mlsanityData to 7 Oct 2026

Few-shot NeRF by Adaptive Rendering Loss Regularization

arXiv 2410.17839 ↗First posted 23 Oct 2024cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

Novel view synthesis with sparse inputs poses great challenges to Neural Radiance Field (NeRF). Recent works demonstrate that the frequency regularization of Positional Encoding (PE) can achieve promising results for few-shot NeRF. In this work, we reveal that there exists an inconsistency between the frequency regularization of PE and rendering loss. This prevents few-shot NeRF from synthesizing higher-quality novel views. To mitigate this inconsistency, we propose Adaptive Rendering loss regularization for few-shot NeRF, dubbed AR-NeRF. Specifically, we present a two-phase rendering supervision and an adaptive rendering loss weight learning strategy to align the frequency relationship between PE and 2D-pixel supervision. In this way, AR-NeRF can learn global structures better in the early training phase and adaptively learn local details throughout the training process. Extensive experiments show that our AR-NeRF achieves state-of-the-art performance on different datasets, including object-level and complex scenes.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 44 of its 54 references that are in the map. First posted on arXiv 23 Oct 2024.

Builds on

44 of 54 references.

References · 44

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  3. 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 3,006
  4. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,335
  5. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,170
  6. 2021Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fieldscited by 2,013
  7. 2021Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fieldscited by 1,957
  8. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,701
  9. 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,574
  10. 2022Magic3D: High-Resolution Text-to-3D Content Creationcited by 1,285
  11. 2020NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collectionscited by 1,230
  12. 2021Volume Rendering of Neural Implicit Surfacescited by 990
32 more
  1. 2021MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereocited by 735
  2. 2021Depth-supervised NeRF: Fewer Views and Faster Training for Freecited by 732
  3. 2020pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesiscited by 708
  4. 2019Local Light Field Fusion: Practical View Synthesis with Prescriptive Sampling Guidelinescited by 672
  5. 2021RegNeRF: Regularizing Neural Radiance Fields for View Synthesis from Sparse Inputscited by 614
  6. 2022Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generationcited by 597
  7. 2021Ref-NeRF: Structured View-Dependent Appearance for Neural Radiance Fieldscited by 569
  8. 2021Putting NeRF on a Diet: Semantically Consistent Few-Shot View Synthesiscited by 464
  9. 2023FreeNeRF: Improving Few-shot Neural Rendering with Free Frequency Regularizationcited by 310
  10. 2021Dense Depth Priors for Neural Radiance Fields from Sparse Input Viewscited by 301
  11. 2023SparseNeRF: Distilling Depth Ranking for Few-shot Novel View Synthesiscited by 247
  12. 2022Geo-Neus: Geometry-Consistent Neural Implicit Surfaces Learning for Multi-view Reconstructioncited by 211
  13. 2021GeoNeRF: Generalizing NeRF with Geometry Priorscited by 195
  14. 2022SPARF: Neural Radiance Fields from Sparse and Noisy Posescited by 195
  15. 2021Stereo Radiance Fields (SRF): Learning View Synthesis for Sparse Views of Novel Scenescited by 190
  16. 2021InfoNeRF: Ray Entropy Minimization for Few-Shot Neural Volume Renderingcited by 180
  17. 2023DiffusioNeRF: Regularizing Neural Radiance Fields with Denoising Diffusion Modelscited by 127
  18. 2022ActiveNeRF: Learning where to See with Uncertainty Estimationcited by 124
  19. 2019Multi-Scale Geometric Consistency Guided Multi-View Stereocited by 105
  20. 2021Stochastic Neural Radiance Fields: Quantifying Uncertainty in Implicit 3D Representationscited by 80
  21. 2022Conditional-Flow NeRF: Accurate 3D Modelling with Reliable Uncertainty Quantificationcited by 71
  22. 2023GeCoNeRF: Few-shot Neural Radiance Fields via Geometric Consistencycited by 54
  23. 2023MixNeRF: Modeling a Ray with Mixture Density for Novel View Synthesis from Sparse Inputscited by 40
  24. 2023SCADE: NeRFs from Space Carving with Ambiguity-Aware Depth Estimatescited by 35
  25. 2023FlipNeRF: Flipped Reflection Rays for Few-shot Novel View Synthesiscited by 29
  26. 2024Diffusion Time-step Curriculum for One Image to 3D Generationcited by 20
  27. 2023Hierarchical Prior Mining for Non-local Multi-View Stereocited by 7
  28. 2023Self-NeRF: A Self-Training Pipeline for Few-Shot Neural Radiance Fieldscited by 5
  29. 2024PSDF: Prior-Driven Neural Implicit Surface Learning for Multi-view Reconstructioncited by 4
  30. 2023PR-NeuS: A Prior-based Residual Learning Paradigm for Fast Multi-view Neural Surface Reconstructioncited by 2
  31. 2024PGAHum: Prior-Guided Geometry and Appearance Learning for High-Fidelity Animatable Human Reconstructioncited by 2
  32. 2024GeoGen: Geometry-Aware Generative Modeling via Signed Distance Functionscited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 4; 2026: 1.

6 papers.

  1. 2025Vid2Sim: Realistic and Interactive Simulation from Video for Urban Navigationcited by 30
  2. 2025CoMapGS: Covisibility Map-based Gaussian Splatting for Sparse Novel View Synthesiscited by 10
  3. 2025NeuSpring: Neural Spring Fields for Reconstruction and Simulation of Deformable Objects from Videoscited by 4
  4. 2024Pushing Rendering Boundaries: Hard Gaussian Splattingcited by 3
  5. 2026360CityArena: A Realistic Virtual Urban Navigation Benchmark for Embodied Agentscited by 1
  6. 2025DivCon-NeRF: Diverse and Consistent Ray Augmentation for Few-Shot NeRFcited by 0