3D Representation Learning

Follow this topic Ask about this topic

Momentum

15 papers in the last four weeks, up 67% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 129

All topics

SGSoft: Learning Fused Semantic-Geometric Features for 3D Shape Correspondence via Template-Guided Soft Signals
May 18, 2026Soyeon Yoon, Chang Wook Seo, Hyunjung ShimGeometric Representation Learning Non-Rigid Shape Correspondence
1KAIST AI · 2Anigma Technologies
IVGT: Implicit Visual Geometry Transformer for Neural Scene Representation
May 15, 2026Yuqi Wu, Tianyu Hu, Wenzhao Zheng +43D ViTs Implicit Neural Representations
Intelligent Vision Group, Tsinghua University
Invaria: Learning Scale and Density Invariance in Point Clouds via Next-Resolution Prediction
May 15, 2026Chun-Peng Chang, Shaoxiang Wang, Alain Pagani +2Point Cloud Learning 3D Semantic Segmentation
TU Delft · DFKI
Discretizing Group-Convolutional Neural Networks for 3D Geometry in Feature Space
May 14, 2026Daniel Franzen, Jean Philip Filling, Michael WandEquivariant Neural Networks 3D Representation Learning
Johannes Gutenberg University Mainz, Germany
Tadpole: Autoencoders as Foundation Models for 3D PDEs with Online Learning
May 14, 2026Qiang Liu, Felix Koehler, Benjamin Holzschuh +13D Foundation Models PDE Surrogate Modeling
TUM School of Computation, Information and Technology, Technical University of Munich, Garching, Germany · MCML, Munich Center for Machine Learning, Munich, Germany
Evo-Depth: A Lightweight Depth-Enhanced Vision-Language-Action Model
May 14, 2026Tao Lin, Yuxin Du, Jiting Liu +14Language-Conditioned Robot Manipulation Efficient VLA Models
School of AI, Shanghai Jiao Tong University · King Abdullah University of Science and Technology · SJTU-Quic Robot Joint Lab +1
H2G: Hierarchy-Aware Hyperbolic Grouping for 3D Scenes
May 12, 2026ByungHa Ko, Youngmin Lee, Dong Hwan KimClustering Hierarchical Representation Learning
Department of Computer Science and Engineering, Korea University · Intelligence and Interaction Research Center, Korea Institute of Science and Technology
Learning Protein Structure-Function Relationships through Knowledge-guided Representation Decomposition
May 12, 2026Mingqing Wang, Zhiwei Nie, Athanasios V. Vasilakos +2Representation Disentanglement 3D Representation Learning
Shenzhen International Graduate School, Tsinghua University, Shenzhen, China · Pengcheng Laboratory, Shenzhen, China · School of Electronic and Computer Engineering, Peking University, Shenzhen, China +2
Beyond Spatial Compression: Interface-Centric Generative States for Open-World 3D Structure
May 11, 2026Xiang Chen, Alexander Binder3D Asset Generation 3D Spatial Reasoning
DSC ScaDS.AI, Leipzig University · Institute for Cancer Genetics and Informatics (ICGI), Oslo, Norway · ICT Cluster, Singapore Institute of Technology, Singapore
SpaceMind++: Toward Allocentric Cognitive Maps for Spatially Grounded Video MLLMs
May 10, 2026Bo Gu, Zhikang Zhang, Zizhuang Wei +33D Spatial Reasoning VLM Reasoning
1Fudan University · 2Huawei · 3Shenzhen Loop Area Institute
Proxy3D: Efficient 3D Representations for Vision-Language Models via Semantic Clustering and Alignment
May 8, 2026Jerry Jiang, Haowen Sun, Denis Gudovskiy +43D Spatial Reasoning 3D Representation Learning
Tsinghua University · Panasonic AI Lab · Panasonic DX-CPS +1
Text-to-CAD Retrieval: a Strong Baseline
May 7, 2026Honghu Pan, Zibo Du, Daxiang Liu +2Cross-Modal Retrieval 3D Representation Learning
School of Artificial Intelligence and Robotics, Hunan University · College of Computer Science and Software Engineer, Shenzhen University · Faculty of Science and Technology, University of Macau
Velox: Learning Representations of 4D Geometry and Appearance
May 6, 2026Anagh Malik, Dorian Chan, Xiaoming Zhao +3Representation Learning Point Cloud Learning
Apple · University of Toronto
Representation learning from OCT images
May 4, 2026Hedi Tabia, Désiré Sidibé, Nawres Khlifa +6Medical Imaging Medical Imaging Foundation Models
IBISC Univ. Evry Université Paris-Saclay · University of Tunis El Manar · ESIEE Paris - Université Gustave Eiffel +2
PointCSP: Cross-Sample Semantic Propagation and Stability Preservation in Self-Supervised Point Cloud Learning
May 3, 2026Xinxing Yu, Ajian Liu, Sunyuan Qiang +5Self-Supervised Pre-Training Point Cloud Learning
Faculty of Innovation Engineering, Macau University of Science and Technology, Macau, China · MAIS, The Institute of Automation of the Chinese Academy of Sciences, Beijing, China · Southwest Institute of Technical Physics, Chengdu, China +1
Adaptive Texture-aware Masking for Self-Supervised Learning in 3D Dental CBCT Analysis
May 3, 2026Xinquan Yang, Jianfeng Ren, Xuguang Li +4Cone-Beam CT Self-Supervised Pre-Training
School of Artiﬁcial Intelligence, Shenzhen University, Shenzhen, China. · School of Computer Science, University of Notting-ham Ningbo China, Ningbo, China. · Department of Stomatology, Shenzhen University General Hospital, Shenzhen, China.
Beyond Gaussian Bottlenecks: Topologically Aligned Encoding of Vision-Transformer Feature Spaces
Apr 30, 2026Andrew Bond, Ilkin Umut Melanlioglu, Erkut Erdem +1Variational Autoencoders Hyperspherical Representation Learning
Department of Computer Engineering, Kocı University, Istanbul, Turkey · KUIS AI Research Center, Istanbul, Turkey · Department of Electrical and Electronics Engineering, Kocı University, Istanbul, Turkey +1
SQuadGen: Generating Simple Quad Layouts via Chart Distance Fields
Apr 30, 2026Youkang Kong, Yang Liu, Yue Dong +23D Mesh Generation 3D Representation Learning
Tsinghua University, P. R. China · Microsoft Research Asia, P. R. China · Tsinghua University & International Digital Economy Academy, P. R. China
Long-tail Internet photo reconstruction
Apr 24, 2026Yuan Li, Yuanbo Xiangli, Hadar Averbuch-Elor +23D Foundation Models 3D Reconstruction
Cornell University · 2Kempner Institute, Harvard University
PASR: Pose-Aware 3D Shape Retrieval from Occluded Single Views
Apr 24, 2026Jiaxin Shi, Guofeng Zhang, Wufei Ma +33D Representation Learning
1Shanghai Jiao Tong University · 2Johns Hopkins University · University of California, San Diego +1
FILTR: Extracting Topological Features from Pretrained 3D Models
Apr 24, 2026Louis Martinez, Maks OvsjanikovPoint Cloud Learning 3D Representation Learning
LIX, ´Ecole Polytechnique, IP Paris
Structure-guided molecular design with contrastive 3D protein-ligand learning
Apr 21, 2026Carles Navarro, Philipp Tholke, Gianni de FabritiisContrastive Learning Virtual Screening
Acellera Labs, C/ Doctor Trueta 183, 08005 Barcelona, Spain · Computational Science Laboratory, Universitat Pompeu Fabra, PRBB, C/ Doctor Aiguader 88, 08003 Barcelona, Spain · Instituci´o Catalana de Recerca i Estudis Avan¸cats (ICREA), Passeig Llu´ıs Companys 23, 08010 Barcelona, Spain
Diff-SBSR: Learning Multimodal Feature-Enhanced Diffusion Models for Zero-Shot Sketch-Based 3D Shape Retrieval
Apr 21, 2026Hang Cheng, Fanhe Dong, Long Zeng3D Representation Learning T2I Diffusion Models
Tsinghua Shenzhen International Graduate School, Tsinghua University · Shenzhen, Guangdong, China
Shape: A Self-Supervised 3D Geometry Foundation Model for Industrial CAD Analysis
Apr 19, 2026Bayangmbe Mounmo, Sam Chien, Mile Mitrovic3D Foundation Models Self-Supervised Learning
1SIMD AI · 2SB AI Lab
PLAF: Pixel-wise Language-Aligned Feature Extraction for Efficient 3D Scene Understanding
Apr 17, 2026Junjie Wen, Junlin He, Fei Ma +13D Scene Representation 3D Representation Learning
Pengcheng Laboratory, Shenzhen, 518108, China · The School of Intelligent Engineering, Sun Yat-Sen University-ShenzhenCampus, Shenzhen, Guangdong, China · School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China.
TORA: Topological Representation Alignment for 3D Shape Assembly
Apr 5, 2026Nahyuk Lee, Zhiang Chen, Marc Pollefeys +1Flow Matching 3D Shape Generation
Independent Researcher · ETH Zurich · ETH AI Center
FusionBERT: Multi-View Image--3D Retrieval via Cross-Attention Visual Fusion and Normal-Aware 3D Encoder
Apr 2, 2026Wei Li, Yufan Ren, Hanqing Jiang +6Multi-View Learning Cross-Modal Retrieval
IROOTECH TECHNOLOGY, Hangzhou, Zhejiang, China · Wolf 1069 b Lab, Sany Group, Hangzhou, Zhejiang, China · Zhejiang University, Hangzhou, Zhejiang, China +4
RGB-Pointmap Pretraining for Unified 3D Scene Understanding
Apr 2, 2026Ye Mao, Weixun Luo, Ranran Huang +23D Foundation Models Multi-View Learning
Imperial College London
To View Transform or Not to View Transform: NeRF-based Pre-training Perspective
Mar 30, 2026Hyeonjun Jeong, Juyeb Shin, Dongsuk Kum3D Reconstruction Autonomous Driving Perception
KAIST, Daejeon, Korea
Back to Point: Exploring Point-Language Models for Zero-Shot 3D Anomaly Detection
Mar 23, 2026Kaiqiang Li, Gang Li, Mingle Zhou +3Point Cloud Anomaly Detection Industrial Inspection
Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center (National Supercomputer Center in Jinan), Qilu University of Technology (Shandong Academy of Sciences), Jinan, China. · Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing, Shandong Fundamental Research Center for Computer Science, Jinan, China.

May 18, 2026, cs.CVJ/K move · Enter open · S save

SGSoft: Learning Fused Semantic-Geometric Features for 3D Shape Correspondence via Template-Guided Soft Signals

Soyeon Yoon, Chang Wook Seo, Hyunjung Shim

1KAIST AI · 2Anigma Technologies

Geometric Representation Learning Non-Rigid Shape Correspondence 3D Representation Learning

Open paper AskPDF arXiv

Learning dense correspondences across deformable 3D shapes remains a long-standing challenge due to structural variability, non-isometric deformation, and inconsistent topology. Existing methods typically trade off generalization, geometric fidelity, and efficiency. We address this by proposing SGSoft, a unified intrinsic pipeline that (i) constructs a geodesic correspondence field on a canonical template, (ii) learns multimodal dense descriptors guided by pretrained semantic priors with this geodesic correspondence field supervision, (iii) retrieves dense correspondences in a single feed-forward pass via nearest-neighbor search in descriptor space. This formulation enables stable and topology-invariant supervision under large pose variation, structural differences, and remeshing. SGSoft achieves state-of-the-art inter-category generalization while offering the best accuracy-efficiency trade-off among prior methods. It also achieves near real-time inference without pre-alignment, pairwise optimization, or post-refinement. Learned descriptors can be transferred effectively to downstream tasks such as semantic segmentation and deformation transfer, establishing a scalable and deployment-ready paradigm for dense 3D correspondence.

Momentum

Related topics

Latest papers 129