mlsanityData to 7 Oct 2026

SinNeRF: Training Neural Radiance Fields on Complex Scenes from a Single Image

arXiv 2204.00928 ↗First posted 2 Apr 2022cs.CVcited by 165

Not on the map. Why?

Cited by 20 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Despite the rapid development of Neural Radiance Field (NeRF), the necessity of dense covers largely prohibits its wider applications. While several recent works have attempted to address this issue, they either operate with sparse views (yet still, a few of them) or on simple objects/scenes. In this work, we consider a more ambitious task: training neural radiance field, over realistically complex visual scenes, by "looking only once", i.e., using only a single view. To attain this goal, we present a Single View NeRF (SinNeRF) framework consisting of thoughtfully designed semantic and geometry regularizations. Specifically, SinNeRF constructs a semi-supervised learning process, where we introduce and propagate geometry pseudo labels and semantic pseudo labels to guide the progressive training process. Extensive experiments are conducted on complex scene benchmarks, including NeRF synthetic dataset, Local Light Field Fusion dataset, and DTU dataset. We show that even without pre-training on multi-view datasets, SinNeRF can yield photo-realistic novel-view synthesis results. Under the single image setting, SinNeRF significantly outperforms the current state-of-the-art NeRF baselines in all cases. Project page: https://vita-group.github.io/SinNeRF/

Key facts. Cited by 165 papers in the map (data through 7 Oct 2026). Builds on 51 of its 65 references that are in the map. First posted on arXiv 2 Apr 2022.

Builds on

51 of 65 references.

References · 51

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  4. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  5. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  6. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,698
  7. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  8. 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,214
  9. 2021Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fieldscited by 2,013
  10. 2021Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fieldscited by 1,957
  11. 2021Plenoxels: Radiance Fields without Neural Networkscited by 1,607
  12. 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,574
38 more
  1. 2017Deep Image Priorcited by 1,097
  2. 2016A Point Set Generation Network for 3D Object Reconstruction from a Single Imagecited by 972
  3. 2021Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstructioncited by 961
  4. 2019PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitizationcited by 818
  5. 2018MVSNet: Depth Inference for Unstructured Multi-view Stereocited by 780
  6. 2019On the Variance of the Adaptive Learning Rate and Beyondcited by 763
  7. 2021MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereocited by 735
  8. 2021Depth-supervised NeRF: Fewer Views and Faster Training for Freecited by 732
  9. 2018MegaDepth: Learning Single-View Depth Prediction from Internet Photoscited by 731
  10. 2021IBRNet: Learning Multi-View Image-Based Renderingcited by 698
  11. 2020GRAF: Generative Radiance Fields for 3D-Aware Image Synthesiscited by 688
  12. 2021KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPscited by 672
  13. 2018Pixel2Mesh: Generating 3D Mesh Models from Single RGB Imagescited by 649
  14. 2021RegNeRF: Regularizing Neural Radiance Fields for View Synthesis from Sparse Inputscited by 614
  15. 2021Ref-NeRF: Structured View-Dependent Appearance for Neural Radiance Fieldscited by 569
  16. 2021Zero-Shot Text-Guided Object Generation with Dream Fieldscited by 513
  17. 2021Putting NeRF on a Diet: Semantically Consistent Few-Shot View Synthesiscited by 464
  18. 2019Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matchingcited by 414
  19. 2018DeepVoxels: Learning Persistent 3D Feature Embeddingscited by 401
  20. 2021CLIP-NeRF: Text-and-Image Driven Manipulation of Neural Radiance Fieldscited by 369
  21. 2020Differentiable Augmentation for Data-Efficient GAN Trainingcited by 361
  22. 2019SinGAN: Learning a Generative Model from a Single Natural Imagecited by 348
  23. 2021Deep ViT Features as Dense Visual Descriptorscited by 327
  24. 2017Geometric GANcited by 232
  25. 2020Learning to Recover 3D Scene Shape from a Single Imagecited by 214
  26. 2022Splicing ViT Features for Semantic Appearance Transfercited by 209
  27. 20203D Photography using Context-aware Layered Depth Inpaintingcited by 206
  28. 2021Neural Rays for Occlusion-aware Image-based Renderingcited by 192
  29. 2020GRF: Learning a General Radiance Field for 3D Representation and Renderingcited by 183
  30. 2019DeepHuman: 3D Human Reconstruction from a Single Imagecited by 182
  31. 2021InfoNeRF: Ray Entropy Minimization for Few-Shot Neural Volume Renderingcited by 180
  32. 2017Learning Depth from Monocular Videos using Direct Methodscited by 154
  33. 2021MINE: Towards Continuous Depth MPI with NeRF for Novel View Synthesiscited by 133
  34. 2021NeRFReN: Neural Radiance Fields with Reflectionscited by 121
  35. 2017MarrNet: 3D Shape Reconstruction via 2.5D Sketchescited by 108
  36. 2018Layer-structured 3D Scene Inference via View Synthesiscited by 82
  37. 2019Learning a Neural 3D Texture Space from 2D Exemplarscited by 53
  38. 2020M^3VSNet: Unsupervised Multi-metric Multi-view Stereo Networkcited by 29

50 most cited of 51 All 51 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 19; 2023: 72; 2024: 53; 2025: 19; 2026: 2.

165 papers.

Sort:

By area:

  1. 2023Compact 3D Gaussian Representation for Radiance Fieldcited by 365
  2. 2023Make-It-3D: High-Fidelity 3D Creation from A Single Image with Diffusion Priorcited by 341
  3. 2023Video-P2P: Video Editing with Cross-attention Controlcited by 312
  4. 2023RealFusion: 360deg Reconstruction of Any Object from a Single Imagecited by 305
  5. 2023FSGS: Real-Time Few-shot View Synthesis using Gaussian Splattingcited by 278
  6. 2023ImageDream: Image-Prompt Multi-view Diffusion for 3D Generationcited by 256
  7. 2023SparseNeRF: Distilling Depth Ranking for Few-shot Novel View Synthesiscited by 247
  8. 2023COLMAP-Free 3D Gaussian Splattingcited by 193
  9. 2024CityGaussian: Real-time High-quality Large-Scale Scene Rendering with Gaussianscited by 190
  10. 2023NerfDiff: Single-image View Synthesis with NeRF-guided Distillation from 3D-aware Diffusioncited by 179
  11. 2023SceneScape: Text-Driven Consistent Scene Generationcited by 160
  12. 2022NeRF: Neural Radiance Field in 3D Vision: A Comprehensive Review (Updated Post-Gaussian Splatting)cited by 156
38 more
  1. 2022NeRDi: Single-View NeRF Synthesis with Language-Guided Diffusion as General Image Priorscited by 156
  2. 2022NeuralLift-360: Lifting An In-the-wild 2D Photo to A 3D Object with 360deg Viewscited by 148
  3. 2023SparseGS: Sparse View Synthesis using 3D Gaussian Splattingcited by 134
  4. 2022Is Attention All That NeRF Needs?cited by 113
  5. 2023Viewset Diffusion: (0-)Image-Conditioned 3D Generative Models from 2D Datacited by 113
  6. 2024Flash3D: Feed-Forward Generalisable 3D Scene Reconstruction from a Single Imagecited by 113
  7. 2023ZeroNVS: Zero-Shot 360-Degree View Synthesis from a Single Imagecited by 109
  8. 2023SINE: Semantic-driven Image-based NeRF Editing with Prior-guided Editing Fieldcited by 93
  9. 2024NeRF On-the-go: Exploiting Uncertainty for Distractor-free NeRFs in the Wildcited by 85
  10. 2024DreamScene360: Unconstrained Text-to-3D Scene Generation with Panoramic Gaussian Splattingcited by 81
  11. 2023Consistent-1-to-3: Consistent Image to 3D View Synthesis via Geometry-aware Diffusion Modelscited by 79
  12. 2022NeRF-SOS: Any-View Self-supervised Object Segmentation on Complex Scenescited by 71
  13. 2022Unified Implicit Neural Stylizationcited by 67
  14. 2024InstantSplat: Sparse-view Gaussian Splatting in Secondscited by 67
  15. 2023Real-Time Radiance Fields for Single-Image Portrait View Synthesiscited by 64
  16. 2024GaussianObject: High-Quality 3D Object Reconstruction from Four Views with Gaussian Splattingcited by 59
  17. 2022DiffDreamer: Towards Consistent Unsupervised Single-view Scene Extrapolation with Conditional Diffusion Modelscited by 51
  18. 2024AGG: Amortized Generative 3D Gaussians for Single Image to 3Dcited by 51
  19. 2023Control3D: Towards Controllable Text-to-3D Generationcited by 46
  20. 2023PERF: Panoramic Neural Radiance Field from a Single Panoramacited by 45
  21. 2023SimpleNeRF: Regularizing Sparse Input Neural Radiance Fields with Simpler Solutionscited by 44
  22. 2023DITTO-NeRF: Diffusion-based Iterative Text To Omni-directional 3D Modelcited by 43
  23. 2023ViP-NeRF: Visibility Prior for Sparse Input Neural Radiance Fieldscited by 43
  24. 2023Masked Space-Time Hash Encoding for Efficient Dynamic Scene Reconstructioncited by 43
  25. 2023MixNeRF: Modeling a Ray with Mixture Density for Novel View Synthesis from Sparse Inputscited by 40
  26. 2023Points-to-3D: Bridging the Gap between Sparse Points and Shape-Controllable Text-to-3D Generationcited by 39
  27. 2022One-shot Implicit Animatable Avatars with Model-based Priorscited by 38
  28. 2023Preface: A Data-driven Volumetric Prior for Few-shot Ultra High-resolution Face Synthesiscited by 37
  29. 2022Ref-NPR: Reference-Based Non-Photorealistic Radiance Fields for Controllable Scene Stylizationcited by 35
  30. 2022StegaNeRF: Embedding Invisible Information within Neural Radiance Fieldscited by 32
  31. 2022AligNeRF: High-Fidelity Neural Radiance Fields via Alignment-Aware Trainingcited by 31
  32. 2022S3-NeRF: Neural Reflectance Field from Shading and Shadow under a Single Viewpointcited by 30
  33. 2022Shape, Pose, and Appearance from a Single Image via Bootstrapped Radiance Field Inversioncited by 30
  34. 2022Scalable Neural Video Representations with Learnable Positional Featurescited by 29
  35. 2022Neural Fourier Filter Bankcited by 29
  36. 2023Sat2Density: Faithful Density Learning from Satellite-Ground Image Pairscited by 29
  37. 20244D Gaussian Splatting in the Wild with Uncertainty-Aware Regularizationcited by 28
  38. 2023Enhancing NeRF akin to Enhancing LLMs: Generalizable NeRF Transformer with Mixture-of-View-Expertscited by 27

50 most cited of 165 All 165 (JSON)