mlsanityData to 7 Oct 2026

MINE: Towards Continuous Depth MPI with NeRF for Novel View Synthesis

arXiv 2103.14910 ↗First posted 27 Mar 2021cs.CV cs.GR cs.LGcited by 133

Not on the map. Why?

Abstract (arXiv)

In this paper, we propose MINE to perform novel view synthesis and depth estimation via dense 3D reconstruction from a single image. Our approach is a continuous depth generalization of the Multiplane Images (MPI) by introducing the NEural radiance fields (NeRF). Given a single image as input, MINE predicts a 4-channel image (RGB and volume density) at arbitrary depth values to jointly reconstruct the camera frustum and fill in occluded contents. The reconstructed and inpainted frustum can then be easily rendered into novel RGB or depth views using differentiable rendering. Extensive experiments on RealEstate10K, KITTI and Flowers Light Fields show that our MINE outperforms state-of-the-art by a large margin in novel view synthesis. We also achieve competitive results in depth estimation on iBims-1 and NYU-v2 without annotated depth supervision. Our source code is available at https://github.com/vincentfung13/MINE

Key facts. Cited by 133 papers in the map (data through 7 Oct 2026). Builds on 41 of its 64 references that are in the map. First posted on arXiv 27 Mar 2021.

Builds on

41 of 64 references.

References · 41

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  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. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
  6. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,170
  7. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
  8. 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,574
  9. 2019Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfercited by 1,484
  10. 2018On the Spectral Bias of Neural Networkscited by 1,321
  11. 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,264
  12. 2020NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collectionscited by 1,230
29 more
  1. 2015Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)cited by 1,061
  2. 2018Learning Implicit Fields for Generative Shape Modelingcited by 1,060
  3. 2019Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representationscited by 864
  4. 2016Unsupervised Monocular Depth Estimation with Left-Right Consistencycited by 819
  5. 2017Unsupervised Learning of Depth and Ego-Motion from Videocited by 778
  6. 2020Convolutional Occupancy Networkscited by 760
  7. 2018MegaDepth: Learning Single-View Depth Prediction from Internet Photoscited by 731
  8. 2019Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervisioncited by 699
  9. 2018DeepVoxels: Learning Persistent 3D Feature Embeddingscited by 401
  10. 2020Local Implicit Grid Representations for 3D Scenescited by 372
  11. 2016Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescuecited by 368
  12. 2019SynSin: End-to-end View Synthesis from a Single Imagecited by 364
  13. 2020Single-View View Synthesis with Multiplane Imagescited by 263
  14. 2019Learning Shape Templates with Structured Implicit Functionscited by 242
  15. 2018Stereo Magnification: Learning View Synthesis using Multiplane Imagescited by 206
  16. 20203D Photography using Context-aware Layered Depth Inpaintingcited by 206
  17. 2017Learning a Multi-View Stereo Machinecited by 194
  18. 2019Pushing the Boundaries of View Extrapolation with Multiplane Imagescited by 191
  19. 2016Single-Image Depth Perception in the Wildcited by 179
  20. 2018Unsupervised Learning of Depth and Ego-Motion from Monocular Video Using 3D Geometric Constraintscited by 179
  21. 2017Learning Depth from Monocular Videos using Direct Methodscited by 154
  22. 2018Evaluation of CNN-based Single-Image Depth Estimation Methodscited by 137
  23. 20193D Ken Burns Effect from a Single Imagecited by 128
  24. 2017SfM-Net: Learning of Structure and Motion from Videocited by 89
  25. 2018Layer-structured 3D Scene Inference via View Synthesiscited by 82
  26. 2019Controlling Neural Level Setscited by 76
  27. 2016Deep3D: Fully Automatic 2D-to-3D Video Conversion with Deep Convolutional Neural Networkscited by 72
  28. 2017Learning to Synthesize a 4D RGBD Light Field from a Single Imagecited by 60
  29. 2019Learning a Neural 3D Texture Space from 2D Exemplarscited by 53

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 10; 2022: 24; 2023: 49; 2024: 26; 2025: 19; 2026: 5.

133 papers.

Sort:

By area:

  1. 2021RegNeRF: Regularizing Neural Radiance Fields for View Synthesis from Sparse Inputscited by 614
  2. 2021Neural Fields in Visual Computing and Beyondcited by 539
  3. 2021Advances in Neural Renderingcited by 365
  4. 2023Make-It-3D: High-Fidelity 3D Creation from A Single Image with Diffusion Priorcited by 341
  5. 2021Urban Radiance Fieldscited by 263
  6. 2021GeoNeRF: Generalizing NeRF with Geometry Priorscited by 195
  7. 2023COLMAP-Free 3D Gaussian Splattingcited by 193
  8. 2022SinNeRF: Training Neural Radiance Fields on Complex Scenes from a Single Imagecited by 165
  9. 2022NeRF: Neural Radiance Field in 3D Vision: A Comprehensive Review (Updated Post-Gaussian Splatting)cited by 156
  10. 2023SelfOcc: Self-Supervised Vision-Based 3D Occupancy Predictioncited by 133
  11. 2023S-NeRF: Neural Radiance Fields for Street Viewscited by 116
  12. 2024Flash3D: Feed-Forward Generalisable 3D Scene Reconstruction from a Single Imagecited by 113
38 more
  1. 2021NeRF-SR: High-Quality Neural Radiance Fields using Supersamplingcited by 95
  2. 2024TIP-Editor: An Accurate 3D Editor Following Both Text-Prompts And Image-Promptscited by 76
  3. 2023SceneDreamer: Unbounded 3D Scene Generation from 2D Image Collectionscited by 72
  4. 2023Behind the Scenes: Density Fields for Single View Reconstructioncited by 63
  5. 2024Advances in 3D Generation: A Surveycited by 62
  6. 2022Single-View View Synthesis in the Wild with Learned Adaptive Multiplane Imagescited by 59
  7. 2022Generative Multiplane Images: Making a 2D GAN 3D-Awarecited by 57
  8. 2025Bolt3D: Generating 3D Scenes in Secondscited by 57
  9. 2024AGG: Amortized Generative 3D Gaussians for Single Image to 3Dcited by 51
  10. 2022SceneRF: Self-Supervised Monocular 3D Scene Reconstruction with Radiance Fieldscited by 49
  11. 20213D Photo Stylization: Learning to Generate Stylized Novel Views from a Single Imagecited by 45
  12. 2023PERF: Panoramic Neural Radiance Field from a Single Panoramacited by 45
  13. 2023Persistent Nature: A Generative Model of Unbounded 3D Worldscited by 44
  14. 2023ViP-NeRF: Visibility Prior for Sparse Input Neural Radiance Fieldscited by 43
  15. 2022V4d: voxel for 4d novel view synthesiscited by 42
  16. 2022Relighting4D: Neural Relightable Human from Videoscited by 41
  17. 2023MixNeRF: Modeling a Ray with Mixture Density for Novel View Synthesis from Sparse Inputscited by 40
  18. 2023OccNeRF: Advancing 3D Occupancy Prediction in LiDAR-Free Environmentscited by 39
  19. 2022One-shot Implicit Animatable Avatars with Model-based Priorscited by 38
  20. 2023FlowCam: Training Generalizable 3D Radiance Fields without Camera Poses via Pixel-Aligned Scene Flowcited by 38
  21. 2023MonoNeRD: NeRF-like Representations for Monocular 3D Object Detectioncited by 33
  22. 2022PlaneDepth: Self-supervised Depth Estimation via Orthogonal Planescited by 32
  23. 2025SynCity: Training-Free Generation of 3D Worldscited by 30
  24. 2023FlipNeRF: Flipped Reflection Rays for Few-shot Novel View Synthesiscited by 29
  25. 20243DitScene: Editing Any Scene via Language-guided Disentangled Gaussian Splattingcited by 25
  26. 20233D Cinemagraphy from a Single Imagecited by 23
  27. 2024Invisible Stitch: Generating Smooth 3D Scenes with Depth Inpaintingcited by 23
  28. 2025Advances in Feed-Forward 3D Reconstruction and View Synthesis: A Surveycited by 23
  29. 2025LongSplat: Robust Unposed 3D Gaussian Splatting for Casual Long Videoscited by 23
  30. 2023Super-NeRF: View-consistent Detail Generation for NeRF super-resolutioncited by 21
  31. 2025DVGT: Driving Visual Geometry Transformercited by 20
  32. 2023Local Implicit Ray Function for Generalizable Radiance Field Representationcited by 19
  33. 2024Neural Radiance Field in Autonomous Driving: A Surveycited by 19
  34. 2022MPIB: An MPI-Based Bokeh Rendering Framework for Realistic Partial Occlusion Effectscited by 17
  35. 2023Decoupling Dynamic Monocular Videos for Dynamic View Synthesiscited by 17
  36. 2023ConsistentNeRF: Enhancing Neural Radiance Fields with 3D Consistency for Sparse View Synthesiscited by 17
  37. 2022IR-MCL: Implicit Representation-Based Online Global Localizationcited by 14
  38. 2023Tiled Multiplane Images for Practical 3D Photographycited by 14

50 most cited of 133 All 133 (JSON)