# Rendering-Aware Bayesian 3D Gaussian Splatting with Native Uncertainty and Adaptive Complexity Control

arXiv: https://arxiv.org/abs/2607.05522 · HTML: https://mlsanity.com/paper/2607.05522/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 42 references that are in the map.
- First posted on arXiv 6 Jul 2026.

## Builds on (most cited first, 24 of 24)

- [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)
- [Shortcut Learning in Deep Neural Networks](https://mlsanity.com/paper/2004.07780/) (2020)
- [Natural Adversarial Examples](https://mlsanity.com/paper/1907.07174/) (2019)
- [BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain](https://mlsanity.com/paper/1708.06733/) (2017)
- [Adversarial Examples Are Not Bugs, They Are Features](https://mlsanity.com/paper/1905.02175/) (2019)
- [Universal adversarial perturbations](https://mlsanity.com/paper/1610.08401/) (2016)
- [Spectral Signatures in Backdoor Attacks](https://mlsanity.com/paper/1811.00636/) (2018)
- [Hidden Trigger Backdoor Attacks](https://mlsanity.com/paper/1910.00033/) (2019)
- [Noise or Signal: The Role of Image Backgrounds in Object Recognition](https://mlsanity.com/paper/2006.09994/) (2020)
- [High Frequency Component Helps Explain the Generalization of Convolutional Neural Networks](https://mlsanity.com/paper/1905.13545/) (2019)
- [A Fourier Perspective on Model Robustness in Computer Vision](https://mlsanity.com/paper/1906.08988/) (2019)
- [Simple Black-box Adversarial Attacks](https://mlsanity.com/paper/1905.07121/) (2019)
- [Generative Adversarial Perturbations](https://mlsanity.com/paper/1712.02328/) (2017)
- [Backdoor Attacks Against Deep Learning Systems in the Physical World](https://mlsanity.com/paper/2006.14580/) (2020)
- [Fast Feature Fool: A data independent approach to universal adversarial perturbations](https://mlsanity.com/paper/1707.05572/) (2017)
- [On Generating Transferable Targeted Perturbations](https://mlsanity.com/paper/2103.14641/) (2021)
- [Art of singular vectors and universal adversarial perturbations](https://mlsanity.com/paper/1709.03582/) (2017)
- [Spurious Features Everywhere -- Large-Scale Detection of Harmful Spurious Features in ImageNet](https://mlsanity.com/paper/2212.04871/) (2022)
- [Practical No-box Adversarial Attacks against DNNs](https://mlsanity.com/paper/2012.02525/) (2020)
- [The Adversarial Attack and Detection under the Fisher Information Metric](https://mlsanity.com/paper/1810.03806/) (2018)
- [Backdoor Vulnerabilities in Normally Trained Deep Learning Models](https://mlsanity.com/paper/2211.15929/) (2022)
- [Practical No-box Adversarial Attacks with Training-free Hybrid Image Transformation](https://mlsanity.com/paper/2203.04607/) (2022)
- [Do ImageNet-trained models learn shortcuts? The impact of frequency shortcuts on generalization](https://mlsanity.com/paper/2503.03519/) (2025)

## Built on by (most cited first, 2 of 2)

- [When Variance Is Not an Error Map: Calibrated Uncertainty for Radiative Gaussian Splatting in Sparse-View CT](https://mlsanity.com/paper/2607.13682/) (2026)
- [View-Structured Conformal Prediction for 3D Gaussian Splatting](https://mlsanity.com/paper/2609.10307/) (2026)

## Abstract (arXiv)

3D Gaussian splatting (3DGS) is a strong representation for real-time novel-view synthesis, but its standard training pipeline relies on point estimates and hand-tuned heuristics, providing no native uncertainty or principled complexity control. This is most limiting under sparse views or fixed acquisition budgets, where a model must identify weakly supported geometry and select informative views. We introduce a rendering-aware Bayesian 3DGS framework that tracks Gaussian geometry with a Normal-Inverse-Wishart posterior over means and covariances using renderer-derived surrogate summaries. An optional Dirichlet-process extension adds a probabilistic component-usage signal, and the training schedule makes the closed-form versus approximate inference boundary explicit. Re-rendering posterior geometry samples yields native predictive uncertainty for interval calibration and active view selection. In a fixed-budget 16-to-32 active-view task, native NIW acquisition improves PSNR by +0.453 dB and LPIPS by -0.0146 over a scoring-only 3-member standard-ensemble baseline, winning 29/39 scene-seed pairs and 10/13 scene means; it also improves over PPU-style (+0.355 dB) and NIW-proxy (+0.401 dB) acquisition. NIW native intervals reduce 95% coverage error by about 17x relative to a shared proxy (0.046 vs. 0.796) and are about 10x closer to nominal coverage than a 3-member deep ensemble (0.047 vs. 0.454) at roughly one-third the training cost. As a reconstruction compatibility check, paired NIW-vs-standard analysis over 39 scene-seed runs yields +0.030 dB PSNR with 1.6% additional training time. These results position Bayesian 3DGS as a practical probabilistic scene representation for decision-facing tasks such as active view selection.