# ViP-NeRF: Visibility Prior for Sparse Input Neural Radiance Fields

arXiv: https://arxiv.org/abs/2305.00041 · HTML: https://mlsanity.com/paper/2305.00041/

## Key facts

- Cited by 43 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 52 references that are in the map.
- First posted on arXiv 28 Apr 2023.

## Builds on (most cited first, 30 of 34)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields](https://mlsanity.com/paper/2111.12077/) (2021)
- [Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields](https://mlsanity.com/paper/2103.13415/) (2021)
- [pixelNeRF: Neural Radiance Fields from One or Few Images](https://mlsanity.com/paper/2012.02190/) (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)
- [Local Light Field Fusion: Practical View Synthesis with Prescriptive Sampling Guidelines](https://mlsanity.com/paper/1905.00889/) (2019)
- [RegNeRF: Regularizing Neural Radiance Fields for View Synthesis from Sparse Inputs](https://mlsanity.com/paper/2112.00724/) (2021)
- [Putting NeRF on a Diet: Semantically Consistent Few-Shot View Synthesis](https://mlsanity.com/paper/2104.00677/) (2021)
- [SynSin: End-to-end View Synthesis from a Single Image](https://mlsanity.com/paper/1912.08804/) (2019)
- [Dense Depth Priors for Neural Radiance Fields from Sparse Input Views](https://mlsanity.com/paper/2112.03288/) (2021)
- [DeepMVS: Learning Multi-view Stereopsis](https://mlsanity.com/paper/1804.00650/) (2018)
- [Single-View View Synthesis with Multiplane Images](https://mlsanity.com/paper/2004.11364/) (2020)
- [Learned Initializations for Optimizing Coordinate-Based Neural Representations](https://mlsanity.com/paper/2012.02189/) (2020)
- [SparseFusion: Distilling View-conditioned Diffusion for 3D Reconstruction](https://mlsanity.com/paper/2212.00792/) (2022)
- [Stereo Magnification: Learning View Synthesis using Multiplane Images](https://mlsanity.com/paper/1805.09817/) (2018)
- [Neural Rays for Occlusion-aware Image-based Rendering](https://mlsanity.com/paper/2107.13421/) (2021)
- [Pushing the Boundaries of View Extrapolation with Multiplane Images](https://mlsanity.com/paper/1905.00413/) (2019)
- [InfoNeRF: Ray Entropy Minimization for Few-Shot Neural Volume Rendering](https://mlsanity.com/paper/2112.15399/) (2021)
- [SinNeRF: Training Neural Radiance Fields on Complex Scenes from a Single Image](https://mlsanity.com/paper/2204.00928/) (2022)
- [NeRS: Neural Reflectance Surfaces for Sparse-view 3D Reconstruction in the Wild](https://mlsanity.com/paper/2110.07604/) (2021)
- [MINE: Towards Continuous Depth MPI with NeRF for Novel View Synthesis](https://mlsanity.com/paper/2103.14910/) (2021)
- [DiffusioNeRF: Regularizing Neural Radiance Fields with Denoising Diffusion Models](https://mlsanity.com/paper/2302.12231/) (2023)
- [DPSNet: End-to-end Deep Plane Sweep Stereo](https://mlsanity.com/paper/1905.00538/) (2019)
- [Vision Transformer for NeRF-Based View Synthesis from a Single Input Image](https://mlsanity.com/paper/2207.05736/) (2022)
- [Pix2NeRF: Unsupervised Conditional π-GAN for Single Image to Neural Radiance Fields Translation](https://mlsanity.com/paper/2202.13162/) (2022)
- [Behind the Scenes: Density Fields for Single View Reconstruction](https://mlsanity.com/paper/2301.07668/) (2023)

## Built on by (most cited first, 30 of 43)

- [ReconFusion: 3D Reconstruction with Diffusion Priors](https://mlsanity.com/paper/2312.02981/) (2023)
- [GaussianObject: High-Quality 3D Object Reconstruction from Four Views with Gaussian Splatting](https://mlsanity.com/paper/2402.10259/) (2024)
- [SimpleNeRF: Regularizing Sparse Input Neural Radiance Fields with Simpler Solutions](https://mlsanity.com/paper/2309.03955/) (2023)
- [Binocular-Guided 3D Gaussian Splatting with View Consistency for Sparse View Synthesis](https://mlsanity.com/paper/2410.18822/) (2024)
- [Deceptive-NeRF/3DGS: Diffusion-Generated Pseudo-Observations for High-Quality Sparse-View Reconstruction](https://mlsanity.com/paper/2305.15171/) (2023)
- [SGD: Street View Synthesis with Gaussian Splatting and Diffusion Prior](https://mlsanity.com/paper/2403.20079/) (2024)
- [Decompositional Neural Scene Reconstruction with Generative Diffusion Prior](https://mlsanity.com/paper/2503.14830/) (2025)
- [MVPGS: Excavating Multi-view Priors for Gaussian Splatting from Sparse Input Views](https://mlsanity.com/paper/2409.14316/) (2024)
- [4D Gaussian Splatting in the Wild with Uncertainty-Aware Regularization](https://mlsanity.com/paper/2411.08879/) (2024)
- [ZeroRF: Fast Sparse View 360deg Reconstruction with Zero Pretraining](https://mlsanity.com/paper/2312.09249/) (2023)
- [UW-GS: Distractor-Aware 3D Gaussian Splatting for Enhanced Underwater Scene Reconstruction](https://mlsanity.com/paper/2410.01517/) (2024)
- [LoopSparseGS: Loop Based Sparse-View Friendly Gaussian Splatting](https://mlsanity.com/paper/2408.00254/) (2024)
- [FrugalNeRF: Fast Convergence for Extreme Few-shot Novel View Synthesis without Learned Priors](https://mlsanity.com/paper/2410.16271/) (2024)
- [FewViewGS: Gaussian Splatting with Few View Matching and Multi-stage Training](https://mlsanity.com/paper/2411.02229/) (2024)
- [HoloScene: Simulation-Ready Interactive 3D Worlds from a Single Video](https://mlsanity.com/paper/2510.05560/) (2025)
- [Neural Radiance Field-based Visual Rendering: A Comprehensive Review](https://mlsanity.com/paper/2404.00714/) (2024)
- [BoostMVSNeRFs: Boosting MVS-based NeRFs to Generalizable View Synthesis in Large-scale Scenes](https://mlsanity.com/paper/2407.15848/) (2024)
- [Factorized Motion Fields for Fast Sparse Input Dynamic View Synthesis](https://mlsanity.com/paper/2404.11669/) (2024)
- [DisC-GS: Discontinuity-aware Gaussian Splatting](https://mlsanity.com/paper/2405.15196/) (2024)
- [SolidGS: Consolidating Gaussian Surfel Splatting for Sparse-View Surface Reconstruction](https://mlsanity.com/paper/2412.15400/) (2024)
- [AD-GS: Alternating Densification for Sparse-Input 3D Gaussian Splatting](https://mlsanity.com/paper/2509.11003/) (2025)
- [NeRF-US: Removing Ultrasound Imaging Artifacts from Neural Radiance Fields in the Wild](https://mlsanity.com/paper/2408.10258/) (2024)
- [Martian World Model: Controllable Video Synthesis with Physically Accurate 3D Reconstructions](https://mlsanity.com/paper/2507.07978/) (2025)
- [TiAVox: Time-aware Attenuation Voxels for Sparse-view 4D DSA Reconstruction](https://mlsanity.com/paper/2309.02318/) (2023)
- [The More You See in 2D, the More You Perceive in 3D](https://mlsanity.com/paper/2404.03652/) (2024)
- [Uncertainty-driven 3D Gaussian Splatting Active Mapping via Anisotropic Visibility Field](https://mlsanity.com/paper/2605.30342/) (2026)
- [Ray-Distance Volume Rendering for Neural Scene Reconstruction](https://mlsanity.com/paper/2408.15524/) (2024)
- [Sparse-View 3D Reconstruction: Recent Advances and Open Challenges](https://mlsanity.com/paper/2507.16406/) (2025)
- [Novel View Synthesis from A Few Glimpses via Test-Time Natural Video Completion](https://mlsanity.com/paper/2511.17932/) (2025)
- [Robust Low-light Scene Restoration via Illumination Transition](https://mlsanity.com/paper/2507.03976/) (2025)

## Abstract (arXiv)

Neural radiance fields (NeRF) have achieved impressive performances in view synthesis by encoding neural representations of a scene. However, NeRFs require hundreds of images per scene to synthesize photo-realistic novel views. Training them on sparse input views leads to overfitting and incorrect scene depth estimation resulting in artifacts in the rendered novel views. Sparse input NeRFs were recently regularized by providing dense depth estimated from pre-trained networks as supervision, to achieve improved performance over sparse depth constraints. However, we find that such depth priors may be inaccurate due to generalization issues. Instead, we hypothesize that the visibility of pixels in different input views can be more reliably estimated to provide dense supervision. In this regard, we compute a visibility prior through the use of plane sweep volumes, which does not require any pre-training. By regularizing the NeRF training with the visibility prior, we successfully train the NeRF with few input views. We reformulate the NeRF to also directly output the visibility of a 3D point from a given viewpoint to reduce the training time with the visibility constraint. On multiple datasets, our model outperforms the competing sparse input NeRF models including those that use learned priors. The source code for our model can be found on our project page: https://nagabhushansn95.github.io/publications/2023/ViP-NeRF.html.