3D Reconstruction

Follow this topic Ask about this topic

Momentum

82 papers in the last four weeks, up 134% on the four weeks before. 0.5% of all new papers.

Jul 13Week of Sep 28

Latest papers 608

All topics

First Shape, Then Meaning: Efficient Geometry and Semantics Learning for Indoor Reconstruction
May 5, 2026Remi Chierchia, Léo Lebrat, David Ahmedt-Aristizabal +3Signed Distance Functions 3D Reconstruction
School of Electrical Engineering & Robotics, Queensland University of Technology, Australia · Imaging and Computer Vision Group, CSIRO Data61, Australia
Mix3R: Mixing Feed-forward Reconstruction and Generative 3D Priors for Joint Multi-view Aligned 3D Reconstruction and Pose Estimation
May 5, 2026Siyou Lin, Zhou Xue, Hongwen Zhang +43D Reconstruction Multi-View 3D Reconstruction
Tsinghua University · Beijing Normal University · ByteDance
HumanSplatHMR: Closing the Loop Between Human Mesh Recovery and Gaussian Splatting Avatar
May 4, 2026Yeheng Zong, Pou-Chun Kung, Yike Pan +43D Reconstruction Human Mesh Recovery
University of Michigan
ShapeGrasp: Simultaneous Visuo-Haptic Shape Completion and Grasping for Improved Robot Manipulation
May 4, 2026Lukas Rustler, Matej HoffmannRobotic Grasping 3D Reconstruction
Department of Cybernetics, Faculty of Electrical Engineering, Czech Technical University in Prague, Prague, Czech Republic.
From Concept to Capability: Evaluating 3D Gaussian Splatting for Synthetic Scene Editing in Autonomous Driving
May 3, 2026Ali Nouri, Yifei Zhang, Yifan Zhang +53D Gaussian Splatting 3D Scene Editing
Volvo Cars, Gothenburg, Sweden · Zenseact AB, Gothenburg, Sweden · Lund University, Lund, Sweden +1
High-Fidelity Mobile Avatars with Pruned Local Blendshapes
May 3, 2026Youyi Zhan, He Wang, Tianjia Shao +1Model Compression 3D Gaussian Splatting
State Key Lab of CAD&CG, Zhejiang University · University College London
SplAttN: Bridging 2D and 3D with Gaussian Soft Splatting and Attention for Point Cloud Completion
May 2, 2026Zhaoyang Li, Zhichao You, Tianrui LiCross-Modal Learning Point Cloud Completion
School of Computing and Artificial Intelligence, Southwest Jiaotong University, Chengdu, China
Registration-Free Learnable Multi-View Capture of Faces in Dense Semantic Correspondence
May 2, 2026Panagiotis P. Filntisis, George Retsinas, Radek Daněček +3Test-Time Optimization 3D Reconstruction
Institute of Robotics, Athena Research Center, 15125 Maroussi, Greece · HERON – Hellenic Robotics Center of Excellence, Athens, Greece · School of ECE, NTUA, Greece +3
Terrain Perception for Agricultural UAVs in Complex Farmland via Rotating mmWave Radar
May 2, 2026Zhihao Zhan, Le Tao, Shaobin Li +5Aerial Robotics 3D Reconstruction
School of Computer Science, Hangzhou Dianzi University, Hangzhou, 310018, China · TopXGun Robotics, Nanjing, 211100, China · CARDC, Mianyang, 621000, China +2
CADFit: Precise Mesh-to-CAD Program Generation with Hybrid Optimization
May 2, 2026Ghadi Nehme, Eamon Whalen, Faez Ahmed3D Reconstruction Parametric CAD Modeling
Department of Mechanical Engineering, Massachusetts Institute of Technology, Cambridge, MA 02139, USA · Siemens Digital Industries Software, Plano, TX 75024, USA
A skin-like conformal sensor for real-time shape mapping
May 2, 2026Kaiping Yin, Sooik Im, Chaorui Qiu +5Tactile Sensing 3D Reconstruction
Department of Mechanical Engineering and Materials Science, Duke University, Durham, NC 27708, USA. · Department of Biomedical Engineering, Duke University, Durham, NC 27708, USA · Department of Neurology, Duke University School of Medicine, Durham, NC 27710, USA. +2
2D-SuGaR: Surface-Aware Gaussian Splatting for Geometrically Accurate Mesh Reconstruction
May 1, 2026Prajwal Gupta C. R., Divyam Sheth, Jinjoo Ha +23D Gaussian Splatting 3D Reconstruction
TU Darmstadt · ELIZA · Max Planck Institute for Intelligent Systems
Beyond Heuristics: Learnable Density Control for 3D Gaussian Splatting
May 1, 2026Zhenhua Ning, Xin Li, Jun Yu +33D Gaussian Splatting 3D Reconstruction
Pengcheng Laboratory, Shenzhen · Harbin Institute of Technology, Shenzhen
From Images2Mesh: A 3D Surface Reconstruction Pipeline for Non-Cooperative Space Objects
Apr 30, 2026Bala Prenith Reddy Gopu, Patrick Quinn, George M. Nehma +4Implicit Neural Representations 3D Reconstruction
Department of Aerospace, Physics and Space Sciences, Florida Institute of Technology, 150 W University Blvd, Melbourne, 32901, FL, USA · Creare LLC, Hanover, 03755, NH, USA
Generalizable Sparse-View 3D Reconstruction from Unconstrained Images
Apr 30, 2026Vinayak Gupta, Chih-Hao Lin, Shenlong Wang +23D Gaussian Splatting 3D Reconstruction
University of Maryland, College Park · University of Illinois Urbana-Champaign · Johns Hopkins University
MeshReGen: A Unified 3D Geometry Regeneration Framework
Apr 30, 2026Geon Yeong Park, Roman Shapovalov, Rakesh Ranjan +33D Shape Editing 3D Reconstruction
KAIST · ⋆Work done during an internship at Meta Reality Labs. · Meta Reality Labs
3D Reconstruction Techniques in the Manufacturing Domain: Applications, Research Opportunities and Use Cases
Apr 30, 2026Chialoon Cheng, Kaijun liu, Zhiyang Liu +1Manufacturing 3D Reconstruction
Advanced Robotics Centre, National University of Singapore, Singapore · Advanced Robotics Centre, National University of Singapore, 117608, Singapore · Independent Researcher
ResiHMR: Residual-Limb Aware Single-Image 3D Human Mesh Recovery for Individuals with Limb Loss
Apr 30, 2026Jiaying Ying, Heming Du, Kaihao Zhang +23D Reconstruction Human Mesh Recovery
The University of Queensland · Australian National University · The University of Adelaide
World2Minecraft: Occupancy-Driven Simulated Scenes Construction
Apr 30, 2026Lechao Zhang, Haoran Xu, Jingyu Gong +33D Reconstruction Synthetic Data Generation for Robotics
School of Computer Science and Technology, East China Normal University · Shanghai Artificial Intelligence Laboratory · Shanghai Innovation Institute
Softmax-GS: Generalized Gaussians Learning When to Blend or Bound
Apr 30, 2026Chen Ziwen, Peng Wang, Hao Tan +2Multi-View Consistency 3D Gaussian Splatting
Adobe Research · Tripo AI · Hillbot +1
Reconstruction by Generation: 3D Multi-Object Scene Reconstruction from Sparse Observations
Apr 29, 2026Andrii Zadaianchuk, Leonardo Barcellona, Lennard Schuenemann +73D Reconstruction Object Pose Estimation
University of Amsterdam · KU Leuven · Toyota Research Institute +1
Color-Encoded Illumination for High-Speed Volumetric Scene Reconstruction
Apr 29, 2026David Novikov, Eilon Vaknin, Narek Tumanyan +13D Reconstruction Multi-View 3D Reconstruction
Weizmann Institute of Science, Israel
Seamless Indoor-Outdoor Mapping for INGENIOUS First Responders
Apr 29, 2026Jürgen Wohlfeil, Henry Meißner, Adrian Schischmanow +4Simultaneous Localization and Mapping 3D Reconstruction
Institute of Optical Systems (OS), German Aerospace Center (DLR) Berlin, Germany
EnerGS: Energy-Based Gaussian Splatting with Partial Geometric Priors
Apr 29, 2026Rui Song, Tianhui Cai, Markus Gross +53D Gaussian Splatting 3D Reconstruction
University of California, Los Angeles, California, USA · University of Cambridge, Cambridge, UK · Technical University of Munich, Munich, Germany
BIMStruct3D: A Fully Automated Hybrid Learning Scan-to-BIM Pipeline with Integrated Topology Refinement
Apr 27, 2026Mahdi Chamseddine, Fabian Kaufmann, Marius Schellen +33D Reconstruction Point Cloud Learning
German Research Center for Artificial Intelligence (DFKI), Kaiserslautern, Germany · RPTU Kaiserslautern-Landau, Kaiserslautern, Germany
Spatiotemporal Degradation-Aware 3D Gaussian Splatting for Realistic Underwater Scene Reconstruction
Apr 26, 2026Shaohua Liu, Ning Gao, Zuoya Gu +33D Gaussian Splatting Underwater Imaging
School of Astronautics Beihang University Beijing, China · Shen Yuan Honors College, Beihang University · School of Artificial Intelligence Beihang University Beijing, China +3
GenAssets: Generating in-the-wild 3D Assets in Latent Space
Apr 24, 2026Ze Yang, Jingkang Wang, Haowei Zhang +33D Asset Generation Latent Diffusion Models
Waabi · University of Toronto
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
Holo360D: A Large-Scale Real-World Dataset with Continuous Trajectories for Advancing Panoramic 3D Reconstruction and Beyond
Apr 24, 2026Jing Ou, Zidong Cao, Yinrui Ren +6Panoramic 3D Reconstruction 3D Reconstruction
1The Hong Kong University of Science and Technology (Guangzhou) · 2South China Normal University
EvFlow-GS: Event Enhanced Motion Deblurring with Optical Flow for 3D Gaussian Splatting
Apr 24, 2026Feiyu An, Yufei Deng, Zihui Zhang +1Event-Based Vision 3D Gaussian Splatting
College of Computer Science, Sichuan University, Chengdu, China

May 5, 2026, cs.CVJ/K move · Enter open · S save

First Shape, Then Meaning: Efficient Geometry and Semantics Learning for Indoor Reconstruction

Remi Chierchia, Léo Lebrat, David Ahmedt-Aristizabal, Olivier Salvado+2

School of Electrical Engineering & Robotics, Queensland University of Technology, Australia · Imaging and Computer Vision Group, CSIRO Data61, Australia

Signed Distance Functions 3D Reconstruction 3D Semantic Segmentation Indoor Scene Reconstruction

Open paper AskPDF arXiv

Neural Surface Reconstruction has become a standard methodology for indoor 3D reconstruction, with Signed Distance Functions (SDFs) proving particularly effective for representing scene geometry. A variety of applications require a detailed understanding of the scene context, driving the need for object-level semantic signals. While recent methods successfully integrate semantic labels, they often inherit the slow training time and limited scalability of multi-SDF learning. In this paper, we introduce FSTM, a unified approach for learning geometry and semantics through a two-step process: a geometry warm-up using RGB inputs and geometric cues, followed by semantic field estimation. By first optimising geometry without semantic supervision, we observe substantial improvements compared to the standard joint optimisation. Rather than relying on specialised modules or complex multi-SDF designs, FSTM shows that a streamlined formulation is sufficient to achieve strong geometric and semantic reconstructions. Experiments on both synthetic and real-world indoor datasets show that our method outperforms multi-SDF approaches. It trains 2.3x faster on Replica, improves robustness to real-world imperfections on ScanNet++, and achieves higher recall by recovering the surfaces of more objects in the scene. The code will be made available at https://remichierchia.github.io/FSTM.

Momentum

Related topics

Latest papers 608