# From Pixels to Primitives: Scene Change Detection in 3D Gaussian Splatting

arXiv: https://arxiv.org/abs/2605.07203 · HTML: https://mlsanity.com/paper/2605.07203/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 50 references that are in the map.
- First posted on arXiv 8 May 2026.

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

- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?](https://mlsanity.com/paper/1703.04977/) (2017)
- [2D Gaussian Splatting for Geometrically Accurate Radiance Fields](https://mlsanity.com/paper/2403.17888/) (2024)
- [In Search of Lost Domain Generalization](https://mlsanity.com/paper/2007.01434/) (2020)
- [Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methods](https://mlsanity.com/paper/1910.09457/) (2019)
- [SuGaR: Surface-Aligned Gaussian Splatting for Efficient 3D Mesh Reconstruction and High-Quality Mesh Rendering](https://mlsanity.com/paper/2311.12775/) (2023)
- [Gaussian Splatting SLAM](https://mlsanity.com/paper/2312.06741/) (2023)
- [Fully Convolutional Siamese Networks for Change Detection](https://mlsanity.com/paper/1810.08462/) (2018)
- [PGSR: Planar-based Gaussian Splatting for Efficient and High-Fidelity Surface Reconstruction](https://mlsanity.com/paper/2406.06521/) (2024)
- [Relightable 3D Gaussians: Realistic Point Cloud Relighting with BRDF Decomposition and Ray Tracing](https://mlsanity.com/paper/2311.16043/) (2023)
- [FastGS: Training 3D Gaussian Splatting in 100 Seconds](https://mlsanity.com/paper/2511.04283/) (2025)
- [GI-GS: Global Illumination Decomposition on Gaussian Splatting for Inverse Rendering](https://mlsanity.com/paper/2410.02619/) (2024)
- [SplatPose & Detect: Pose-Agnostic 3D Anomaly Detection](https://mlsanity.com/paper/2404.06832/) (2024)
- [3D VSG: Long-term Semantic Scene Change Prediction through 3D Variable Scene Graphs](https://mlsanity.com/paper/2209.07896/) (2022)
- [The Change You Want to See (Now in 3D)](https://mlsanity.com/paper/2308.10417/) (2023)
- [Towards Generalizable Scene Change Detection](https://mlsanity.com/paper/2409.06214/) (2024)
- [3DGS-CD: 3D Gaussian Splatting-based Change Detection for Physical Object Rearrangement](https://mlsanity.com/paper/2411.03706/) (2024)
- [Zero-Shot Scene Change Detection](https://mlsanity.com/paper/2406.11210/) (2024)
- [ZeroSCD: Zero-Shot Street Scene Change Detection](https://mlsanity.com/paper/2409.15255/) (2024)
- [Robust Scene Change Detection Using Visual Foundation Models and Cross-Attention Mechanisms](https://mlsanity.com/paper/2409.16850/) (2024)
- [Multi-View Pose-Agnostic Change Localization with Zero Labels](https://mlsanity.com/paper/2412.03911/) (2024)
- [SplatPose+: Real-time Image-Based Pose-Agnostic 3D Anomaly Detection](https://mlsanity.com/paper/2410.12080/) (2024)
- [CL-Splats: Continual Learning of Gaussian Splatting with Local Optimization](https://mlsanity.com/paper/2506.21117/) (2025)
- [Towards Generalizing to Unseen Domains with Few Labels](https://mlsanity.com/paper/2403.11674/) (2024)
- [City-scale Scene Change Detection using Point Clouds](https://mlsanity.com/paper/2103.14314/) (2021)
- [EMPLACE: Self-Supervised Urban Scene Change Detection](https://mlsanity.com/paper/2503.17716/) (2025)
- [Gaussian Difference: Find Any Change Instance in 3D Scenes](https://mlsanity.com/paper/2502.16941/) (2025)
- [Predictive Photometric Uncertainty in Gaussian Splatting for Novel View Synthesis](https://mlsanity.com/paper/2603.22786/) (2026)

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

- [PlenoCI: Plenoptic CharacterIstics for View Dependence Aware Change Classification](https://mlsanity.com/paper/2609.28930/) (2026)
- [ChronoFuseGS: Multi-Temporal Gaussian Fusion with Per-Splat Persistence and Change Visualization](https://mlsanity.com/paper/2609.31339/) (2026)
- [GS-Pool: Object-Level Change Detection in 3D Gaussian Splatting](https://mlsanity.com/paper/2610.06688/) (2026)

## Abstract (arXiv)

Scene change detection methods built on Gaussian splatting universally follow a render-then-compare paradigm: the pre-change scene is rendered into 2D and compared against post-change images via pixel or feature residuals. This change detection problem with Gaussian Splatting has been treated as a question about pixels; we treat it as a question about primitives. We provide direct evidence that native primitive attributes alone -- position, anisotropic covariance, and color -- carry sufficient signal for scene change detection. What makes primitive-space comparison hard is the under-constrained nature of Gaussian splatting representation: independent optimizations yield primitive solutions whose count, positions, shapes, and colors differ even where nothing has changed. We address this challenge with anisotropic models of geometric and photometric drift, complemented by a per-primitive observability term that reflects the extent to which each Gaussian is constrained by the camera geometry. Operating directly on primitives gives our method, GD-DIFF, two properties that distinguish it from render-then-compare methods. First, change maps are multi-view consistent by construction, where prior work had to learn this through an additional optimization objective. Second, geometric and appearance changes are scored separately, identifying not just where but what kind of change occurred, distinguishing structural changes (e.g., an added object) from surface-level ones (e.g., a color change) without supervision or external model dependencies. On real-world benchmarks, GS-DIFF surpasses the prior state-of-the-art approach by ~17% in mean Intersection over Union.