mlsanityData to 7 Oct 2026

NeRF--: Neural Radiance Fields Without Known Camera Parameters

arXiv 2102.07064 ↗First posted 14 Feb 2021cs.CVcited by 155

Not on the map. Why?

Abstract (arXiv)

Considering the problem of novel view synthesis (NVS) from only a set of 2D images, we simplify the training process of Neural Radiance Field (NeRF) on forward-facing scenes by removing the requirement of known or pre-computed camera parameters, including both intrinsics and 6DoF poses. To this end, we propose NeRF--, with three contributions: First, we show that the camera parameters can be jointly optimised as learnable parameters with NeRF training, through a photometric reconstruction; Second, to benchmark the camera parameter estimation and the quality of novel view renderings, we introduce a new dataset of path-traced synthetic scenes, termed as Blender Forward-Facing Dataset (BLEFF); Third, we conduct extensive analyses to understand the training behaviours under various camera motions, and show that in most scenarios, the joint optimisation pipeline can recover accurate camera parameters and achieve comparable novel view synthesis quality as those trained with COLMAP pre-computed camera parameters. Our code and data are available at https://nerfmm.active.vision.

Key facts. Cited by 155 papers in the map (data through 7 Oct 2026). Builds on 16 of its 46 references that are in the map. First posted on arXiv 14 Feb 2021.

Builds on

16 of 46 references.

References · 16

  1. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  2. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,590
  3. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
  4. 2020NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collectionscited by 1,230
  5. 2015ORB-SLAM: a Versatile and Accurate Monocular SLAM Systemcited by 983
  6. 2019Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representationscited by 864
  7. 2020Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenescited by 750
  8. 2019Local Light Field Fusion: Practical View Synthesis with Prescriptive Sampling Guidelinescited by 672
  9. 2020INeRF: Inverting Neural Radiance Fields for Pose Estimationcited by 381
  10. 2020Single-View View Synthesis with Multiplane Imagescited by 263
  11. 2019DeepView: View Synthesis with Learned Gradient Descentcited by 253
  12. 2020Free View Synthesiscited by 231
4 more
  1. 2020Stable View Synthesiscited by 165
  2. 2018Extreme View Synthesiscited by 94
  3. 2018InteriorNet: Mega-scale Multi-sensor Photo-realistic Indoor Scenes Datasetcited by 87
  4. 2016SceneNet RGB-D: 5M Photorealistic Images of Synthetic Indoor Trajectories with Ground Truthcited by 31

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 12; 2022: 50; 2023: 50; 2024: 25; 2025: 16; 2026: 2.

155 papers.

Sort:

By area:

  1. 2021Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstructioncited by 961
  2. 2022Block-NeRF: Scalable Large Scene Neural View Synthesiscited by 720
  3. 2021KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPscited by 672
  4. 2021AD-NeRF: Audio Driven Neural Radiance Fields for Talking Head Synthesiscited by 339
  5. 2021NeRF in the Dark: High Dynamic Range View Synthesis from Noisy Raw Imagescited by 336
  6. 2023SparseNeRF: Distilling Depth Ranking for Few-shot Novel View Synthesiscited by 247
  7. 2022NoPe-NeRF: Optimising Neural Radiance Field with No Pose Priorcited by 235
  8. 2022SPARF: Neural Radiance Fields from Sparse and Noisy Posescited by 195
  9. 2021InfoNeRF: Ray Entropy Minimization for Few-Shot Neural Volume Renderingcited by 180
  10. 2021Deblur-NeRF: Neural Radiance Fields from Blurry Imagescited by 179
  11. 2022Shape, Light, and Material Decomposition from Images using Monte Carlo Rendering and Denoisingcited by 163
  12. 2023NICER-SLAM: Neural Implicit Scene Encoding for RGB SLAMcited by 162
38 more
  1. 2022NeRF: Neural Radiance Field in 3D Vision: A Comprehensive Review (Updated Post-Gaussian Splatting)cited by 156
  2. 2022NeRDi: Single-View NeRF Synthesis with Language-Guided Diffusion as General Image Priorscited by 156
  3. 2023SUDS: Scalable Urban Dynamic Scenescited by 151
  4. 2022SPIn-NeRF: Multiview Segmentation and Perceptual Inpainting with Neural Radiance Fieldscited by 144
  5. 2023S-NeRF: Neural Radiance Fields for Street Viewscited by 116
  6. 2023Progressively Optimized Local Radiance Fields for Robust View Synthesiscited by 103
  7. 2022SAMURAI: Shape And Material from Unconstrained Real-world Arbitrary Image collectionscited by 89
  8. 2022Orbeez-SLAM: A Real-time Monocular Visual SLAM with ORB Features and NeRF-realized Mappingcited by 79
  9. 2021Learning to Stylize Novel Viewscited by 76
  10. 2022Pix2NeRF: Unsupervised Conditional π-GAN for Single Image to Neural Radiance Fields Translationcited by 73
  11. 2021SIMONe: View-Invariant, Temporally-Abstracted Object Representations via Unsupervised Video Decompositioncited by 69
  12. 2022Multi-Frame Self-Supervised Depth with Transformerscited by 64
  13. 2024SpotlessSplats: Ignoring Distractors in 3D Gaussian Splattingcited by 61
  14. 2023DBARF: Deep Bundle-Adjusting Generalizable Neural Radiance Fieldscited by 60
  15. 2022Ev-NeRF: Event Based Neural Radiance Fieldcited by 59
  16. 2022Local-to-Global Registration for Bundle-Adjusting Neural Radiance Fieldscited by 58
  17. 2023Tetra-NeRF: Representing Neural Radiance Fields Using Tetrahedracited by 57
  18. 2021CAMPARI: Camera-Aware Decomposed Generative Neural Radiance Fieldscited by 55
  19. 2022Parallel Inversion of Neural Radiance Fields for Robust Pose Estimationcited by 55
  20. 2023Urban Radiance Field Representation with Deformable Neural Mesh Primitivescited by 55
  21. 2022Uncertainty Guided Policy for Active Robotic 3D Reconstruction using Neural Radiance Fieldscited by 53
  22. 2022SparsePose: Sparse-View Camera Pose Regression and Refinementcited by 53
  23. 2023Watch Your Steps: Local Image and Scene Editing by Text Instructionscited by 50
  24. 2022SiNeRF: Sinusoidal Neural Radiance Fields for Joint Pose Estimation and Scene Reconstructioncited by 49
  25. 2024Loopy-SLAM: Dense Neural SLAM with Loop Closurescited by 48
  26. 2023NeRF-Supervised Deep Stereocited by 46
  27. 2023Reconstructing Animatable Categories from Videoscited by 46
  28. 2023PERF: Panoramic Neural Radiance Field from a Single Panoramacited by 45
  29. 2022NeRF-In: Free-Form NeRF Inpainting with RGB-D Priorscited by 43
  30. 2022NeRF2Real: Sim2real Transfer of Vision-guided Bipedal Motion Skills using Neural Radiance Fieldscited by 41
  31. 2023NeRF-LOAM: Neural Implicit Representation for Large-Scale Incremental LiDAR Odometry and Mappingcited by 41
  32. 2023Reference-guided Controllable Inpainting of Neural Radiance Fieldscited by 40
  33. 2022FWD: Real-time Novel View Synthesis with Forward Warping and Depthcited by 39
  34. 2022nerf2nerf: Pairwise Registration of Neural Radiance Fieldscited by 39
  35. 2023Instance Neural Radiance Fieldcited by 39
  36. 2022Fast Learning Radiance Fields by Shooting Much Fewer Rayscited by 38
  37. 2021NeRF in detail: Learning to sample for view synthesiscited by 35
  38. 2021NeuLF: Efficient Novel View Synthesis with Neural 4D Light Fieldcited by 33

50 most cited of 155 All 155 (JSON)