# UGOD: Uncertainty-Guided Differentiable Opacity and Soft Dropout for Enhanced Sparse-View 3DGS

arXiv: https://arxiv.org/abs/2508.04968 · HTML: https://mlsanity.com/paper/2508.04968/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 24 references that are in the map.
- First posted on arXiv 7 Aug 2025.

## Builds on (most cited first, 15 of 15)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [Instant Neural Graphics Primitives with a Multiresolution Hash Encoding](https://mlsanity.com/paper/2201.05989/) (2022)
- [DUSt3R: Geometric 3D Vision Made Easy](https://mlsanity.com/paper/2312.14132/) (2023)
- [On the Spectral Bias of Neural Networks](https://mlsanity.com/paper/1806.08734/) (2018)
- [Concrete Dropout](https://mlsanity.com/paper/1705.07832/) (2017)
- [MASt3R-SfM: a Fully-Integrated Solution for Unconstrained Structure-from-Motion](https://mlsanity.com/paper/2409.19152/) (2024)
- [Revising Densification in Gaussian Splatting](https://mlsanity.com/paper/2404.06109/) (2024)
- [CoR-GS: Sparse-View 3D Gaussian Splatting via Co-Regularization](https://mlsanity.com/paper/2405.12110/) (2024)
- [DropGaussian: Structural Regularization for Sparse-view Gaussian Splatting](https://mlsanity.com/paper/2504.00773/) (2025)
- [Event3DGS: Event-Based 3D Gaussian Splatting for High-Speed Robot Egomotion](https://mlsanity.com/paper/2406.02972/) (2024)
- [Does 3D Gaussian Splatting Need Accurate Volumetric Rendering?](https://mlsanity.com/paper/2502.19318/) (2025)
- [Volumetrically Consistent 3D Gaussian Rasterization](https://mlsanity.com/paper/2412.03378/) (2024)
- [OMG: Opacity Matters in Material Modeling with Gaussian Splatting](https://mlsanity.com/paper/2502.10988/) (2025)
- [Depth Priors in Removal Neural Radiance Fields](https://mlsanity.com/paper/2405.00630/) (2024)

## Built on by (most cited first, 3 of 3)

- [Dense-Jump Flow Matching with Non-Uniform Time Scheduling for Robotic Policies: Mitigating Multi-Step Inference Degradation](https://mlsanity.com/paper/2509.13574/) (2025)
- [PairDropGS: Paired Dropout-Induced Consistency Regularization for Sparse-View Gaussian Splatting](https://mlsanity.com/paper/2605.12072/) (2026)
- [Improving Sparse-View 3DGS Generalization via Flat Minima Optimization](https://mlsanity.com/paper/2607.00885/) (2026)

## Abstract (arXiv)

3D Gaussian Splatting (3DGS) has become a competitive approach for novel view synthesis (NVS) due to its advanced rendering efficiency through 3D Gaussian projection and blending. However, Gaussians are treated equally weighted for rendering in most 3DGS methods, making them prone to overfitting, which is particularly the case in sparse-view scenarios. To address this, we investigate how adaptive weighting of Gaussians affects rendering quality, which is characterised by learned uncertainties proposed. This learned uncertainty serves two key purposes: first, it guides the differentiable update of Gaussian opacity while preserving the 3DGS pipeline integrity; second, the uncertainty undergoes soft differentiable dropout regularisation, which strategically transforms the original uncertainty into continuous drop probabilities that govern the final Gaussian projection and blending process for rendering. Extensive experimental results over widely adopted datasets demonstrate that our method outperforms rivals in sparse-view 3D synthesis, achieving higher quality reconstruction with fewer Gaussians in most datasets compared to existing sparse-view approaches, e.g., compared to DropGaussian, our method achieves 3.27% PSNR improvements on the MipNeRF 360 dataset.