# DropoutGS: Dropping Out Gaussians for Better Sparse-view Rendering

arXiv: https://arxiv.org/abs/2504.09491 · HTML: https://mlsanity.com/paper/2504.09491/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- Builds on 45 of its 54 references that are in the map.
- First posted on arXiv 13 Apr 2025.

## Builds on (most cited first, 30 of 45)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Instant Neural Graphics Primitives with a Multiresolution Hash Encoding](https://mlsanity.com/paper/2201.05989/) (2022)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields](https://mlsanity.com/paper/2111.12077/) (2021)
- [Improved Regularization of Convolutional Neural Networks with Cutout](https://mlsanity.com/paper/1708.04552/) (2017)
- [pixelNeRF: Neural Radiance Fields from One or Few Images](https://mlsanity.com/paper/2012.02190/) (2020)
- [Random Erasing Data Augmentation](https://mlsanity.com/paper/1708.04896/) (2017)
- [2D Gaussian Splatting for Geometrically Accurate Radiance Fields](https://mlsanity.com/paper/2403.17888/) (2024)
- [A Point Set Generation Network for 3D Object Reconstruction from a Single Image](https://mlsanity.com/paper/1612.00603/) (2016)
- [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)
- [Fast is better than free: Revisiting adversarial training](https://mlsanity.com/paper/2001.03994/) (2020)
- [Local Light Field Fusion: Practical View Synthesis with Prescriptive Sampling Guidelines](https://mlsanity.com/paper/1905.00889/) (2019)
- [Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fields](https://mlsanity.com/paper/2304.06706/) (2023)
- [Pixel2Mesh: Generating 3D Mesh Models from Single RGB Images](https://mlsanity.com/paper/1804.01654/) (2018)
- [RegNeRF: Regularizing Neural Radiance Fields for View Synthesis from Sparse Inputs](https://mlsanity.com/paper/2112.00724/) (2021)
- [3D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstruction](https://mlsanity.com/paper/1604.00449/) (2016)
- [FastNeRF: High-Fidelity Neural Rendering at 200FPS](https://mlsanity.com/paper/2103.10380/) (2021)
- [Overfitting in adversarially robust deep learning](https://mlsanity.com/paper/2002.11569/) (2020)
- [Putting NeRF on a Diet: Semantically Consistent Few-Shot View Synthesis](https://mlsanity.com/paper/2104.00677/) (2021)
- [FreeNeRF: Improving Few-shot Neural Rendering with Free Frequency Regularization](https://mlsanity.com/paper/2303.07418/) (2023)
- [Dense Depth Priors for Neural Radiance Fields from Sparse Input Views](https://mlsanity.com/paper/2112.03288/) (2021)
- [FSGS: Real-Time Few-shot View Synthesis using Gaussian Splatting](https://mlsanity.com/paper/2312.00451/) (2023)
- [DNGaussian: Optimizing Sparse-View 3D Gaussian Radiance Fields with Global-Local Depth Normalization](https://mlsanity.com/paper/2403.06912/) (2024)
- [SparseNeRF: Distilling Depth Ranking for Few-shot Novel View Synthesis](https://mlsanity.com/paper/2303.16196/) (2023)

## Built on by (most cited first, 29 of 29)

- [GSFixer: Improving 3D Gaussian Splatting with Reference-Guided Video Diffusion Priors](https://mlsanity.com/paper/2508.09667/) (2025)
- [Quantifying and Alleviating Co-Adaptation in Sparse-View 3D Gaussian Splatting](https://mlsanity.com/paper/2508.12720/) (2025)
- [RAGAR: Retrieval Augmented Personalized Image Generation Guided by Recommendation](https://mlsanity.com/paper/2505.01657/) (2025)
- [VGD: Visual Geometry Gaussian Splatting for Feed-Forward Surround-view Driving Reconstruction](https://mlsanity.com/paper/2510.19578/) (2025)
- [Lay2Story: Extending Diffusion Transformers for Layout-Togglable Story Generation](https://mlsanity.com/paper/2508.08949/) (2025)
- [MoFu: Scale-Aware Modulation and Fourier Fusion for Multi-Subject Video Generation](https://mlsanity.com/paper/2512.22310/) (2025)
- [InnoAds-Composer: Efficient Condition Composition for E-Commerce Poster Generation](https://mlsanity.com/paper/2603.05898/) (2026)
- [Dropping Anchor and Spherical Harmonics for Sparse-view Gaussian Splatting](https://mlsanity.com/paper/2602.20933/) (2026)
- [ArtifactWorld: Scaling 3D Gaussian Splatting Artifact Restoration via Video Generation Models](https://mlsanity.com/paper/2604.12251/) (2026)
- [FixingGS: Enhancing 3D Gaussian Splatting via Training-Free Score Distillation](https://mlsanity.com/paper/2509.18759/) (2025)
- [Intrinsic Geometry-Appearance Consistency Optimization for Sparse-View Gaussian Splatting](https://mlsanity.com/paper/2603.02893/) (2026)
- [LoD-Structured 3D Gaussian Splatting for Streaming Video Reconstruction](https://mlsanity.com/paper/2601.18475/) (2026)
- [DOC-GS: Dual-Domain Observation and Calibration for Reliable Sparse-View Gaussian Splatting](https://mlsanity.com/paper/2604.06739/) (2026)
- [Initialize to Generalize: A Stronger Initialization Pipeline for Sparse-View 3DGS](https://mlsanity.com/paper/2510.17479/) (2025)
- [Do Flat Minima Improve Sparse Novel View Synthesis?](https://mlsanity.com/paper/2511.17918/) (2025)
- [Pseudo-View Enhancement via Confidence Fusion for Unposed Sparse-View Reconstruction](https://mlsanity.com/paper/2602.21535/) (2026)
- [GeoQuery: Geometry-Query Diffusion for Sparse-View Reconstruction](https://mlsanity.com/paper/2605.12399/) (2026)
- [Pi-GS: Sparse-View Gaussian Splatting with Dense π3 Initialization](https://mlsanity.com/paper/2602.03327/) (2026)
- [COSMOS: Coherent Supergaussian Modeling with Spatial Priors for Sparse-View 3D Splatting](https://mlsanity.com/paper/2602.06044/) (2025)
- [Multimodal-Prior-Guided Importance Sampling for Hierarchical Gaussian Splatting in Sparse-View Novel View Synthesis](https://mlsanity.com/paper/2603.02866/) (2026)
- [UniSem: Generalizable Semantic 3D Reconstruction from Sparse Unposed Images](https://mlsanity.com/paper/2603.17519/) (2026)
- [Incoherent Deformation, Not Capacity: Diagnosing and Mitigating Overfitting in Dynamic Gaussian Splatting](https://mlsanity.com/paper/2604.16747/) (2026)
- [GeoRect4D: Geometry-Compatible Generative Rectification for Dynamic Sparse-View 3D Reconstruction](https://mlsanity.com/paper/2604.20784/) (2026)
- [PairDropGS: Paired Dropout-Induced Consistency Regularization for Sparse-View Gaussian Splatting](https://mlsanity.com/paper/2605.12072/) (2026)
- [From Uncertainty to Stability and Fidelity: Guiding Sparse-View 3D Gaussian Splatting with Fisher Information](https://mlsanity.com/paper/2606.20842/) (2026)
- [Projection-Volume Fidelity Divergence: Diagnosing and Controlling Optimization Drift in Sparse-View 3D Gaussian Tomography](https://mlsanity.com/paper/2606.22525/) (2026)
- [Improving Sparse-View 3DGS Generalization via Flat Minima Optimization](https://mlsanity.com/paper/2607.00885/) (2026)
- [CLEAR: Conflict-aware Learning via Evidence-guided Adaptive Routing for Unified Sparse-View 3D Gaussian Super-Resolution](https://mlsanity.com/paper/2608.02206/) (2026)
- [TV-SGS: Gaussian Splatting with Geometric Information Propagation via Tensor Voting under sparse views](https://mlsanity.com/paper/2609.07734/) (2026)

## Abstract (arXiv)

Although 3D Gaussian Splatting (3DGS) has demonstrated promising results in novel view synthesis, its performance degrades dramatically with sparse inputs and generates undesirable artifacts. As the number of training views decreases, the novel view synthesis task degrades to a highly under-determined problem such that existing methods suffer from the notorious overfitting issue. Interestingly, we observe that models with fewer Gaussian primitives exhibit less overfitting under sparse inputs. Inspired by this observation, we propose a Random Dropout Regularization (RDR) to exploit the advantages of low-complexity models to alleviate overfitting. In addition, to remedy the lack of high-frequency details for these models, an Edge-guided Splitting Strategy (ESS) is developed. With these two techniques, our method (termed DropoutGS) provides a simple yet effective plug-in approach to improve the generalization performance of existing 3DGS methods. Extensive experiments show that our DropoutGS produces state-of-the-art performance under sparse views on benchmark datasets including Blender, LLFF, and DTU. The project page is at: https://xuyx55.github.io/DropoutGS/.