mlsanityData to 7 Oct 2026

MonoPatchNeRF: Improving Neural Radiance Fields with Patch-based Monocular Guidance

arXiv 2404.08252 ↗First posted 12 Apr 2024cs.CVcited by 2

Not on the map. Why?

Abstract (arXiv)

The latest regularized Neural Radiance Field (NeRF) approaches produce poor geometry and view extrapolation for large scale sparse view scenes, such as ETH3D. Density-based approaches tend to be under-constrained, while surface-based approaches tend to miss details. In this paper, we take a density-based approach, sampling patches instead of individual rays to better incorporate monocular depth and normal estimates and patch-based photometric consistency constraints between training views and sampled virtual views. Loosely constraining densities based on estimated depth aligned to sparse points further improves geometric accuracy. While maintaining similar view synthesis quality, our approach significantly improves geometric accuracy on the ETH3D benchmark, e.g. increasing the F1@2cm score by 4x-8x compared to other regularized density-based approaches, with much lower training and inference time than other approaches.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 44 of its 58 references that are in the map. First posted on arXiv 12 Apr 2024.

Builds on

44 of 58 references.

References · 44

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  3. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
  4. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,698
  5. 2021Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fieldscited by 2,013
  6. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,701
  7. 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,574
  8. 2023DUSt3R: Geometric 3D Vision Made Easycited by 1,526
  9. 2022TensoRF: Tensorial Radiance Fieldscited by 1,275
  10. 2021Volume Rendering of Neural Implicit Surfacescited by 990
  11. 2018MVSNet: Depth Inference for Unstructured Multi-view Stereocited by 780
  12. 2019Local Light Field Fusion: Practical View Synthesis with Prescriptive Sampling Guidelinescited by 672
32 more
  1. 2021RegNeRF: Regularizing Neural Radiance Fields for View Synthesis from Sparse Inputscited by 614
  2. 2021Ref-NeRF: Structured View-Dependent Appearance for Neural Radiance Fieldscited by 569
  3. 2022MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstructioncited by 467
  4. 2021Putting NeRF on a Diet: Semantically Consistent Few-Shot View Synthesiscited by 464
  5. 2023Neuralangelo: High-Fidelity Neural Surface Reconstructioncited by 464
  6. 2024Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimationcited by 389
  7. 2021Omnidata: A Scalable Pipeline for Making Multi-Task Mid-Level Vision Datasets from 3D Scanscited by 336
  8. 2023FreeNeRF: Improving Few-shot Neural Rendering with Free Frequency Regularizationcited by 310
  9. 2022MobileNeRF: Exploiting the Polygon Rasterization Pipeline for Efficient Neural Field Rendering on Mobile Architecturescited by 308
  10. 2021Dense Depth Priors for Neural Radiance Fields from Sparse Input Viewscited by 301
  11. 2019Recurrent MVSNet for High-resolution Multi-view Stereo Depth Inferencecited by 252
  12. 2023SparseNeRF: Distilling Depth Ranking for Few-shot Novel View Synthesiscited by 247
  13. 2016DeMoN: Depth and Motion Network for Learning Monocular Stereocited by 200
  14. 2022SPARF: Neural Radiance Fields from Sparse and Noisy Posescited by 195
  15. 2020Non-Local Spatial Propagation Network for Depth Completioncited by 194
  16. 2021NerfingMVS: Guided Optimization of Neural Radiance Fields for Indoor Multi-view Stereocited by 191
  17. 2018DeepV2D: Video to Depth with Differentiable Structure from Motioncited by 185
  18. 2020LiDARsim: Realistic LiDAR Simulation by Leveraging the Real Worldcited by 137
  19. 2021Improving neural implicit surfaces geometry with patch warpingcited by 136
  20. 2018Learning Depth with Convolutional Spatial Propagation Networkcited by 135
  21. 2023DiffusioNeRF: Regularizing Neural Radiance Fields with Denoising Diffusion Modelscited by 127
  22. 2022Neural 3D Scene Reconstruction with the Manhattan-world Assumptioncited by 123
  23. 2022NeRFusion: Fusing Radiance Fields for Large-Scale Scene Reconstructioncited by 99
  24. 2022NerfAcc: A General NeRF Acceleration Toolboxcited by 73
  25. 2021DIVeR: Real-time and Accurate Neural Radiance Fields with Deterministic Integration for Volume Renderingcited by 60
  26. 2022Masked Wavelet Representation for Compact Neural Radiance Fieldscited by 57
  27. 2021MVS2D: Efficient Multi-view Stereo via Attention-Driven 2D Convolutionscited by 43
  28. 2022A Benchmark and a Baseline for Robust Multi-view Depth Estimationcited by 38
  29. 2019DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstructioncited by 23
  30. 2021PatchMatch-RL: Deep MVS with Pixelwise Depth, Normal, and Visibilitycited by 17
  31. 2023DeLiRa: Self-Supervised Depth, Light, and Radiance Fieldscited by 5
  32. 2022QFF: Quantized Fourier Features for Neural Field Representationscited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 1.

2 papers.

  1. 2025Clustered Error Correction with Grouped 4D Gaussian Splattingcited by 4
  2. 20264Director: Controlling Video World Models with Rigid 3D Geometrycited by 0