mlsanityData to 7 Oct 2026

Dense Depth Priors for Neural Radiance Fields from Sparse Input Views

arXiv 2112.03288 ↗First posted 6 Dec 2021cs.CVcited by 301

Not on the map. Why?

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

Abstract (arXiv)

Neural radiance fields (NeRF) encode a scene into a neural representation that enables photo-realistic rendering of novel views. However, a successful reconstruction from RGB images requires a large number of input views taken under static conditions - typically up to a few hundred images for room-size scenes. Our method aims to synthesize novel views of whole rooms from an order of magnitude fewer images. To this end, we leverage dense depth priors in order to constrain the NeRF optimization. First, we take advantage of the sparse depth data that is freely available from the structure from motion (SfM) preprocessing step used to estimate camera poses. Second, we use depth completion to convert these sparse points into dense depth maps and uncertainty estimates, which are used to guide NeRF optimization. Our method enables data-efficient novel view synthesis on challenging indoor scenes, using as few as 18 images for an entire scene.

Key facts. Cited by 301 papers in the map (data through 7 Oct 2026). Builds on 16 of its 31 references that are in the map. First posted on arXiv 6 Dec 2021.

Builds on

16 of 31 references.

References · 16

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  4. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
  5. 2017Matterport3D: Learning from RGB-D Data in Indoor Environmentscited by 1,354
  6. 2020NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collectionscited by 1,230
  7. 2021Depth-supervised NeRF: Fewer Views and Faster Training for Freecited by 732
  8. 2019DeepView: View Synthesis with Learned Gradient Descentcited by 253
  9. 2020Free View Synthesiscited by 231
  10. 2018Stereo Magnification: Learning View Synthesis using Multiplane Imagescited by 206
  11. 2019Pushing the Boundaries of View Extrapolation with Multiplane Imagescited by 191
  12. 2021NerfingMVS: Guided Optimization of Neural Radiance Fields for Indoor Multi-view Stereocited by 191
4 more
  1. 2018Learning Depth with Convolutional Spatial Propagation Networkcited by 135
  2. 2018Depth Estimation via Affinity Learned with Convolutional Spatial Propagation Networkcited by 109
  3. 2017ScanComplete: Large-Scale Scene Completion and Semantic Segmentation for 3D Scanscited by 103
  4. 2019SG-NN: Sparse Generative Neural Networks for Self-Supervised Scene Completion of RGB-D Scanscited by 77

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 34; 2023: 102; 2024: 97; 2025: 53; 2026: 15.

301 papers.

Sort:

By area:

  1. 2022MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstructioncited by 467
  2. 2024Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimationcited by 389
  3. 2022Decomposing NeRF for Editing via Feature Field Distillationcited by 370
  4. 2023Compact 3D Gaussian Representation for Radiance Fieldcited by 365
  5. 2025GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Controlcited by 325
  6. 2023ReconFusion: 3D Reconstruction with Diffusion Priorscited by 317
  7. 2023FreeNeRF: Improving Few-shot Neural Rendering with Free Frequency Regularizationcited by 310
  8. 2024DNGaussian: Optimizing Sparse-View 3D Gaussian Radiance Fields with Global-Local Depth Normalizationcited by 256
  9. 2022NoPe-NeRF: Optimising Neural Radiance Field with No Pose Priorcited by 235
  10. 2022SPARF: Neural Radiance Fields from Sparse and Noisy Posescited by 195
  11. 2023Depth-Regularized Optimization for 3D Gaussian Splatting in Few-Shot Imagescited by 172
  12. 2025Difix3D+: Improving 3D Reconstructions with Single-Step Diffusion Modelscited by 160
38 more
  1. 2022Instant Volumetric Head Avatarscited by 157
  2. 2022NeRF: Neural Radiance Field in 3D Vision: A Comprehensive Review (Updated Post-Gaussian Splatting)cited by 156
  3. 2022NeRDi: Single-View NeRF Synthesis with Language-Guided Diffusion as General Image Priorscited by 156
  4. 2023SUDS: Scalable Urban Dynamic Scenescited by 151
  5. 2024DN-Splatter: Depth and Normal Priors for Gaussian Splatting and Meshingcited by 136
  6. 2023SelfOcc: Self-Supervised Vision-Based 3D Occupancy Predictioncited by 133
  7. 2023DiffusioNeRF: Regularizing Neural Radiance Fields with Denoising Diffusion Modelscited by 127
  8. 2022NeuRIS: Neural Reconstruction of Indoor Scenes Using Normal Priorscited by 125
  9. 2023Text2NeRF: Text-Driven 3D Scene Generation with Neural Radiance Fieldscited by 122
  10. 2024CoR-GS: Sparse-View 3D Gaussian Splatting via Co-Regularizationcited by 120
  11. 2023S-NeRF: Neural Radiance Fields for Street Viewscited by 116
  12. 2024Pixel-GS: Density Control with Pixel-aware Gradient for 3D Gaussian Splattingcited by 111
  13. 2024Motion-aware 3D Gaussian Splatting for Efficient Dynamic Scene Reconstructioncited by 100
  14. 2024How NeRFs and 3D Gaussian Splatting are Reshaping SLAM: a Surveycited by 72
  15. 2022E-NeRF: Neural Radiance Fields from a Moving Event Cameracited by 70
  16. 2024MultiDiff: Consistent Novel View Synthesis from a Single Imagecited by 67
  17. 2022Removing Objects From Neural Radiance Fieldscited by 66
  18. 2023Neural LiDAR Fields for Novel View Synthesiscited by 65
  19. 2023Behind the Scenes: Density Fields for Single View Reconstructioncited by 63
  20. 2022Sat-NeRF: Learning Multi-View Satellite Photogrammetry With Transient Objects and Shadow Modeling Using RPC Camerascited by 59
  21. 2023GeCoNeRF: Few-shot Neural Radiance Fields via Geometric Consistencycited by 54
  22. 2023NeRFMeshing: Distilling Neural Radiance Fields into Geometrically-Accurate 3D Meshescited by 52
  23. 2024DOGS: Distributed-Oriented Gaussian Splatting for Large-Scale 3D Reconstruction Via Gaussian Consensuscited by 51
  24. 2022SceneRF: Self-Supervised Monocular 3D Scene Reconstruction with Radiance Fieldscited by 49
  25. 2022NeRF-RPN: A general framework for object detection in NeRFscited by 46
  26. 2023LiDAR-NeRF: Novel LiDAR View Synthesis via Neural Radiance Fieldscited by 46
  27. 2022RGBD2: Generative Scene Synthesis via Incremental View Inpainting using RGBD Diffusion Modelscited by 45
  28. 2023NeRF-LiDAR: Generating Realistic LiDAR Point Clouds with Neural Radiance Fieldscited by 44
  29. 2023SimpleNeRF: Regularizing Sparse Input Neural Radiance Fields with Simpler Solutionscited by 44
  30. 2023Robust e-NeRF: NeRF from Sparse & Noisy Events under Non-Uniform Motioncited by 44
  31. 2023Deformable 3D Gaussian Splatting for Animatable Human Avatarscited by 44
  32. 2024PhyRecon: Physically Plausible Neural Scene Reconstructioncited by 44
  33. 2022NeRF-In: Free-Form NeRF Inpainting with RGB-D Priorscited by 43
  34. 2023ViP-NeRF: Visibility Prior for Sparse Input Neural Radiance Fieldscited by 43
  35. 2025GenFusion: Closing the Loop between Reconstruction and Generation via Videoscited by 41
  36. 2023MixNeRF: Modeling a Ray with Mixture Density for Novel View Synthesis from Sparse Inputscited by 40
  37. 2023Deceptive-NeRF/3DGS: Diffusion-Generated Pseudo-Observations for High-Quality Sparse-View Reconstructioncited by 39
  38. 2023Points-to-3D: Bridging the Gap between Sparse Points and Shape-Controllable Text-to-3D Generationcited by 39

50 most cited of 301 All 301 (JSON)