3D Diffusion Models

Follow this topic Ask about this topic

Momentum

14 papers in the last four weeks, up 250% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 54

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
Unified Multi-plane Autoregressive Diffusion for 3D Multi-contrast MRI Synthesis
Oct 7, 2026Yejee Shin, Geonhui Son, Jinglu Wang +3Medical Image Synthesis 3D Diffusion Models
Yonsei University · Microsoft Research Asia · Korea Institute of Science and Technology
DecomVoxel: Harnessing 3D-Native Priors with Guided In-situ Denoising Optimization for Decompositional Scene Reconstruction
Oct 1, 2026Junfeng Ni, Zirui Zhou, Yixin Chen +53D Reconstruction 3D Mesh Reconstruction
Tsinghua University, State Key Laboratory of General Artificial Intelligence, BIGAI, China · Peking University, China
BTC3D: Blended Tile Conditioning for Detail-Enhancing Image-to-3D Generation
Sep 30, 2026Junyu Li, Qiuyu Chen, Pengcheng Wang +5Diffusion Model Guidance 3D Diffusion Models
City University of Hong Kong (Dongguan) · SB Intuitions Corp. · Universitat Autònoma de Barcelona
GeoVerse: World-Consistent Novel View Synthesis in Geometric Latent Space
Sep 28, 2026Kerui Ren, Tao Lu, Linning Xu +5Multi-View Consistency Novel View Synthesis
Shanghai Jiao Tong University · Shanghai Artificial Intelligence Laboratory · The Chinese University of Hong Kong +3
Does Native 3D Texture Generation Necessarily Require 3D Assets for Training?
Sep 28, 2026Jiangshan Wang, Zeqiang Lai, Jiayi Guo +63D Asset Generation 3D Diffusion Models
MMLab, CUHK · Tencent Hunyuan · Tsinghua University +3
EMERGE: Resolution-Agnostic Point Cloud Generation with Equivariant Graph-Based Diffusion
Sep 22, 2026Ilias Mitsouras, Nikolaos Chaidos, Giorgos Stamou +1Graph Neural Networks Equivariant Neural Networks
National Technical University of Athens Athens, Greece
ZVeC: A Zero-Shot Framework for Instance-Level Vehicle Extraction and Generative Point Cloud Completion
Sep 21, 2026Daisy Li, Kyle Gao, Quanyun Wu +3Point Cloud Completion 3D Scene Completion
University of Waterloo · Karlsruhe Institute of Technology
Learning Foresight without Explicit Trajectories for 3D Diffusion Policies
Sep 17, 2026Zhongbo Zhang, Zaibin Zhang, Yifan Wang +3Robot Policy Learning Diffusion Policy
Dalian University of Technology
GS-PI: An Optimization-Decoupled Appearance Decomposition Approach for Generating PBR Gaussian Assets
Sep 17, 2026Jieting Xu, Rengan Xie, Zijian Huang +3Inverse Rendering 3D Gaussian Splatting
State Key Laboratory of CAD&CG, Zhejiang University, China
LIFD: Anchored Diffusion for 3D-Aware Scene Memory in Robotic Manipulation
Sep 17, 2026Wenbo Li, Yiteng Chen, Wenhao Li +1Robotic Manipulation 3D Scene Representation
School of Software Engineering, South China University of Technology
3D CT-to-PET Translation via Latent Brownian Bridge Diffusion
Sep 14, 2026Sarita Mourya, Francesco Di Feola, Pierangelo Veltri +1PET/CT Imaging Medical Image Synthesis
Department of Medical and Surgical Sciences, Universit`a ”Magna Græcia” di Catanzaro Catanzaro, Italy · Department of Diagnostics and Intervention, Radiation Physics, Biomedical Engineering, Ume˚a University, Sweden · Department of Computer Science, Modeling, Electronics and Systems Engineering (DIMES) University of Calabria, Italy +1
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
Geometry Without Coordinates: LiDAR Diffusion as a 3D Feature Bridge
Sep 9, 2026Samed Doğan, Nico Leuze, Alfred Schöttl3D Semantic Segmentation Transfer Learning
Department of Electrical Engineering and Information Technology Munich University of Applied Sciences Munich, Bavaria 80335
PocketVE: Stable and Property-Guided Structure-Based Drug Design with Variance-Exploding Diffusion
Sep 8, 2026Peining Zhang, Jinbo BiDiffusion Model Guidance Structure-Based Drug Design
University of Connecticut Storrs, Connecticut 06269, USA
Flow3D-OPD: Multi-Teacher On-Policy Distillation for 3D Geometry Generation with Flow-Matching Diffusion Transformer
Sep 7, 2026Zhiwei Ning, Zhen Zhou, Puhua Jiang +73D Mesh Generation Diffusion Model Distillation
GridFlow: Structured Latent Flow for Seamless City-Scale 3D Point Cloud Generation
Aug 30, 2026Xinyu Wang, Muhammad Ibrahim, Atif Mansoor +13D Scene Generation Point Cloud Generation
The University of Western Australia, Perth, WA 6009, Australia
AnaDiffusion: Anatomically CompositionalLatent Diffusion for Controllable 3D Brain MRI Generation
Aug 24, 2026Huiwen Han, Lulin Liu, Bangya Liu +8Compositional Image Generation Medical Image Synthesis
Stanford University · Texas A&M University · University of Minnesota +4
SCULPT: Subtractive Composition for 3D Part Generation
Aug 13, 2026Sikuang Li, Chen Yang, Jiemin Fang +5Part-Level 3D Generation 3D Asset Generation
Shanghai Jiao Tong University · This work was done during an internship at Huawei. · Huawei
TGRHuman: Text-Guided Realistic 3D Human Generation via Diffusion Renderer
Aug 12, 2026Muxin Zhang, Chaohui Yu, Yuanwang Yang +33D Avatar Generation Text-to-3D Generation
Tianjin University, Tianjin, 300350, China · Independent Scholar, Beijing, 100080, China
SUMI: Scalable Unified Model for 3D Point Cloud Inference
Aug 8, 2026Yanlong LI, Kanchana ThilakarathnaPoint Cloud Completion 3D Shape Completion
Ordered Diffusion for 3D Human Registration
Aug 6, 2026Mattia Masiero, Ilya A. Petrov, Daniel Cremers +2Point Cloud Registration 3D Diffusion Models
University of Tübingen, Germany · Tübingen AI Center, Germany · Technical University of Munich, Germany +2
EditFlow3D: Automated Local Editing of 3D Assets with Trajectory Preservation
Aug 4, 2026Rui Nie, Chuang Wang, Haitao Zhou +43D Shape Editing 3D Diffusion Models
Beihang University · Bambu Lab · Shanghai Jiao Tong University
Hunyuan3D-Buffalo 1.0: A Unified Multimodal Model for Scalable 3D Generation, Understanding, and Editing
Aug 3, 2026Junliang Ye, Kenkun Liu, Guocun Wang +133D Foundation Models Part-Level 3D Generation
Tencent Hunyuan
PartMat: Material-Aware 3D Part Decomposition with a Single Global Latent
Aug 3, 2026Guangming Fu, Jin Song, Yiyun Fei +3Part-Level 3D Generation 3D Asset Generation
1Nankai University, China · 2Alibaba Group, China
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
ProgFormer: Hierarchical Voxel Diffusion Transformer for Longitudinal Brain MRI Prediction
Jul 30, 2026Dexuan Ding, Yuankai Qi, Luping Zhou +3Diffusion Transformer Longitudinal Medical Image Analysis
Macquarie University · University of Sydney · University of California Merced
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
Physics-Guided Generative AI for Property-Targeted 3D Porous Media Design
Jul 27, 2026Peng WangGenerative Modeling Conditional Generative Modeling
Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, Guildford, UK
Scene-SAM3D: Multi-View Scene Asset Generation Without Fine-Tuning
Jul 18, 2026Yuqi Zhang, Yadan Luo, Xiangyu Sun +33D Asset Generation 3D Scene Generation
The University of Queensland · Shanghai AI Laboratory · East China Normal University

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 54