Overview

3D reconstruction studies how to infer the shape and appearance of objects or scenes, along with camera positions and motion, from partial observations. Methods range from structure-from-motion and multi-view stereo to neural radiance fields, Gaussian splatting, signed distance fields, meshes, and feed-forward models that predict geometry directly; some also use diffusion priors, active view selection, or physical sensor models. Applications include mapping and robotics, digital twins, medical imaging, and human or object modeling, with evaluations often comparing both rendered views and geometric accuracy on indoor, outdoor, and specialized datasets. A central challenge is that realistic novel-view images do not always imply accurate, metrically consistent geometry, especially with sparse or unposed views, changing scenes, difficult materials, or limited computation.

Latest papers

CardsList

1,033 papers76 papers in the last four weeks, down 37% on the four weeks before. 0.6% of all new papers.

  1. Sparse-View 3D Coronary Reconstruction from Vessel Segmentations Using a Diffusion Prior

    Nov 3, 2026Tianyuan Wang, Kenan Niu, Stefano StramigioliSparse-View 3D Reconstruction3D Reconstruction

  2. Predicting Void Points in Self-Occluding Forest Volumes

    Nov 3, 2026Benjamin Bachmayr, Mohamed Youssef, Oliver BimberForest Remote Sensing3D Occupancy Prediction

  3. Mamba3R: Fixed-Capacity Selective State Memory for Long-Sequence 3D Reconstruction

    Nov 3, 2026Zhenxiang Xiong, Tianchen Deng, Nailin Wang +3Streaming 3D Reconstruction3D Reconstruction

  4. 3D dark matter map of the JWST COSMOS-Web field using diffusion-based generative priors

    Nov 2, 2026Diana Scognamiglio, Brandon Zhao, Katherine L. Bouman +173D Reconstruction

  5. Visual-to-Executable Procedural Reconstruction of Buildings

    Nov 2, 2026Zichong Zhu, Zhihao Liu, Andrei Sharf +1Procedural 3D GenerationProcedural Content Generation

  6. 3D Gaussian Splatting within Self-Learned Neural View-Dependent Color Fields

    Nov 2, 2026Yixiao Yang, Yu-Shen Liu, Zhizhong Han3DGS TrainingNovel View Synthesis

  7. Solv3R: 3D Looped Transformer as a Multi-view Solver

    Nov 2, 2026Jeong-gi Kwak, Andrea Tagliasacchi, Sho Kagami +23D ReconstructionMulti-View 3D Reconstruction

  8. Learning from high-resolution 2D images to reconstruct 3D microstructures

    Nov 1, 2026Wenbo Sui, Lars P. Mikkelsen, Jens W. Andreasen +33D ReconstructionCross-Modal Knowledge Distillation

  9. EgoMo3R: Joint Egocentric Motion and Scene Reconstruction

    Nov 1, 2026Chaitanya Patel, Yusuke Kato, Rin Takahira +33D ReconstructionEgocentric Video Understanding

  10. A Reproducible Reconstruction and Evaluation Framework for Photorealistic Lunar Analog Scene Reconstruction Toward Digital Twins

    Oct 31, 2026Antar Mazumder, Ryan Hartzell, Luke Boyd +43D ReconstructionNovel View Synthesis

  11. 3D Neural Rendering for Automated Ultrasonic Laser Scans

    Oct 31, 2026Thomas Pierson, Matthew Mitchell, Kira Perna +3Neural Rendering3D Reconstruction

  12. Efficacy of Monocular Depth Estimation in Lunar Environments

    Oct 27, 2026Michael W. Lanighan, Kenji Brameld, Seth GeeMonocular Depth Estimation3D Reconstruction

  13. GOFish: Full Field-of-View Gaussian Splatting and Mesh Extraction

    Oct 27, 2026Allen Tu, Meher Gitika Karumuri, Shifan Zhu +53D Reconstruction3D Gaussian Splatting

  14. HoloRecon: Incremental Reconstruction of Long-Range Panoramas with Global Consistency

    Oct 27, 2026Zhuoxiao Li, Xinyi Liu, Hongye Hou +8Panoramic 3D Reconstruction3D Reconstruction

  15. Ground Sample Distance Constrained k-Coverage Viewpoint Planning via Set Multi-Cover Formulation

    Oct 27, 2026Waleed Bin Khalid, Chul Min YeumNext-Best-View Planning3D Reconstruction

  16. Any3R: Feedforward 3D Reconstruction from Any Camera Type

    Oct 26, 2026Jingong Chen, Qingwen Zhang, Youming Deng +53D ReconstructionMulti-View 3D Reconstruction

  17. SceneAgent: An Agentic Pipeline from 3D and 4D Captures to Simulation Environments

    Oct 26, 2026Luke Hollis, Tianxing Fan, Heng YangRobotics SimulationPhysics-Aware 3D Scene Reconstruction

  18. RIDE-Splat: Reflection Removal for In-the-Wild Driving Environments

    Oct 25, 2026Kevin David Hayes, Alex Hanson, Allen Tu +33D Reconstruction3D Gaussian Splatting

  19. Hybrid Mamba-Transformer Network for Single-Shot 3D Reconstruction from Fringe Patterns

    Oct 25, 2026Xinjie Zhou, XiaoLei Li3D ReconstructionFringe Projection Profilometry

  20. FreeView: Robust 3D Reconstruction from Uncurated Views

    Oct 24, 2026Junho Kim, Hyunyoung Choi, Seongwon Lee3D ReconstructionMulti-View 3D Reconstruction

  21. CADonatello: Towards Real-World Multi-Part 3D CAD Reconstruction

    Oct 24, 2026Ahmet Serdar Karadeniz, Dimitrios Mallis, Parsa Akbari Chianeh +33D ReconstructionParametric CAD Modeling

  22. OmniRay: Camera-Agnostic Monocular 3D Reconstruction with Composite Ray Fields

    Oct 22, 2026Namitha Guruprasad, Abhay Yadav, Cheng Peng +23D ReconstructionMonocular 3D Reconstruction

  23. HiP3R: Hierarchical Pose Graphs for Long-Horizon 3D Reconstruction

    Oct 22, 2026Zunnan Xu, Shangchen Zhou, Yihang Luo +13D ReconstructionCamera Pose Estimation

  24. DRAFT: Decoding and Reconstructing 3D Room Layouts from fMRI and Camera Trajectories

    Oct 22, 2026Chi-Wei Lee, An-Kai Chen, Cheng-Han Chiang +23D ReconstructionIndoor Scene Reconstruction

  25. H-2DGS: Height-Field Gaussian Splatting for Sharp and Deformable Neurosurgical Surface Reconstruction

    Oct 22, 2026Zhang Zichuan, Bart Brouwers, Rembrandt Bakker +33D Reconstruction3D Gaussian Splatting

  26. Plausible but Unimplantable: A Trustworthiness Audit of Shape Completion Foundation Models for Cranial Defect Reconstruction

    Oct 21, 2026Marek Wodzinski, Kamil Kwarciak, Daria Hemmerling +1Trustworthy AI3D Shape Completion