Neural Radiance Fields

Also known as NeRF

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

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

Reliability-Aware Monocular Depth Supervision for Sparse-View Neural Reconstruction
Jun 27, 2026Wei-Teng Chu, Yashasvini Gopalan, Changju YuanSparse-View 3D Reconstruction Neural Radiance Fields
Stanford University
Sculpting NeRF Geometry: Human-Preference Fine-Tuning of a 3D-Aware Face GAN
Jun 25, 2026Archer Moore, Mingming Gong, Liam Hodgkinson3D Shape Generation RL for Generative Models
School of Mathematics and Statistics, The University of Melbourne, Parkville, VIC 3010, Australia
VisDom: Sparse Novel View Synthesis with Visible Domain Constraint
Jun 18, 2026Mariia Gladkova*, Tarun Yenamandra*, Edmond Boyer +3Multi-View 3D Reconstruction Novel View Synthesis
1TU Munich · 2MCML
NeuMesh++: Towards Versatile and Efficient Volumetric Editing with Disentangled Neural Mesh-based Implicit Field
Jun 17, 2026Chong Bao, Yuan Li, Bangbang Yang +5Implicit Neural Representations 3D Shape Editing
State Key Lab of CAD&CG, College of Computer Science, Zhejiang University · ByteDance · Ant Research +1
EDoF-NeRF: extended depth-of-field neural radiance fields using a coded aperture camera
Jun 17, 2026Yoshiyuki Shirasaki, Ryoichi HorisakiNeural Rendering Neural Radiance Fields
Department of Information Physics and Computing, Graduate School of Information Science and Technology, The University of Tokyo, 7-3-1 Hongo, Bunkyo-ku, Tokyo 113-8656, Japan
Beyond Spherical Harmonics: Rethinking Appearance Models for Radiance Reconstruction
Jun 8, 2026Ewa Miazga, Jorge Condor, Piotr DidykNovel View Synthesis 3D Scene Representation
1École Polytechnique Fédérale de Lausanne, Switzerland · 2Università della Svizzera Italiana, Lugano, Switzerland
Liquid Neural Networks as a Drop-in Continuous-Time Deformation Field for Dynamic 3D Gaussian Splatting
Jun 4, 2026Mingzhao Li, Arghya Pal, Guan Yuan Tan3D Gaussian Splatting Liquid Neural Networks
School of Information Technology, Monash University, Selangor, Malaysia
Sparse-View Lung Nodule Volumetry from Digitally Reconstructed Radiographs via AReT: Anatomy-Regularized TensoRF
May 31, 2026Spoorthi M, Suja Palaniswamy3D Medical Imaging Sparse-View 3D Reconstruction
Department of Computer Science & Engineering, Amrita School of Computing, Bengaluru, Amrita Vishwa Vidyapeetham, India
Beyond Static Gaussians: An Empirical Investigation of Architectural Paradigms for Dynamic 3D Scene Reconstruction
May 30, 2026Adrian Ramlal, John S. Zelek3D Gaussian Splatting Dynamic Scene Reconstruction
University of Waterloo
CLEAR-NeRF: Collinearity and Local-region Enhanced Accurate 3D Reconstruction in Unbounded Scenes
May 27, 2026Vladislav Polianskii, Elijs Dima, Isabel Salmerón Marazuela +33D Reconstruction Multi-View 3D Reconstruction
Ericsson Research, Stockholm, Sweden
NeRF-based Spacecraft Reconstruction from Monocular Imagery Under Illumination Variability and Pose Uncertainty
May 18, 2026Antoine Legrand, Renaud Detry, Christophe De VleeschouwerDistribution Shift 3D Reconstruction
Aerospacelab, Mont-Saint-Guibert, 1435, Belgium · ICTEAM, UCLouvain, Louvain-la-Neuve, 1348, Belgium
CATRF: Codec-Adaptive TriPlane Radiance Fields for Volumetric Content Delivery
May 18, 2026Tung-I Chen, Lingdong Wang, Subhransu Maji +1Tri-Plane Representations Rate-Distortion Optimization
University of Massachusetts Amherst
Predicting 3D structure by latent posterior sampling
May 11, 2026Azmi Haider, Dan RosenbaumNeural Radiance Fields Multi-View 3D Reconstruction
Department of Computer Science University of Haifa Haifa, Israel · Department of Computational Science University of Haifa Haifa, Israel
BathyFacto: Refraction-Aware Two-Media Neural Radiance Fields for Bathymetry
May 11, 2026Markus Brezovsky, Anatol Günthner, Frederik Schulte +3Underwater Imaging 3D Reconstruction
Department of Geodesy and Geoinformation, TU Wien, Vienna, Austria · Institute of Photogrammetry and Remote Sensing (IPF), Karlsruhe Institute of Technology (KIT), Karlsruhe, Germany · Unit of Geometry and Surveying, University of Innsbruck, Innsbruck, Austria
Low-Cost Neural Radiance Fields
May 10, 2026Alice Huang, Prathamesh Sonawane, Yashdeep Thorat +1Neural Rendering Sparse-View 3D Reconstruction
University of Illinois Urbana Champaign
RayFormer: Modeling Inter- and Intra-Ray Similarity for NeRF-Based Video Snapshot Compressive Imaging
Apr 30, 2026Yubo Dong, Danhua Liu, Anqi Li +1Image Reconstruction Dynamic Scene Reconstruction
Changzhi Medical College, Changzhi 046000, China · Engineering Research Centre for Intelligent Data Assisted Diagnosis and Treatment in Shanxi Province, Changzhi 046000, China · Uniwave Artificial Intelligence Technology Co., Ltd., Changzhi 046000, China +1
Multivariate Gaussian NeRF for Wide Field-of-View Ultrasound Reconstruction
Apr 27, 2026Patris Valera, Magdalena Wysocki, Felix Duelmer +4Novel View Synthesis Ultrasound Imaging
Chair for Computer Aided Medical Procedures (CAMP), Technical University of Munich, Germany · Munich Center for Machine Learning (MCML), Munich, Germany · LUMA Vision, Beech Hill Road, Dublin, Ireland
BALTIC: A Benchmark and Cross-Domain Strategy for 3D Reconstruction Across Air and Underwater Domains Under Varying Illumination
Apr 21, 2026Michele Grimaldi, David Nakath, Oscar Pizarro +33D Gaussian Splatting Underwater Imaging
School of Engineering & Physical Sciences, Heriot-Watt University, Edinburgh, UK · Marine Data Science Group, Christian Albrechts University of Kiel, Kiel, Germany · Department of Marine Technology, Norwegian University of Science and Technology (NTNU), Trondheim, Norway +1
A Comparative Evaluation of Geometric Accuracy in NeRF and Gaussian Splatting
Apr 20, 2026Mikolaj Zielinski, Eryk Vykysaly, Bartlomiej Biesiada +33D Gaussian Splatting 3D Reconstruction Benchmarks
Institute of Robotics and Machine Intelligence, Poznan University of Technology
MU-GeNeRF: Multi-view Uncertainty-guided Generalizable Neural Radiance Fields for Distractor-aware Scene
Apr 20, 2026Wenjie Mu, Zhan Li, Chuanzhou Su +83D Reconstruction Neural Rendering
School of Computer Science and Technology, Tongji University, Shanghai, China · MOE Key Lab of Embedded System and Service Computing, Tongji University, Shanghai, China · College of Surveying and Geographic Informatics, Tongji University, Shanghai, China +1
PCM-NeRF: Probabilistic Camera Modeling for Neural Radiance Fields under Pose Uncertainty
Apr 20, 2026Shravan Venkatraman, Rakesh Raj Madavan, Pavan Kumar Sathya Venkatesh3D Reconstruction Camera Pose Estimation
Mohamed bin Zayed University of AI · University of Amsterdam · University of Massachusetts Amherst
Incoherent Deformation, Not Capacity: Diagnosing and Mitigating Overfitting in Dynamic Gaussian Splatting
Apr 17, 2026Ahmad Droby3D Gaussian Splatting Adaptive Gaussian Densification
Independent Researcher
NG-GS: NeRF-Guided 3D Gaussian Splatting Segmentation
Apr 16, 2026Yi He, Tao Wang, Yi Jin +33D Gaussian Splatting 3DGS Segmentation
Key Laboratory of Big Data and Artificial Intelligence in Transportation, Ministry of Education; School of Computer and Information Technology, Beijing Jiaotong University, Beijing 100044, China · Department of Artificial Intelligence, Westlake University, Hangzhou 310030, China
PartNerFace: Part-based Neural Radiance Fields for Animatable Facial Avatar Reconstruction
Apr 15, 2026Xianggang Yu, Lingteng Qiu, Xiaohang Ren +43D Face Reconstruction Human Avatar Animation
DF3DV-1K: A Large-Scale Dataset and Benchmark for Distractor-Free Novel View Synthesis
Apr 15, 2026Cheng-You Lu, Yi-Shan Hung, Wei-Ling Chi +6Novel View Synthesis Neural Radiance Fields
University of Technology Sydney · University of Sydney · National Yang Ming Chiao Tung University
A Geometric Algebra-informed NeRF Framework for Generalizable Wireless Channel Prediction
Apr 13, 2026Jingzhou Shen, Luis Lago Enamorado, Shiwen Mao +1Wireless Communications Radio Propagation Modeling
Knight Foundation School of Computing and Information Sciences, Florida International University, Miami, FL 33199, US · Department of Electrical and Computer Engineering, Auburn University, Auburn, AL 36849, US
Coverage Optimization for Camera View Selection
Apr 6, 2026Timothy Chen, Adam Dai, Maximilian Adang +2Active View Selection Next-Best-View Planning
Stanford University
Factorized Multi-Resolution HashGrid for Efficient Neural Radiance Fields: Execution on Edge-Devices
Apr 3, 2026Kim Jun-Seong, Mingyu Kim, GeonU Kim +2Neural Radiance Fields Memory-Efficient Training
Dept. of E.E., POSTECH · Dept. of CS, The Univ. of British Columbia · Grad. School of AI, POSTECH +3
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
RehearsalNeRF: Decoupling Intrinsic Neural Fields of Dynamic Illuminations for Scene Editing
Mar 30, 2026Changyeon Won, Hyunjun Jung, Jungu Cho +3Neural Radiance Fields 3D Scene Editing
Department of AI Convergence, GIST, Gwangju, Korea. · AI R&D Division, CJ Corporation, Seoul, Korea. · Department of Artificial Intelligence, Yonsei University, Seoul, Korea.

Jun 27, 2026J/K move · Enter open · S save

Reliability-Aware Monocular Depth Supervision for Sparse-View Neural Reconstruction

Wei-Teng Chu, Yashasvini Gopalan, Changju Yuan

Stanford University

Sparse-View 3D Reconstruction Neural Radiance Fields

Open paper AskPDF arXiv

Sparse-view neural reconstruction is challenging in outdoor driving scenes, where cameras usually move along a narrow forward-facing trajectory and provide limited multi-view overlap. Although monocular depth estimators can provide dense geometric priors, their predictions are noisy, and not uniformly reliable across image regions. In this work, we study monocular depth supervision for sparse-view neural reconstruction. We use Depth Anything V2 as a dense monocular depth prior, align its predictions to metric depth using scale-shift fitting, and apply depth supervision selectively through photometric masks generated from an RGB-only baseline model. We evaluate this strategy on two representative scene representations: Mip-NeRF-360 and Splatfacto. On KITTISeq02 under an every2 sparse-view setting, masked monocular depth supervision gives only marginal rendering gains for Mip-NeRF-360 and does not improve metric geometry. In contrast, Splatfacto benefits more clearly, improving PSNR from 14.903 to 15.932 and reducing RMSE from 0.542 to 0.100. Additional KITTISeq05 experiments and matched-ratio mask ablations further show that the gains for Splatfacto come from selecting reliable low-error regions rather than simply reducing the number of depth-supervised pixels. Additional experiments on the Bicycle scene show that depth supervision can improve geometry while hurting RGB rendering quality when multi-view coverage is already strong. Overall, our results suggest that monocular depth priors are useful for under-constrained sparse-view reconstruction, but should be applied selectively and with moderate weighting.