Neural Radiance Fields

Also known as NeRF

Ask about this topic

Overview

Neural radiance fields (NeRFs) learn a continuous 3D scene from posed images and use differentiable volume rendering to synthesize unseen views. Methods range from per-scene multilayer perceptrons to faster hash-grid, tensor-factorized, and plane-based encodings, often adding depth or geometry priors for sparse or noisy inputs. Evaluation spans synthetic scenes and real-world benchmarks such as LLFF and Mip-NeRF 360, while extensions address dynamic scenes, robotics, medical imaging, LiDAR, and other sensing modalities. The central challenge is balancing visual quality and geometric accuracy against training, memory, and rendering costs; robustness to uncertain poses and sparse views, and generalization to camera paths unlike those in training, remain difficult.

Latest papers

CardsList

82 papers7 papers in the last four weeks, down 22% on the four weeks before. 0.0% of all new papers.

  1. DriftNeRF: Cross-Ray Density Drifting for Sparse-View Neural Radiance Fields

    Oct 21, 2026Juntang Wang, Yihan Wang, Sheng'en Li +3Novel View SynthesisNeural Radiance Fields

    Harvard University, Cambridge, USA · Duke University, Durham, USA · Duke Kunshan University, Kunshan, China

  2. Geometry Regularization for Vanilla NeRF via Self-Supervised Cross-Ray Consistency

    Oct 20, 2026Zongji WangNeural Radiance Fields3D Reconstruction

  3. SpaRV: Sparse Radiance Voxels for Scalable Geometrically Consistent LiDAR-Visual Mapping and Rendering

    Oct 19, 2026Jianheng Liu, Yunfei Wan, Fangming Cheng +73D MappingLarge-Scale 3D Reconstruction

    Department of Mechanical Engineering, The University of Hong Kong.

  4. OX-NeRF: 3D X-ray Tomography Reconstruction from Sparse Views Using Implicit Neural Representation

    Oct 8, 2026Thomas Welsch, Min-Hsin Tu, David J. Chapman +1Sparse-View CT ReconstructionNeural Radiance Fields

    Department of Engineering Science University of Oxford Oxford, United Kingdom

  5. NeRFifyMesh: Optimizing Neural Radiance Fields from Textured Meshes for Robotics Scene Building

    Oct 7, 2026Nillan Nimal, Mahboubeh Asadi, Sajad Saeedi3D Scene RepresentationNeural Radiance Fields

    Department of Mechanical and Industrial Engineering, University of Toronto, Canada · Department of Mechanical, Industrial and Mechatronics Engineering, Toronto Metropolitan University, Canada · Department of Computer Science, University College London, UK

  6. VCURF: Virtual Camera-based Uncertainty of Radiance Fields

    Oct 2, 2026Liyan Chen, Nathaniel Burgdorfer, Philippos MordohaiUncertainty QuantificationNeural Rendering

    Stevens Institute of Technology

  7. Reconstructing the Dynamic World: A Representation-Centric View of 4D Scene Reconstruction

    Sep 30, 2026Ziren Gong, Guo Chen, Yongjia Li +133D Gaussian Splatting4D Reconstruction

    Department of Computer Science and Engineering, University of Bologna, Italy · Wangxuan Institute of Computer Technology, Peking University, China · Department of Computing, The Hong Kong Polytechnic University, Hong Kong +8

  8. Image Fidelity is Not Field Fidelity: Joint Thermodynamic Reconstruction and Error Localization in Neural Tomography

    Sep 24, 2026Alan Hsu, Jenna Samra, Alin Razvan Paraschiv +1Uncertainty Quantification3D Reconstruction

    Harvard University Cambridge, MA, USA · Center for Astrophysics | Harvard & Smithsonian Cambridge, MA, USA · National Solar Observatory Boulder, CO, USA

  9. WS-NeRF: A Mamba-Driven World-State-Aware Adaptive Deblurring Neural Radiance Field

    Sep 18, 2026Hang Jiang, Jinghao Wang, Yiming Zhang +3Neural Radiance FieldsImage Deblurring

    School of Intelligent Science and Technology, Xinjiang University, Urumqi, China · School of Computer Science and Technology, Xinjiang University, Urumqi, China · Joint Research Laboratory for Embodied Intelligence, Xinjiang University, Urumqi, China +1

  10. GRF-Recon: Global Ray-Field Optimization for Long-Sequence Feed-forward Reconstruction

    Sep 17, 2026Enpeng Li, Yunzhou Zhang, Zhiyao Zhang +43D ReconstructionMonocular 3D Reconstruction

    College of Information Science and Engineering, Northeastern University, China

  11. Multi-Stage NeRF for Efficient 3D Coronary Artery Reconstruction from Two Narrow-Angle Angiographic Projections

    Sep 14, 2026Deyu Meng, Mojtaba Lashgari, Yiying Wang +1Coronary Angiography3D Reconstruction

    Institute of Biomedical Engineering, Department of Engineering Science, University of Oxford, Oxford, United Kingdom

  12. What Makes a 3D Scene Editable? A Factorized Benchmark of Fidelity, Locality, Consistency, and Preservation

    Sep 14, 2026Sariah Patro, Arjun Mehra, Nikhil Bhatia3D Gaussian Splatting3D Scene Editing

    University of Delhi & Jadavpur University

  13. RouteBridge: Reliability-Routed Bidirectional Distillation Between Neural Radiance Fields and 3D Gaussian Splatting

    Sep 9, 2026YuanHang Wang, Xin Cao3D Gaussian Splatting3D Reconstruction

    University of Technology Sydney

  14. From Explicit References to Scene Manifolds: Distributional Fidelity and Realism for Radiance Field Quality Assessment

    Sep 7, 2026Saeed Mahmoudpour, Gi-Mun Um, Hyon-Gon Choo +13D Gaussian SplattingNeural Rendering

    Vrije Universiteit Brussel, Department of Electronics and Informatics, Belgium · imec, Kapeldreef 75, B-3001 Leuven, Belgium · Electronics and Telecommunications Research Institute (ETRI), Republic of Korea

  15. Temporal Residual Neural Radiance Fields for Monocular Video Dynamic Human Body Reconstruction

    Sep 4, 2026Tianle Du, Jie Wang, Xiaolong Xie +33D Human ReconstructionDynamic Scene Reconstruction

    Nanchang University

  16. Query Rewriting for Complex Object Segmentation in 4D Gaussian Representations

    Sep 2, 2026Thanh-Khoi Nguyen, Thien-Phuc Tran, Minh-Triet TranQuery ReformulationNeural Radiance Fields

    University of Science, Ho Chi Minh City, Vietnam · Viet Nam National University, Ho Chi Minh City, Vietnam

  17. Comparative Evaluation of 3D Reconstruction Methods for Immersive Visualization of Laboratory Objects

    Aug 27, 2026Brian De La Cruz, Aaron Y. Zhao, Maitrey Gramopadhye +43D ReconstructionEducational Technology

    Department of Computer Science, College of Arts and Sciences, The University of North Carolina, Chapel Hill, NC, USA, 27599 · Department of Chemistry, College of Arts and Sciences, The University of North Carolina, Chapel Hill, NC, USA, 27599 · Department of Biostatistics, School of Public Health and the Lineberger Comprehensive Cancer Center, The University of North Carolina, Chapel Hill, NC, USA, 27599 +1

  18. Cross-Platform Benchmark of Neural 3D Reconstruction for Autonomous Laboratory Robots

    Aug 26, 2026Yongho Kim, Mengjiao Han, Victor Mateevitsi +33D ReconstructionNeural Rendering

    Argonne National Laboratory · University of Illinois Chicago · NAISE, Northwestern University

  19. PIVOT: A Multi-Trajectory Dataset and Testbed for Pose, Intrinsics, and Novel Viewpoint Evaluation in Real-World 3D Reconstruction

    Aug 26, 2026Mary RaymondNovel View SynthesisNeural Radiance Fields

    Independent Researcher

  20. WiNeRF: Measurement Constrained Radiance Fields for Actionable Wireless Channel Modeling

    Aug 24, 2026Saif Ur Rahman, Rafid Umayer Murshed, Anton Dmitriev +3Wireless CommunicationsRadio Propagation Modeling

    University of Illinois Urbana-Champaign · Intel

  21. HistReNeRF: Historic Image Relocalisation within Contemporary Neural Radiance Field Reconstructions

    Aug 15, 2026Benjamin T. Hughes, Stuart JamesCamera Pose EstimationVisual Place Recognition

    Durham University, Durham, UK

  22. Semantic Radiance Fields as Simulators for Spatial Reasoning in Real-World Scenes

    Aug 13, 2026Nico Heider, Michał Jan Włodarczyk, Katarzyna Wasielewska-Michniewska +53D Spatial Reasoning3D Scene Representation

    1Leipzig University · 2Systems Research Institute Polish Academy of Sciences · 3Wrocław University of Economics

  23. Multi-Submap Implicit Neural SLAM with Local-to-Global Loop Closure for Large-Scale Scene Reconstruction

    Aug 10, 2026Tianchen Deng, Chongdi Wang, Nailin Wang +6Simultaneous Localization and Mapping3D Reconstruction

    School of Automation and Intelligent Sensing, Shanghai Jiao Tong university and State Key Laboratory of Avionics Integration and Aviation System-of-Systems Synthesis, Shanghai Key Laboratory of Navigation and Location Based Services, Shanghai 200240, China · Carnegie Mellon University, Pittsburgh, PA, United States · School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore

  24. DoRF++: Spherical Representation Learning over Doppler Radiance Fields for Robust Wi-Fi Sensing

    Aug 9, 2026Navid Hasanzadeh, Shahrokh ValaeeHuman Activity RecognitionGeometric Representation Learning

    Department of Electrical & Computer Engineering, University of Toronto, Toronto, ON, Canada.

  25. CHOW-SLAM: Compact Hybrid Representation with Complementary Overlap Window Optimization for RGB-D SLAM

    Aug 3, 2026Wenxuan Ji, Jin Xiao, Xiaoguang Hu +3Simultaneous Localization and MappingVisual SLAM

    School of Automation Science and Electrical Engineering, Beihang University, Beijing, 100191, China

  26. CORF-GS: Real-Time Wireless Radiance Field Reconstruction via Coupled Optical-RF Gaussian Splatting

    Jul 28, 2026Jinya Zhang, Jiajia Guo, Chao-Kai Wen +13D Gaussian SplattingStreaming 3D Reconstruction

  27. NEO: NeRF It Once, Edit It Many Times for Continuous Object Manipulation

    Jul 27, 2026Mikołaj Zieliński, David Hall, Dominik Belter +13D Scene EditingRobotic Manipulation

    Institute of Robotics and Machine Intelligence, Poznan University of Technology, 61-131 Pozna´n, Poland · CSIRO Robotics, CSIRO, Australia

  28. Hash-QNeRF: Multiresolution Hash Encoding for Quantum Neural Radiance Fields

    Jul 23, 2026Digonto Biswas, Tana Ballove, Anjan Bandyopadhyay +2Neural RenderingHybrid Quantum-Classical ML

    Centres of Innovation and Research KIIT Deemed to be University Bhubaneswar, India

  29. Neural LiDAR Bundle Adjustment

    Jul 5, 2026Chin Yung Anson Hon, Kaicheng Zhang, Sen Wang3D MappingPoint Cloud Registration

    Imperial College London, London, United Kingdom

  30. Mind the Gap: Standard 3DGS Evaluation Primarily Measures Near-Trajectory Interpolation

    Jul 2, 2026Gaoxiang Jia, Vikram Appia3D Gaussian SplattingSpatial Generalization

    Advanced Micro Devices, Inc.