mlsanityData to 7 Oct 2026

ConsistentNeRF: Enhancing Neural Radiance Fields with 3D Consistency for Sparse View Synthesis

arXiv 2305.11031 ↗First posted 18 May 2023cs.CVcited by 17

Not on the map. Why?

Abstract (arXiv)

Neural Radiance Fields (NeRF) has demonstrated remarkable 3D reconstruction capabilities with dense view images. However, its performance significantly deteriorates under sparse view settings. We observe that learning the 3D consistency of pixels among different views is crucial for improving reconstruction quality in such cases. In this paper, we propose ConsistentNeRF, a method that leverages depth information to regularize both multi-view and single-view 3D consistency among pixels. Specifically, ConsistentNeRF employs depth-derived geometry information and a depth-invariant loss to concentrate on pixels that exhibit 3D correspondence and maintain consistent depth relationships. Extensive experiments on recent representative works reveal that our approach can considerably enhance model performance in sparse view conditions, achieving improvements of up to 94% in PSNR, 76% in SSIM, and 31% in LPIPS compared to the vanilla baselines across various benchmarks, including DTU, NeRF Synthetic, and LLFF.

Key facts. Cited by 17 papers in the map (data through 7 Oct 2026). Builds on 32 of its 43 references that are in the map. First posted on arXiv 18 May 2023.

Builds on

32 of 43 references.

References · 32

  1. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  2. 2020RAFT: Recurrent All-Pairs Field Transforms for Optical Flowcited by 2,385
  3. 2021Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fieldscited by 1,957
  4. 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,574
  5. 2019Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfercited by 1,484
  6. 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,264
  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. 2021IBRNet: Learning Multi-View Image-Based Renderingcited by 698
  10. 2019Local Light Field Fusion: Practical View Synthesis with Prescriptive Sampling Guidelinescited by 672
  11. 2021RegNeRF: Regularizing Neural Radiance Fields for View Synthesis from Sparse Inputscited by 614
  12. 2022Point-NeRF: Point-based Neural Radiance Fieldscited by 503
20 more
  1. 2021Putting NeRF on a Diet: Semantically Consistent Few-Shot View Synthesiscited by 464
  2. 2021Dense Depth Priors for Neural Radiance Fields from Sparse Input Viewscited by 301
  3. 2023SparseNeRF: Distilling Depth Ranking for Few-shot Novel View Synthesiscited by 247
  4. 2021GeoNeRF: Generalizing NeRF with Geometry Priorscited by 195
  5. 2022SPARF: Neural Radiance Fields from Sparse and Noisy Posescited by 195
  6. 2021Neural Rays for Occlusion-aware Image-based Renderingcited by 192
  7. 2021NerfingMVS: Guided Optimization of Neural Radiance Fields for Indoor Multi-view Stereocited by 191
  8. 2021Stereo Radiance Fields (SRF): Learning View Synthesis for Sparse Views of Novel Scenescited by 190
  9. 2020GRF: Learning a General Radiance Field for 3D Representation and Renderingcited by 183
  10. 2021CodeNeRF: Disentangled Neural Radiance Fields for Object Categoriescited by 183
  11. 2021InfoNeRF: Ray Entropy Minimization for Few-Shot Neural Volume Renderingcited by 180
  12. 2021Efficient Neural Radiance Fields for Interactive Free-viewpoint Videocited by 150
  13. 2022StylizedNeRF: Consistent 3D Scene Stylization as Stylized NeRF via 2D-3D Mutual Learningcited by 140
  14. 2021Improving neural implicit surfaces geometry with patch warpingcited by 136
  15. 2021MINE: Towards Continuous Depth MPI with NeRF for Novel View Synthesiscited by 133
  16. 2021ShaRF: Shape-conditioned Radiance Fields from a Single Viewcited by 92
  17. 2021PixelSynth: Generating a 3D-Consistent Experience from a Single Imagecited by 82
  18. 2021DoubleField: Bridging the Neural Surface and Radiance Fields for High-fidelity Human Reconstruction and Renderingcited by 52
  19. 2022Ray Priors through Reprojection: Improving Neural Radiance Fields for Novel View Extrapolationcited by 26
  20. 2022DevNet: Self-supervised Monocular Depth Learning via Density Volume Constructioncited by 22

Built on by

Cited by year

Citing papers per year: 2023: 4; 2024: 10; 2025: 3.

17 papers.

Sort:

By area:

  1. 2024DNGaussian: Optimizing Sparse-View 3D Gaussian Radiance Fields with Global-Local Depth Normalizationcited by 256
  2. 2023MiDaS v3.1 -- A Model Zoo for Robust Monocular Relative Depth Estimationcited by 173
  3. 2023DynPoint: Dynamic Neural Point For View Synthesiscited by 37
  4. 2025Decompositional Neural Scene Reconstruction with Generative Diffusion Priorcited by 30
  5. 20244D Gaussian Splatting in the Wild with Uncertainty-Aware Regularizationcited by 28
  6. 2024FrugalNeRF: Fast Convergence for Extreme Few-shot Novel View Synthesis without Learned Priorscited by 18
  7. 2023CorresNeRF: Image Correspondence Priors for Neural Radiance Fieldscited by 15
  8. 2024CVT-xRF: Contrastive In-Voxel Transformer for 3D Consistent Radiance Fields from Sparse Inputscited by 13
  9. 2025HoloScene: Simulation-Ready Interactive 3D Worlds from a Single Videocited by 13
  10. 2024TrackNeRF: Bundle Adjusting NeRF from Sparse and Noisy Views via Feature Trackscited by 12
  11. 2024UC-NeRF: Uncertainty-aware Conditional Neural Radiance Fields from Endoscopic Sparse Viewscited by 8
  12. 2024Uncertainty-guided Optimal Transport in Depth Supervised Sparse-View 3D Gaussiancited by 6
5 more
  1. 2023TiAVox: Time-aware Attenuation Voxels for Sparse-view 4D DSA Reconstructioncited by 5
  2. 2024CombiNeRF: A Combination of Regularization Techniques for Few-Shot Neural Radiance Field View Synthesiscited by 4
  3. 2024Ray-Distance Volume Rendering for Neural Scene Reconstructioncited by 4
  4. 2025Sparse-View 3D Reconstruction: Recent Advances and Open Challengescited by 3
  5. 2024Prism: Semi-Supervised Multi-View Stereo with Monocular Structure Priorscited by 0