# IDU: Incremental Dynamic Update of Existing 3D Virtual Environments with New Imagery Data

arXiv: https://arxiv.org/abs/2508.17579 · HTML: https://mlsanity.com/paper/2508.17579/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 26 references that are in the map.
- First posted on arXiv 25 Aug 2025.

## Builds on (most cited first, 18 of 18)

- [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)
- [Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields](https://mlsanity.com/paper/2103.13415/) (2021)
- [DUSt3R: Geometric 3D Vision Made Easy](https://mlsanity.com/paper/2312.14132/) (2023)
- [Structured 3D Latents for Scalable and Versatile 3D Generation](https://mlsanity.com/paper/2412.01506/) (2024)
- [Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fields](https://mlsanity.com/paper/2304.06706/) (2023)
- [FastNeRF: High-Fidelity Neural Rendering at 200FPS](https://mlsanity.com/paper/2103.10380/) (2021)
- [STPLS3D: A Large-Scale Synthetic and Real Aerial Photogrammetry 3D Point Cloud Dataset](https://mlsanity.com/paper/2203.09065/) (2022)
- [Deformable Beta Splatting](https://mlsanity.com/paper/2501.18630/) (2025)
- [How to Reduce Change Detection to Semantic Segmentation](https://mlsanity.com/paper/2206.07557/) (2022)
- [AtomGS: Atomizing Gaussian Splatting for High-Fidelity Radiance Field](https://mlsanity.com/paper/2405.12369/) (2024)
- [SplatMAP: Online Dense Monocular SLAM with 3D Gaussian Splatting](https://mlsanity.com/paper/2501.07015/) (2025)
- [Fully Automated Photogrammetric Data Segmentation and Object Information Extraction Approach for Creating Simulation Terrain](https://mlsanity.com/paper/2008.03697/) (2020)
- [Semantic Segmentation and Data Fusion of Microsoft Bing 3D Cities and Small UAV-based Photogrammetric Data](https://mlsanity.com/paper/2008.09648/) (2020)
- [Generating synthetic photogrammetric data for training deep learning based 3D point cloud segmentation models](https://mlsanity.com/paper/2008.09647/) (2020)
- [Ground material classification for UAV-based photogrammetric 3D data A 2D-3D Hybrid Approach](https://mlsanity.com/paper/2109.12221/) (2021)
- [Utilizing Satellite Imagery Datasets and Machine Learning Data Models to Evaluate Infrastructure Change in Undeveloped Regions](https://mlsanity.com/paper/2009.00185/) (2020)
- [Open-Vocabulary High-Resolution 3D (OVHR3D) Data Segmentation and Annotation Framework](https://mlsanity.com/paper/2412.06268/) (2024)

## Abstract (arXiv)

For simulation and training purposes, military organizations have made substantial investments in developing high-resolution 3D virtual environments through extensive imaging and 3D scanning. However, the dynamic nature of battlefield conditions-where objects may appear or vanish over time-makes frequent full-scale updates both time-consuming and costly. In response, we introduce the Incremental Dynamic Update (IDU) pipeline, which efficiently updates existing 3D reconstructions, such as 3D Gaussian Splatting (3DGS), with only a small set of newly acquired images. Our approach starts with camera pose estimation to align new images with the existing 3D model, followed by change detection to pinpoint modifications in the scene. A 3D generative AI model is then used to create high-quality 3D assets of the new elements, which are seamlessly integrated into the existing 3D model. The IDU pipeline incorporates human guidance to ensure high accuracy in object identification and placement, with each update focusing on a single new object at a time. Experimental results confirm that our proposed IDU pipeline significantly reduces update time and labor, offering a cost-effective and targeted solution for maintaining up-to-date 3D models in rapidly evolving military scenarios.