mlsanityData to 7 Oct 2026

DWTNeRF: Boosting Few-shot Neural Radiance Fields via Discrete Wavelet Transform

arXiv 2501.12637 ↗First posted 22 Jan 2025cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

Neural Radiance Fields (NeRF) has achieved superior performance in novel view synthesis and 3D scene representation, but its practical applications are hindered by slow convergence and reliance on dense training views. To this end, we present DWTNeRF, a unified framework based on Instant-NGP's fast-training hash encoding. It is coupled with regularization terms designed for few-shot NeRF, which operates on sparse training views. Our DWTNeRF additionally includes a novel Discrete Wavelet loss that allows explicit prioritization of low frequencies directly in the training objective, reducing few-shot NeRF's overfitting on high frequencies in earlier training stages. We also introduce a model-based approach, based on multi-head attention, that is compatible with INGP, which are sensitive to architectural changes. On the 3-shot LLFF benchmark, DWTNeRF outperforms Vanilla INGP by 15.07% in PSNR, 24.45% in SSIM and 36.30% in LPIPS. Our approach encourages a re-thinking of current few-shot approaches for fast-converging implicit representations like INGP or 3DGS.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 33 of its 44 references that are in the map. First posted on arXiv 22 Jan 2025.

Builds on

33 of 44 references.

References · 33

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  4. 2016Densely Connected Convolutional Networkscited by 6,691
  5. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
  6. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  7. 2021Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fieldscited by 2,013
  8. 2021Plenoxels: Radiance Fields without Neural Networkscited by 1,607
  9. 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,574
  10. 2020D-NeRF: Neural Radiance Fields for Dynamic Scenescited by 1,459
  11. 2018On the Spectral Bias of Neural Networkscited by 1,321
  12. 2021PlenOctrees for Real-time Rendering of Neural Radiance Fieldscited by 904
21 more
  1. 2019Local Light Field Fusion: Practical View Synthesis with Prescriptive Sampling Guidelinescited by 672
  2. 2021RegNeRF: Regularizing Neural Radiance Fields for View Synthesis from Sparse Inputscited by 614
  3. 2022HumanNeRF: Free-viewpoint Rendering of Moving People from Monocular Videocited by 483
  4. 2021Putting NeRF on a Diet: Semantically Consistent Few-Shot View Synthesiscited by 464
  5. 2023FreeNeRF: Improving Few-shot Neural Rendering with Free Frequency Regularizationcited by 310
  6. 2023SparseNeRF: Distilling Depth Ranking for Few-shot Novel View Synthesiscited by 247
  7. 2022SPARF: Neural Radiance Fields from Sparse and Noisy Posescited by 195
  8. 2021InfoNeRF: Ray Entropy Minimization for Few-Shot Neural Volume Renderingcited by 180
  9. 2023NeuRAD: Neural Rendering for Autonomous Drivingcited by 146
  10. 2023DiffusioNeRF: Regularizing Neural Radiance Fields with Denoising Diffusion Modelscited by 127
  11. 2023VR-NeRF: High-Fidelity Virtualized Walkable Spacescited by 86
  12. 2022MedNeRF: Medical Neural Radiance Fields for Reconstructing 3D-aware CT-Projections from a Single X-raycited by 66
  13. 2023NeRF in the Palm of Your Hand: Corrective Augmentation for Robotics via Novel-View Synthesiscited by 56
  14. 2023GeCoNeRF: Few-shot Neural Radiance Fields via Geometric Consistencycited by 54
  15. 2023FeatureNeRF: Learning Generalizable NeRFs by Distilling Foundation Modelscited by 47
  16. 2023FlipNeRF: Flipped Reflection Rays for Few-shot Novel View Synthesiscited by 29
  17. 2023CuNeRF: Cube-Based Neural Radiance Field for Zero-Shot Medical Image Arbitrary-Scale Super Resolutioncited by 28
  18. 2024Are NeRFs ready for autonomous driving? Towards closing the real-to-simulation gapcited by 20
  19. 2024Is Vanilla MLP in Neural Radiance Field Enough for Few-shot View Synthesis?cited by 15
  20. 2024SplatSDF: Boosting SDF-NeRF via Architecture-Level Fusion with Gaussian Splatscited by 5
  21. 2024CombiNeRF: A Combination of Regularization Techniques for Few-Shot Neural Radiance Field View Synthesiscited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 3; 2026: 3.

6 papers.

  1. 2025DynaGSLAM: Real-Time Gaussian-Splatting SLAM for Online Rendering, Tracking, Motion Predictions of Moving Objects in Dynamic Scenescited by 10
  2. 2025From Coarse to Fine: Learnable Discrete Wavelet Transforms for Efficient 3D Gaussian Splattingcited by 6
  3. 2025DWTGS: Rethinking Frequency Regularization for Sparse-view 3D Gaussian Splattingcited by 5
  4. 2026Learnable Multi-level Discrete Wavelet Transforms for 3D Gaussian Splatting Frequency Modulationcited by 1
  5. 2026LGDWT-GS: Local and Global Discrete Wavelet-Regularized 3D Gaussian Splatting for Sparse-View Scene Reconstructioncited by 0
  6. 2026Speech2Grasp: Data-Efficient Transfer of Text-Conditioned Grasp Detection to Speech in Humanoid Robotscited by 0