
FILIGREE3D: Scaling Sparse Latent Flow Matching for Ultra-High-Resolution Image-to-3D Generation
Sep 28, 2026Hongjie Li, Xinran Yang, Xiuchao Wu +2Flow Matching 3D ViTs
AlibabaGroup
ReGDiff: Guided Diffusion in Regulated Latent Space for Exploring Metamaterial Voxel Geometry
Sep 28, 2026Wangzhi Zhan, Jianpeng Chen, Dongqi Fu +1Diffusion Guidance Materials Science
Department of Computer Science Virginia Tech Blacksburg, VA 24061 · Meta Menlo Park, CA 94025
NeuralSRNF: Neural Square Root Normal Fields for the Statistical Shape Analysis and Generation of Nonrigid 3D and 4D Objects
Sep 23, 2026Awais Nizamani, Hamid Laga, Guanjin Wang +3Neural Representation Geometry Statistical Shape Modeling
Murdoch University, Perth, Australia · The University of Western Australia, Perth, Australia · The Johns Hopkins University, Maryland, US
KaiNinja: Extending Native 3D Generators to the Part Level
Sep 14, 2026Ruihan Yu, Lian Fu, Muyao Niu +93D Mesh Generation Part-Level 3D Generation
1Alaya Lab 2The University of Tokyo · 1Alaya Lab · 1Alaya Lab 3University of California, Merced +2
ReconPlusGen: Injecting Reconstruction Prior into Multi-view 3D Generation through Noise Inversion and Modulation
Sep 11, 2026Jiarui Liu, Heng Li, Weiyu Li +73D Shape Generation 3D Diffusion Models
HKUST · LightIllusions · BYD +1
Guiding Image-to-3D Generation with Test-Time Partial Observations
Sep 9, 2026Jerred Chen, Simon Weber, Ronald Clark3D Asset Generation 3D Shape Generation
University of Oxford
Flow-Corrected Shape Optimization: Taming Manifold Drift in High-Dimensional 3D Models
Aug 7, 2026Emilien Seiler, Nicolas Talabot, Yingxuan You +2Constrained Generative Modeling 3D Shape Generation
CVLab, EPFL
Hierarchical Flow Matching for 3D Point Cloud Generation
Aug 6, 2026Linhao Wang, Qichang Zhang, Ye Su +1Flow Matching 3D Shape Generation
Shandong Normal University · University of Macau
Learning to Tessellate: Point Cloud Generation via Recursive Spectral Partitioning
Aug 3, 2026Monan Sun, Bangzhen Liu, Huaidong Zhang +1Point Cloud Learning 3D Shape Generation
South China University of Technology, China · University of Chinese Academy of Sciences, China · Singapore Management University, Singapore +1
RL-Lock: Reinforcement Learning for Generating Interlocking Assemblies
Aug 3, 2026Xuyang Ma, Chaewoon Kim, Haonan Zhang +33D Shape Generation RL for Combinatorial Optimization
Singapore University of Technology and Design · The Hong Kong University of Science and Technology · Beijing Normal-Hong Kong Baptist University
ROAD: Reciprocal-Objective Alignment of Discriminative Semantics for 3D Shape Generation
Jul 30, 2026Xiao Luo, Mingyang Du, Xin Zhou +5Diffusion Model Alignment 3D Shape Generation
Huazhong University of Science and Technology, China · 2Megvii, China · 3Zhejiang University, China +1
FPSGen: Flexible Point Cloud Scene Generation with BEV-Supported Transport Flows
Jul 29, 2026Wenzhe He, Meng Wang, JiaWei Qian +3Point Cloud Completion 3D Scene Generation
College of Computer Science and Electronic Engineering, Hunan University, Hunan, China · College of Information Science and Engineering, Hunan Normal University, Hunan, China
UMI3D: Robust 3D Generation on Unconstrained Multi-Image Inputs via Simultaneous Focus Cross-Attention Routing
Jul 27, 2026Zefan Qu, Zhenwei Wang, Gerhard Petrus Hancke +13D Foundation Models Cross-Attention
Department of Computer Science City University of Hong Kong
Axolotl3D: a Unified Framework for Faithful 3D Shape Completion
Jul 22, 2026Anita Hu, Maria Shugrina3D Reconstruction Multi-View 3D Reconstruction
NVIDIA
Autoregressive B-Rep Shape Generation with Parametric Surfaces
Jul 19, 2026Dafei Qin, Rui Xu, Zeyu Shen +8Parametric CAD Modeling 3D Shape Generation
The University of Hong Kong, Deemos Technology Co., Ltd., China · Institute of Software, Chinese Academy of Sciences, China · ShanghaiTech University, Deemos Technology Co., Ltd., China +3
Nexus: Native Mesh Generation with Diffusion
Jul 15, 2026Hanxiao Wang, Ying-Tian Liu, Yuan-Chen Guo +53D Mesh Generation 3D Shape Generation
MAIS, Institute of Automation, Chinese Academy of Sciences; School of Artificial Intelligence, University of Chinese Academy of Sciences, China · VAST, China · Tsinghua University, China +1
TreeSRNF: Square-Root Normal Fields for Generative Modelling of the Geometric and Structural Variability in Tree-like 3D Objects
Jul 15, 2026Tahmina Khanam, Hamid Laga, Mohammed Bennamoun +4Statistical Shape Modeling Non-Rigid Shape Correspondence
Murdoch University, WA, Australia. · University of Western Australia, WA, Australia. · Johns Hopkins University, USA.
DiffGI: Differentiable Geometry Images for High-Fidelity Thin-Shell 3D Generation
Jul 15, 2026Eungjune Shim, Hansol Lee, Eunjung Ju3D Mesh Generation 3D Shape Generation
CLO Virtual Fashion Inc., South Korea
Compos3D: Interactive Part-Based Composition for Creative Control in Generative 3D Models
Jul 13, 2026Faraz Faruqi, Sean J. Liu, George Fitzmaurice +13D Asset Generation 3D Shape Editing
Autodesk Research Boston, MA, USA · Autodesk Research San Francisco, California, USA · Autodesk Research Toronto, Ontario, Canada
LATO.2: Factorized 3D Mesh Generation with Vertex and Topology Flow
Jul 12, 2026Hang Long, Tianhao Zhao, Junkai Lin +7Flow Matching 3D Mesh Generation
Huazhong University of Science and Technology · Meshy AI · Independent Researcher +1
Mirror Illusion Art
Jul 2, 2026Xiaopei Zhu, Zeyuan Li, Jun Zhu +1Inverse Rendering 3D Asset Generation
Department of Computer Science and Technology, BNRist, Tsinghua University · Huazhong University of Science and Technology · IDG/McGovern Institute for Brain Research, Tsinghua University +1
Vitality-Aware Compression for Efficient Image-to-Shape Diffusion Transformers
Jul 1, 2026Jaeah Lee, Hyunjin Kim, Jaewoong Cho +1Model Compression Diffusion Transformer
KRAFTON AI, Republic of Korea · Amazon, Australia
Deep Spectral Models for Robust Dental Shape Generation
Jun 30, 2026Tibor Kubík, François Guibault, Michal Španěl +1Geometric Representation Learning Generative Modeling
Polytechnique Montr´eal, Montr´eal, Canada · Brno University of Technology, Brno, Czech Republic
Sculpting NeRF Geometry: Human-Preference Fine-Tuning of a 3D-Aware Face GAN
Jun 25, 2026Archer Moore, Mingming Gong, Liam Hodgkinson3D Shape Generation RL for Generative Models
School of Mathematics and Statistics, The University of Melbourne, Parkville, VIC 3010, Australia
ISAP-3D: Identity-Slot Aligned Part-Aware 3D Generation
Jun 10, 2026Junlin Hao, Haoshuai Fu, Xibin Song +4Part-Level 3D Generation Generative Modeling
No Institute Given
3D-CBM: A Framework for Concept-Based Interpretability in Generative 3D Modeling
Jun 9, 2026Ahmad Al-KabbanyConcept Bottleneck Models Interpretable ML
Yubree Labs, Ottawa K2M1T2, Canada · Multimedia Interaction and Communication Lab, Arab Academy for Science and Technology, Alexandria 21937, Egypt

Oct 7, 2026, cs.CVJ/K move · Enter open · S save

Position Forcing: Self-Conditioning 3D Generation

Ziheng Ouyang, Zeqiang Lai, Jiarui Chen, Jiangshan Wang+6

VCIP, Nankai University · Tencent Hunyuan · MMLab, CUHK+3

3D Shape Generation 3D Diffusion Models Diffusion Model Guidance Conditional Diffusion Models

Open paper AskPDF arXiv

Recent single-stage 3D generative models commonly adopt VecSet representations, encoding 3D shapes as unordered sets of latent tokens. However, compared with two-stage methods that provide explicit positional guidance, these models must implicitly infer token positions throughout denoising, limiting their generation quality. We observe that, despite the absence of explicit positional conditioning, VecSet tokens retain recoverable spatial correspondences. Building on this observation, we propose Position Forcing, a position-based self-conditioning framework. During denoising, Position Forcing recovers token positions from the current clean latent estimate, quantizes them at progressively finer resolutions according to the denoising stage, and feeds the resulting positional encodings back into the diffusion Transformer. This progressively refined positional feedback provides spatial guidance at a granularity appropriate to each denoising stage, guiding shape generation along a coarse-to-fine trajectory and substantially improving generation quality without a separate position generation stage. Experiments demonstrate that Position Forcing achieves strong performance among single-stage 3D generative methods and outperforms several competitive multi-stage approaches.

Momentum

Related topics

Latest papers 76