# WaveNeRF: Wavelet-based Generalizable Neural Radiance Fields

arXiv: https://arxiv.org/abs/2308.04826 · HTML: https://mlsanity.com/paper/2308.04826/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 45 references that are in the map.
- First posted on arXiv 9 Aug 2023.

## Builds on (most cited first, 29 of 29)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Instant Neural Graphics Primitives with a Multiresolution Hash Encoding](https://mlsanity.com/paper/2201.05989/) (2022)
- [pixelNeRF: Neural Radiance Fields from One or Few Images](https://mlsanity.com/paper/2012.02190/) (2020)
- [D-NeRF: Neural Radiance Fields for Dynamic Scenes](https://mlsanity.com/paper/2011.13961/) (2020)
- [TensoRF: Tensorial Radiance Fields](https://mlsanity.com/paper/2203.09517/) (2022)
- [NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collections](https://mlsanity.com/paper/2008.02268/) (2020)
- [Neural Sparse Voxel Fields](https://mlsanity.com/paper/2007.11571/) (2020)
- [MVSNet: Depth Inference for Unstructured Multi-view Stereo](https://mlsanity.com/paper/1804.02505/) (2018)
- [Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenes](https://mlsanity.com/paper/2011.13084/) (2020)
- [MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereo](https://mlsanity.com/paper/2103.15595/) (2021)
- [Depth-supervised NeRF: Fewer Views and Faster Training for Free](https://mlsanity.com/paper/2107.02791/) (2021)
- [pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesis](https://mlsanity.com/paper/2012.00926/) (2020)
- [IBRNet: Learning Multi-View Image-Based Rendering](https://mlsanity.com/paper/2102.13090/) (2021)
- [GRAF: Generative Radiance Fields for 3D-Aware Image Synthesis](https://mlsanity.com/paper/2007.02442/) (2020)
- [Local Light Field Fusion: Practical View Synthesis with Prescriptive Sampling Guidelines](https://mlsanity.com/paper/1905.00889/) (2019)
- [Point-NeRF: Point-based Neural Radiance Fields](https://mlsanity.com/paper/2201.08845/) (2022)
- [iMAP: Implicit Mapping and Positioning in Real-Time](https://mlsanity.com/paper/2103.12352/) (2021)
- [Dynamic Neural Radiance Fields for Monocular 4D Facial Avatar Reconstruction](https://mlsanity.com/paper/2012.03065/) (2020)
- [Dynamic View Synthesis from Dynamic Monocular Video](https://mlsanity.com/paper/2105.06468/) (2021)
- [Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matching](https://mlsanity.com/paper/1912.06378/) (2019)
- [Neural Point-Based Graphics](https://mlsanity.com/paper/1906.08240/) (2019)
- [Recurrent MVSNet for High-resolution Multi-view Stereo Depth Inference](https://mlsanity.com/paper/1902.10556/) (2019)
- [The Creation and Detection of Deepfakes: A Survey](https://mlsanity.com/paper/2004.11138/) (2020)
- [GeoNeRF: Generalizing NeRF with Geometry Priors](https://mlsanity.com/paper/2111.13539/) (2021)
- [Deep Stereo using Adaptive Thin Volume Representation with Uncertainty Awareness](https://mlsanity.com/paper/1911.12012/) (2019)
- [Hallucinated Neural Radiance Fields in the Wild](https://mlsanity.com/paper/2111.15246/) (2021)
- [StyleRF: Zero-shot 3D Style Transfer of Neural Radiance Fields](https://mlsanity.com/paper/2303.10598/) (2023)
- [VMRF: View Matching Neural Radiance Fields](https://mlsanity.com/paper/2207.02621/) (2022)
- [wildNeRF: Complete view synthesis of in-the-wild dynamic scenes captured using sparse monocular data](https://mlsanity.com/paper/2209.10399/) (2022)

## Built on by (most cited first, 24 of 24)

- [FreGS: 3D Gaussian Splatting with Progressive Frequency Regularization](https://mlsanity.com/paper/2403.06908/) (2024)
- [Advances in Feed-Forward 3D Reconstruction and View Synthesis: A Survey](https://mlsanity.com/paper/2507.14501/) (2025)
- [WateRF: Robust Watermarks in Radiance Fields for Protection of Copyrights](https://mlsanity.com/paper/2405.02066/) (2024)
- [3D-GSW: 3D Gaussian Splatting for Robust Watermarking](https://mlsanity.com/paper/2409.13222/) (2024)
- [DaReNeRF: Direction-aware Representation for Dynamic Scenes](https://mlsanity.com/paper/2403.02265/) (2024)
- [Neural Radiance Field-based Visual Rendering: A Comprehensive Review](https://mlsanity.com/paper/2404.00714/) (2024)
- [Pose-Free Neural Radiance Fields via Implicit Pose Regularization](https://mlsanity.com/paper/2308.15049/) (2023)
- [InsertNeRF: Instilling Generalizability into NeRF with HyperNet Modules](https://mlsanity.com/paper/2308.13897/) (2023)
- [SparSplat: Fast Multi-View Reconstruction with Generalizable 2D Gaussian Splatting](https://mlsanity.com/paper/2505.02175/) (2025)
- [From Coarse to Fine: Learnable Discrete Wavelet Transforms for Efficient 3D Gaussian Splatting](https://mlsanity.com/paper/2506.23042/) (2025)
- [DWTGS: Rethinking Frequency Regularization for Sparse-view 3D Gaussian Splatting](https://mlsanity.com/paper/2507.15690/) (2025)
- [Generalizable Neural Human Renderer](https://mlsanity.com/paper/2404.14199/) (2024)
- [Puzzle Similarity: A Perceptually-guided Cross-Reference Metric for Artifact Detection in 3D Scene Reconstructions](https://mlsanity.com/paper/2411.17489/) (2024)
- [Generalizable Radio-Frequency Radiance Fields for Spatial Spectrum Synthesis](https://mlsanity.com/paper/2502.05708/) (2025)
- [Frequency-Aware Gaussian Splatting Decomposition](https://mlsanity.com/paper/2503.21226/) (2025)
- [SplatWeaver: Learning to Allocate Gaussian Primitives for Generalizable Novel View Synthesis](https://mlsanity.com/paper/2605.07287/) (2026)
- [Learnable Multi-level Discrete Wavelet Transforms for 3D Gaussian Splatting Frequency Modulation](https://mlsanity.com/paper/2602.14199/) (2026)
- [UnWave-Net: Unrolled Wavelet Network for Compton Tomography Image Reconstruction](https://mlsanity.com/paper/2406.03413/) (2024)
- [DaRePlane: Direction-aware Representations for Dynamic Scene Reconstruction](https://mlsanity.com/paper/2410.14169/) (2024)
- [Breaking the Context Bottleneck on Long Time Series Forecasting](https://mlsanity.com/paper/2412.16572/) (2024)
- [LGDWT-GS: Local and Global Discrete Wavelet-Regularized 3D Gaussian Splatting for Sparse-View Scene Reconstruction](https://mlsanity.com/paper/2601.17185/) (2026)
- [DefenseSplat: Enhancing the Robustness of 3D Gaussian Splatting via Frequency-Aware Filtering](https://mlsanity.com/paper/2602.19323/) (2026)
- [Fast and Generalizable NeRF Architecture Selection for Satellite Scene Reconstruction](https://mlsanity.com/paper/2603.18306/) (2026)
- [AdaptiveSplat:Texture Aware Controllable 3D Gaussian Allocation for Feed-Forward Reconstruction](https://mlsanity.com/paper/2607.04256/) (2026)

## Abstract (arXiv)

Neural Radiance Field (NeRF) has shown impressive performance in novel view synthesis via implicit scene representation. However, it usually suffers from poor scalability as requiring densely sampled images for each new scene. Several studies have attempted to mitigate this problem by integrating Multi-View Stereo (MVS) technique into NeRF while they still entail a cumbersome fine-tuning process for new scenes. Notably, the rendering quality will drop severely without this fine-tuning process and the errors mainly appear around the high-frequency features. In the light of this observation, we design WaveNeRF, which integrates wavelet frequency decomposition into MVS and NeRF to achieve generalizable yet high-quality synthesis without any per-scene optimization. To preserve high-frequency information when generating 3D feature volumes, WaveNeRF builds Multi-View Stereo in the Wavelet domain by integrating the discrete wavelet transform into the classical cascade MVS, which disentangles high-frequency information explicitly. With that, disentangled frequency features can be injected into classic NeRF via a novel hybrid neural renderer to yield faithful high-frequency details, and an intuitive frequency-guided sampling strategy can be designed to suppress artifacts around high-frequency regions. Extensive experiments over three widely studied benchmarks show that WaveNeRF achieves superior generalizable radiance field modeling when only given three images as input.