NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collections
Not on the map. Why?
Cited by 40 in Diffusion models, but placed by its own abstract, which didn’t fit.
Abstract (arXiv)
We present a learning-based method for synthesizing novel views of complex scenes using only unstructured collections of in-the-wild photographs. We build on Neural Radiance Fields (NeRF), which uses the weights of a multilayer perceptron to model the density and color of a scene as a function of 3D coordinates. While NeRF works well on images of static subjects captured under controlled settings, it is incapable of modeling many ubiquitous, real-world phenomena in uncontrolled images, such as variable illumination or transient occluders. We introduce a series of extensions to NeRF to address these issues, thereby enabling accurate reconstructions from unstructured image collections taken from the internet. We apply our system, dubbed NeRF-W, to internet photo collections of famous landmarks, and demonstrate temporally consistent novel view renderings that are significantly closer to photorealism than the prior state of the art.
Key facts. Cited by 1,230 papers in the map (data through 7 Oct 2026). First posted on arXiv 5 Aug 2020.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 130; 2022: 207; 2023: 316; 2024: 309; 2025: 179; 2026: 89.
1,230 papers.
Sort:
By area:
- 2021Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fieldscited by 2,013
- 2021Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fieldscited by 1,957
- 2023DUSt3R: Geometric 3D Vision Made Easycited by 1,526
- 2022TensoRF: Tensorial Radiance Fieldscited by 1,275
- 2021Efficient Geometry-aware 3D Generative Adversarial Networkscited by 1,204
- 20234D Gaussian Splatting for Real-Time Dynamic Scene Renderingcited by 1,144
- 2021Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstructioncited by 961
- 2021PlenOctrees for Real-time Rendering of Neural Radiance Fieldscited by 904
- 2023ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenescited by 747
- 2023K-Planes: Explicit Radiance Fields in Space, Time, and Appearancecited by 742
- 2021MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereocited by 735
- 2021Depth-supervised NeRF: Fewer Views and Faster Training for Freecited by 732
38 more
- 2022Block-NeRF: Scalable Large Scene Neural View Synthesiscited by 720
- 2021IBRNet: Learning Multi-View Image-Based Renderingcited by 698
- 2021KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPscited by 672
- 2023pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstructioncited by 668
- 2023Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fieldscited by 667
- 2021UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstructioncited by 643
- 2021RegNeRF: Regularizing Neural Radiance Fields for View Synthesis from Sparse Inputscited by 614
- 2022Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generationcited by 597
- 2023Nerfstudio: A Modular Framework for Neural Radiance Field Developmentcited by 596
- 2021NICE-SLAM: Neural Implicit Scalable Encoding for SLAMcited by 586
- 2023HexPlane: A Fast Representation for Dynamic Scenescited by 582
- 2021Ref-NeRF: Structured View-Dependent Appearance for Neural Radiance Fieldscited by 569
- 2021Neural Fields in Visual Computing and Beyondcited by 539
- 2021FastNeRF: High-Fidelity Neural Rendering at 200FPScited by 510
- 2022Point-NeRF: Point-based Neural Radiance Fieldscited by 503
- 2022HumanNeRF: Free-viewpoint Rendering of Moving People from Monocular Videocited by 483
- 2023Neuralangelo: High-Fidelity Neural Surface Reconstructioncited by 464
- 2021Dynamic View Synthesis from Dynamic Monocular Videocited by 420
- 2021In-Place Scene Labelling and Understanding with Implicit Scene Representationcited by 411
- 2021Mega-NeRF: Scalable Construction of Large-Scale NeRFs for Virtual Fly-Throughscited by 396
- 2022Kubric: A scalable dataset generatorcited by 373
- 2021GAN Inversion: A Surveycited by 366
- 2021Advances in Neural Renderingcited by 365
- 2021Extracting Triangular 3D Models, Materials, and Lighting From Imagescited by 363
- 2023DrivingGaussian: Composite Gaussian Splatting for Surrounding Dynamic Autonomous Driving Scenescited by 359
- 2022Fast Dynamic Radiance Fields with Time-Aware Neural Voxelscited by 344
- 2021AD-NeRF: Audio Driven Neural Radiance Fields for Talking Head Synthesiscited by 339
- 2021NeRF in the Dark: High Dynamic Range View Synthesis from Noisy Raw Imagescited by 336
- 2021PhySG: Inverse Rendering with Spherical Gaussians for Physics-based Material Editing and Relightingcited by 332
- 2021Neural RGB-D Surface Reconstructioncited by 312
- 2023FreeNeRF: Improving Few-shot Neural Rendering with Free Frequency Regularizationcited by 310
- 2021Dense Depth Priors for Neural Radiance Fields from Sparse Input Viewscited by 301
- 2023Text-to-3D using Gaussian Splattingcited by 299
- 2021Mixture of Volumetric Primitives for Efficient Neural Renderingcited by 277
- 20223D Neural Field Generation using Triplane Diffusioncited by 274
- 2021Urban Radiance Fieldscited by 263
- 2021A Survey of Embodied AI: From Simulators to Research Taskscited by 256
- 2021A-NeRF: Articulated Neural Radiance Fields for Learning Human Shape, Appearance, and Posecited by 233
50 most cited of 1,230 All 1,230 (JSON)
- 2026EvenSplat: Coupled 2D-3D Decomposition for Gaussian Splatting under Exposure and Illumination Variation1 Oct 2026
- 2026Resolving Mixed Single-Photon LiDAR Returns for Foreground-View and Hidden Scene Reconstruction1 Oct 2026
- 2026DyRAD: Radar Novel View Synthesis for Dynamic Driving Scenes30 Sep 2026
- 2026DecoGS: Adaptive Static-Dynamic Decoupling of 3D Gaussians for Free-Viewpoint Video Streaming15 Sep 2026
- 2026SignMimic: Robust High-Quality Sign Language Motion Generation via Human-Shape-Oblivious Pose Transfer Guidance12 Sep 2026
- 2026Single Image to Textured 3D Object Generation in Frequency Domain: From Theory to Pipeline7 Sep 2026
- 2026ADELE - Adaptive Delaunay Grids for High-Fidelity Mesh-Native Reconstruction6 Sep 2026
- 2026FujinSplat: Seeing Through Smoke with RAW-Domain Gaussian Splatting5 Sep 2026
- 2026ENEAS: Embedding-guided Neural Ensemble for Adaptive Segmentation3 Sep 2026
- 2026Chat-Edit-3D++: Interactive 3D and 4D Scene Editing via Large Language Models29 Aug 2026
- 2026WilLaGS: Latent-Conditional 3D Appearance Fields for Robust Gaussian Splatting In-the-Wild28 Aug 2026
- 20263D-USE: From Image-Level to Scene-Level Underwater Enhancement28 Aug 2026
38 more
- 2026Per-View Gaussian Predictions Enable Training-Free Distractor Filtering in Feed-Forward 3DGS27 Aug 2026
- 2026NeuDonatello: Uncertainty-Aware Framework for Accurate Neural SDF Learning27 Aug 2026
- 2026HistReNeRF: Historic Image Relocalisation within Contemporary Neural Radiance Field Reconstructions15 Aug 2026
- 2026Endo-NeRF++: Uncertainty-Aware Neural Rendering with Multi-Resolution Hash Encoding for Dynamic Surgical Scene Reconstruction30 Jul 2026
- 20264DHumanDiff: Direct Text-to-4DGS Generation for Consistent 360-Degree Dynamic Humans30 Jul 2026
- 2026UMI3D: Robust 3D Generation on Unconstrained Multi-Image Inputs via Simultaneous Focus Cross-Attention Routing27 Jul 2026
- 2026Deformable Triangle Splatting: Flexible Primitives for Real-Time Radiance Field Rendering24 Jul 2026
- 2026Instant NuRec: Feed-Forward 3D Gaussian Reconstruction for Driving Scene Simulation15 Jul 2026
- 2026ABot-3DWorld 0: A Universal World Model to Explore Any 3D Space13 Jul 2026
- 2026SSA-3DGS: Unsupervised Removal of Screen-Space Artifacts for 3D Gaussian Splatting6 Jul 2026
- 2026Beyond Isolated Objects: Relationship-aware Open Vocabulary Scene Understanding via 3D Scene Graph Analysis6 Jul 2026
- 2026MVFusion-GS: Motion-Variance Guided Temporal Attention for High-Quality Dynamic Gaussian Splatting2 Jul 2026
- 2026AugSplat: Radiance Field-Informed Gaussian Splatting for Sparse-View Settings30 Jun 2026
- 2026Walking in the Implicit: Interactive World Exploration via Neural Scene Representation29 Jun 2026
- 2026Rectifying Mask via Entropy for Distractor-Free 3DGS in Ambiguous Scenarios28 Jun 2026
- 2026DANTE-W: Diffuse Albedo Neural Texturing in the Wild26 Jun 2026
- 2026SatSplat: Geometrically-Accurate Gaussian Splatting for Satellite Imagery26 Jun 2026
- 2026ShuffleFlow: Scalable Posterior Inference for Bayesian Inverse Imaging19 Jun 2026
- 2026Wild3R: Feed-Forward 3D Gaussian Splatting from Unconstrained Sparse Photo Collection10 Jun 2026
- 2026Beyond Spherical Harmonics: Rethinking Appearance Models for Radiance Reconstruction8 Jun 2026
- 2026MLP Splatting: Object-Centric Neural Fields2 Jun 2026
- 2026Reasmory: 3D Reconstruction as Explicit Memory for VLMs Spatial Reasoning31 May 2026
- 2026Cohort-Scale Neural Atlases of Ultrasound Video30 May 2026
- 2026Underwater360: Reconstructing Underwater Scenes from Panoramic Images with Omnidirectional Gaussian Splatting26 May 2026
- 2026CAD-Free Learning of Spacecraft Pose Estimators via NeRF-Based Augmentations19 May 2026
- 2026NeRF-based Spacecraft Reconstruction from Monocular Imagery Under Illumination Variability and Pose Uncertainty18 May 2026
- 2026HarmoGS: Robust 3D Gaussian Splatting in the Wild via Conflict-Aware Gradient Harmonization13 May 2026
- 2026SeasonScapes: Learning Large-scale Re-lightable 3D Landscapes with Seasonal Variation from Sparse Webcams9 May 2026
- 2026Relightable Gaussian Splatting for Virtual Production Using Image-Based Illumination9 May 2026
- 2026Disambiguating 2D-3D Correspondences in Gaussian Splatting-based Feature Fields for Visual Localization8 May 2026
- 2026Ground4D: Spatially-Grounded Feedforward 4D Reconstruction for Unstructured Off-Road Scenes6 May 2026
- 2026Generalizable Sparse-View 3D Reconstruction from Unconstrained Images30 Apr 2026
- 2026Difix3D-W: Distractor-Free Few-Shot 3D Gaussian Splatting in the Wild30 Apr 2026
- 2026Light 'em Up: Enabling Few-Shot Low-Light 3D Gaussian Splatting with Multi-Scale Explicit Retinex Illumination Decoupling27 Apr 2026
- 2026DualSplat: Robust 3D Gaussian Splatting via Pseudo-Mask Bootstrapping from Reconstruction Failures23 Apr 2026
- 2026WildSplatter: Feed-forward 3D Gaussian Splatting with Appearance Control from Unconstrained Images23 Apr 2026
- 2026Face Anything: 4D Face Reconstruction from Any Image Sequence21 Apr 2026
- 2026MU-GeNeRF: Multi-view Uncertainty-guided Generalizable Neural Radiance Fields for Distractor-aware Scene20 Apr 2026
50 newest of 1,230 All 1,230 (JSON)
- 2022Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generationcited by 597
- 20223D Neural Field Generation using Triplane Diffusioncited by 274
- 2022DiffRF: Rendering-Guided 3D Radiance Field Diffusioncited by 204
- 2025Difix3D+: Improving 3D Reconstructions with Single-Step Diffusion Modelscited by 160
- 2024ReconX: Reconstruct Any Scene from Sparse Views with Video Diffusion Modelcited by 139
- 2023Text2NeRF: Text-Driven 3D Scene Generation with Neural Radiance Fieldscited by 122
- 2023A Unified Approach for Text- and Image-guided 4D Scene Generationcited by 82
- 2024NVS-Solver: Video Diffusion Model as Zero-Shot Novel View Synthesizercited by 79
- 2023NeuralField-LDM: Scene Generation with Hierarchical Latent Diffusion Modelscited by 76
- 2024A Diffusion Approach to Radiance Field Relighting using Multi-Illumination Synthesiscited by 37
- 2022DATID-3D: Diversity-Preserved Domain Adaptation Using Text-to-Image Diffusion for 3D Generative Modelcited by 32
- 2023Debiasing Scores and Prompts of 2D Diffusion for View-consistent Text-to-3D Generationcited by 32
12 most cited of 39 All 39 (JSON)
- 2026Single Image to Textured 3D Object Generation in Frequency Domain: From Theory to Pipeline7 Sep 2026
- 2026Intrinsic Geometry-Appearance Consistency Optimization for Sparse-View Gaussian Splatting3 Mar 2026
- 2025UniVerse: Unleashing the Scene Prior of Video Diffusion Models for Robust Radiance Field Reconstruction2 Oct 2025
- 2025DT-NeRF: A Diffusion and Transformer-Based Optimization Approach for Neural Radiance Fields in 3D Reconstruction21 Sep 2025
- 2025VDEGaussian: Video Diffusion Enhanced 4D Gaussian Splatting for Dynamic Urban Scenes Modeling4 Aug 2025
- 2025SHaDe: Compact and Consistent Dynamic 3D Reconstruction via Tri-Plane Deformation and Latent Diffusion22 May 2025
- 2025Generative AI for Film Creation: A Survey of Recent Advances11 Apr 2025
- 2025SparseGS-W: Sparse-View 3D Gaussian Splatting in the Wild with Generative Priors25 Mar 2025
- 2025Taming Video Diffusion Prior with Scene-Grounding Guidance for 3D Gaussian Splatting from Sparse Inputs7 Mar 2025
- 2025Difix3D+: Improving 3D Reconstructions with Single-Step Diffusion Models3 Mar 2025
- 2024Perturb-and-Revise: Flexible 3D Editing with Generative Trajectories6 Dec 2024
- 2024How to Use Diffusion Priors under Sparse Views?3 Dec 2024
12 newest of 39 All 39 (JSON)
- 2024OmniRe: Omni Urban Scene Reconstructioncited by 159
- 2021Pathdreamer: A World Model for Indoor Navigationcited by 117
- 2024HUGSIM: A Real-Time, Photo-Realistic and Closed-Loop Simulator for Autonomous Drivingcited by 84
- 2024MagicDrive3D: Controllable 3D Generation for Any-View Rendering in Street Scenescited by 70
- 2022DiffDreamer: Towards Consistent Unsupervised Single-view Scene Extrapolation with Conditional Diffusion Modelscited by 51
- 2024Dynamic 3D Gaussian Fields for Urban Areascited by 35
- 2024S-NeRF++: Autonomous Driving Simulation via Neural Reconstruction and Generationcited by 28
- 2024VDG: Vision-Only Dynamic Gaussian for Driving Simulationcited by 16
- 2023Predictive World Models from Real-World Partial Observationscited by 4
- 2026ABot-3DWorld 0: A Universal World Model to Explore Any 3D Spacecited by 1
- 2026ABot-3DWorld 0: A Universal World Model to Explore Any 3D Space13 Jul 2026
- 2024HUGSIM: A Real-Time, Photo-Realistic and Closed-Loop Simulator for Autonomous Driving2 Dec 2024
- 2024OmniRe: Omni Urban Scene Reconstruction29 Aug 2024
- 2024VDG: Vision-Only Dynamic Gaussian for Driving Simulation26 Jun 2024
- 2024Dynamic 3D Gaussian Fields for Urban Areas5 Jun 2024
- 2024MagicDrive3D: Controllable 3D Generation for Any-View Rendering in Street Scenes23 May 2024
- 2024S-NeRF++: Autonomous Driving Simulation via Neural Reconstruction and Generation3 Feb 2024
- 2023Predictive World Models from Real-World Partial Observations12 Jan 2023
- 2022DiffDreamer: Towards Consistent Unsupervised Single-view Scene Extrapolation with Conditional Diffusion Models22 Nov 2022
- 2021Pathdreamer: A World Model for Indoor Navigation18 May 2021
- 2024When LLMs step into the 3D World: A Survey and Meta-Analysis of 3D Tasks via Multi-modal Large Language Modelscited by 41
- 2024Chat-Edit-3D: Interactive 3D Scene Editing via Text Promptscited by 19
- 2024LLaNA: Large Language and NeRF Assistantcited by 6
- 2026OpenVoxel: Training-Free Grouping and Captioning Voxels for Open-Vocabulary 3D Scene Understandingcited by 5
- 2026Chat-Edit-3D++: Interactive 3D and 4D Scene Editing via Large Language Modelscited by 1
- 2023Compositional Semantics for Open Vocabulary Spatio-semantic Representationscited by 0
- 2025Scaling LLaNA: Advancing NeRF-Language Understanding Through Large-Scale Trainingcited by 0
- 2025ArchGPT: Understanding the World's Architectures with Large Multimodal Modelscited by 0
- 2026Beyond Isolated Objects: Relationship-aware Open Vocabulary Scene Understanding via 3D Scene Graph Analysiscited by 0
- 2026Chat-Edit-3D++: Interactive 3D and 4D Scene Editing via Large Language Models29 Aug 2026
- 2026Beyond Isolated Objects: Relationship-aware Open Vocabulary Scene Understanding via 3D Scene Graph Analysis6 Jul 2026
- 2026OpenVoxel: Training-Free Grouping and Captioning Voxels for Open-Vocabulary 3D Scene Understanding14 Jan 2026
- 2025ArchGPT: Understanding the World's Architectures with Large Multimodal Models25 Sep 2025
- 2025Scaling LLaNA: Advancing NeRF-Language Understanding Through Large-Scale Training18 Apr 2025
- 2024Chat-Edit-3D: Interactive 3D Scene Editing via Text Prompts9 Jul 2024
- 2024LLaNA: Large Language and NeRF Assistant17 Jun 2024
- 2024When LLMs step into the 3D World: A Survey and Meta-Analysis of 3D Tasks via Multi-modal Large Language Models16 May 2024
- 2023Compositional Semantics for Open Vocabulary Spatio-semantic Representations8 Oct 2023
- 2023NeuRAD: Neural Rendering for Autonomous Drivingcited by 146
- 2024Forging Vision Foundation Models for Autonomous Driving: Challenges, Methodologies, and Opportunitiescited by 24
- 2023Applications of Large Scale Foundation Models for Autonomous Drivingcited by 14
- 2025Learning-based 3D Reconstruction in Autonomous Driving: A Comprehensive Surveycited by 9
- 2025DrivingGaussian++: Towards Realistic Reconstruction and Editable Simulation for Surrounding Dynamic Driving Scenescited by 4
- 2026Instant NuRec: Feed-Forward 3D Gaussian Reconstruction for Driving Scene Simulationcited by 2
- 2026DyRAD: Radar Novel View Synthesis for Dynamic Driving Scenescited by 0
- 2026DyRAD: Radar Novel View Synthesis for Dynamic Driving Scenes30 Sep 2026
- 2026Instant NuRec: Feed-Forward 3D Gaussian Reconstruction for Driving Scene Simulation15 Jul 2026
- 2025DrivingGaussian++: Towards Realistic Reconstruction and Editable Simulation for Surrounding Dynamic Driving Scenes28 Aug 2025
- 2025Learning-based 3D Reconstruction in Autonomous Driving: A Comprehensive Survey17 Mar 2025
- 2024Forging Vision Foundation Models for Autonomous Driving: Challenges, Methodologies, and Opportunities16 Jan 2024
- 2023NeuRAD: Neural Rendering for Autonomous Driving26 Nov 2023
- 2023Applications of Large Scale Foundation Models for Autonomous Driving20 Nov 2023
- 2021Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fieldscited by 2,013
- 2021Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fieldscited by 1,957
- 2023DUSt3R: Geometric 3D Vision Made Easycited by 1,526
- 2022TensoRF: Tensorial Radiance Fieldscited by 1,275
- 2021Efficient Geometry-aware 3D Generative Adversarial Networkscited by 1,204
- 20234D Gaussian Splatting for Real-Time Dynamic Scene Renderingcited by 1,144
- 2021Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstructioncited by 961
- 2021PlenOctrees for Real-time Rendering of Neural Radiance Fieldscited by 904
- 2023ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenescited by 747
- 2023K-Planes: Explicit Radiance Fields in Space, Time, and Appearancecited by 742
- 2021MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereocited by 735
- 2021Depth-supervised NeRF: Fewer Views and Faster Training for Freecited by 732
12 most cited of 1,160 All 1,160 (JSON)
- 2026EvenSplat: Coupled 2D-3D Decomposition for Gaussian Splatting under Exposure and Illumination Variation1 Oct 2026
- 2026Resolving Mixed Single-Photon LiDAR Returns for Foreground-View and Hidden Scene Reconstruction1 Oct 2026
- 2026DecoGS: Adaptive Static-Dynamic Decoupling of 3D Gaussians for Free-Viewpoint Video Streaming15 Sep 2026
- 2026SignMimic: Robust High-Quality Sign Language Motion Generation via Human-Shape-Oblivious Pose Transfer Guidance12 Sep 2026
- 2026ADELE - Adaptive Delaunay Grids for High-Fidelity Mesh-Native Reconstruction6 Sep 2026
- 2026FujinSplat: Seeing Through Smoke with RAW-Domain Gaussian Splatting5 Sep 2026
- 2026ENEAS: Embedding-guided Neural Ensemble for Adaptive Segmentation3 Sep 2026
- 2026WilLaGS: Latent-Conditional 3D Appearance Fields for Robust Gaussian Splatting In-the-Wild28 Aug 2026
- 20263D-USE: From Image-Level to Scene-Level Underwater Enhancement28 Aug 2026
- 2026Per-View Gaussian Predictions Enable Training-Free Distractor Filtering in Feed-Forward 3DGS27 Aug 2026
- 2026NeuDonatello: Uncertainty-Aware Framework for Accurate Neural SDF Learning27 Aug 2026
- 2026HistReNeRF: Historic Image Relocalisation within Contemporary Neural Radiance Field Reconstructions15 Aug 2026
12 newest of 1,160 All 1,160 (JSON)