# VG3S: Visual Geometry Grounded Gaussian Splatting for Semantic Occupancy Prediction

arXiv: https://arxiv.org/abs/2603.06210 · HTML: https://mlsanity.com/paper/2603.06210/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 32 references that are in the map.
- First posted on arXiv 6 Mar 2026.

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

- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [Vision Transformers for Dense Prediction](https://mlsanity.com/paper/2103.13413/) (2021)
- [VGGT: Visual Geometry Grounded Transformer](https://mlsanity.com/paper/2503.11651/) (2025)
- [BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers](https://mlsanity.com/paper/2203.17270/) (2022)
- [Vision Transformers Need Registers](https://mlsanity.com/paper/2309.16588/) (2023)
- [DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queries](https://mlsanity.com/paper/2110.06922/) (2021)
- [Tri-Perspective View for Vision-Based 3D Semantic Occupancy Prediction](https://mlsanity.com/paper/2302.07817/) (2023)
- [MonoScene: Monocular 3D Semantic Scene Completion](https://mlsanity.com/paper/2112.00726/) (2021)
- [OctNet: Learning Deep 3D Representations at High Resolutions](https://mlsanity.com/paper/1611.05009/) (2016)
- [SurroundOcc: Multi-Camera 3D Occupancy Prediction for Autonomous Driving](https://mlsanity.com/paper/2303.09551/) (2023)
- [VoxFormer: Sparse Voxel Transformer for Camera-based 3D Semantic Scene Completion](https://mlsanity.com/paper/2302.12251/) (2023)
- [OccFormer: Dual-path Transformer for Vision-based 3D Semantic Occupancy Prediction](https://mlsanity.com/paper/2304.05316/) (2023)
- [Visual Geometry Grounded Deep Structure From Motion](https://mlsanity.com/paper/2312.04563/) (2023)
- [Atlas: End-to-End 3D Scene Reconstruction from Posed Images](https://mlsanity.com/paper/2003.10432/) (2020)
- [GaussianFormer: Scene as Gaussians for Vision-Based 3D Semantic Occupancy Prediction](https://mlsanity.com/paper/2405.17429/) (2024)
- [RenderOcc: Vision-Centric 3D Occupancy Prediction with 2D Rendering Supervision](https://mlsanity.com/paper/2309.09502/) (2023)
- [GaussianFormer-2: Probabilistic Gaussian Superposition for Efficient 3D Occupancy Prediction](https://mlsanity.com/paper/2412.04384/) (2024)
- [ViewFormer: Exploring Spatiotemporal Modeling for Multi-View 3D Occupancy Perception via View-Guided Transformers](https://mlsanity.com/paper/2405.04299/) (2024)
- [DGGT: Feedforward 4D Reconstruction of Dynamic Driving Scenes using Unposed Images](https://mlsanity.com/paper/2512.03004/) (2025)
- [DVGT: Driving Visual Geometry Transformer](https://mlsanity.com/paper/2512.16919/) (2025)
- [SEPT: Standard-Definition Map Enhanced Scene Perception and Topology Reasoning for Autonomous Driving](https://mlsanity.com/paper/2505.12246/) (2025)
- [GoIRL: Graph-Oriented Inverse Reinforcement Learning for Multimodal Trajectory Prediction](https://mlsanity.com/paper/2506.21121/) (2025)
- [ST-GS: Vision-Based 3D Semantic Occupancy Prediction with Spatial-Temporal Gaussian Splatting](https://mlsanity.com/paper/2509.16552/) (2025)
- [VG3T: Visual Geometry Grounded Gaussian Transformer](https://mlsanity.com/paper/2512.05988/) (2025)
- [Stereo Neural Vernier Caliper](https://mlsanity.com/paper/2203.11018/) (2022)
- [Learning better representations for crowded pedestrians in offboard LiDAR-camera 3D tracking-by-detection](https://mlsanity.com/paper/2505.16029/) (2025)

## Built on by (most cited first, 5 of 5)

- [VGOcc: Learning Visual-Geometric Gaussians for Vision-Centric 3D Driving Occupancy Prediction](https://mlsanity.com/paper/2607.18078/) (2026)
- [Learning Adaptive Semantic Gaussian Allocation for 3D Occupancy](https://mlsanity.com/paper/2607.21896/) (2026)
- [OccAnyScene: Towards Unified Indoor-Outdoor 3D Occupancy Prediction](https://mlsanity.com/paper/2608.08696/) (2026)
- [Monocular Depth Estimation from a Single Image: Progress and Opportunities](https://mlsanity.com/paper/2609.01172/) (2026)
- [GNFormer: Gaussian Neural Field Transformer for Efficient Camera-based Occupancy Prediction](https://mlsanity.com/paper/2610.15522/) (2026)

## Abstract (arXiv)

3D semantic occupancy prediction has become a crucial perception task for comprehensive scene understanding in autonomous driving. While recent advances have explored 3D Gaussian splatting for occupancy modeling to substantially reduce computational overhead, the generation of high-quality 3D Gaussians relies heavily on accurate geometric cues, which are often insufficient in purely vision-centric paradigms. To bridge this gap, we advocate for injecting the strong geometric grounding capability from Vision Foundation Models (VFMs) into occupancy prediction. In this regard, we introduce Visual Geometry Grounded Gaussian Splatting (VG3S), a novel framework that empowers Gaussian-based occupancy prediction with cross-view 3D geometric grounding. Specifically, to fully exploit the rich 3D geometric priors from a frozen VFM, we propose a plug-and-play hierarchical geometric feature adapter, which can effectively transform generic VFM tokens via feature aggregation, task-specific alignment, and multi-scale restructuring. Extensive experiments on the nuScenes occupancy benchmark demonstrate that VG3S achieves remarkable improvements of 12.6% in IoU and 7.5% in mIoU over the baseline. Furthermore, we show that VG3S generalizes seamlessly across diverse VFMs, consistently enhancing occupancy prediction accuracy and firmly underscoring the immense value of integrating priors derived from powerful, pre-trained geometry-grounded VFMs.