# GS-SDF: LiDAR-Augmented Gaussian Splatting and Neural SDF for Geometrically Consistent Rendering and Reconstruction

arXiv: https://arxiv.org/abs/2503.10170 · HTML: https://mlsanity.com/paper/2503.10170/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 32 references that are in the map.
- First posted on arXiv 13 Mar 2025.

## Builds on (most cited first, 26 of 26)

- [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)
- [2D Gaussian Splatting for Geometrically Accurate Radiance Fields](https://mlsanity.com/paper/2403.17888/) (2024)
- [The Replica Dataset: A Digital Replica of Indoor Spaces](https://mlsanity.com/paper/1906.05797/) (2019)
- [SuGaR: Surface-Aligned Gaussian Splatting for Efficient 3D Mesh Reconstruction and High-Quality Mesh Rendering](https://mlsanity.com/paper/2311.12775/) (2023)
- [iMAP: Implicit Mapping and Positioning in Real-Time](https://mlsanity.com/paper/2103.12352/) (2021)
- [Gaussian Splatting SLAM](https://mlsanity.com/paper/2312.06741/) (2023)
- [PGSR: Planar-based Gaussian Splatting for Efficient and High-Fidelity Surface Reconstruction](https://mlsanity.com/paper/2406.06521/) (2024)
- [Gaussian Opacity Fields: Efficient Adaptive Surface Reconstruction in Unbounded Scenes](https://mlsanity.com/paper/2404.10772/) (2024)
- [EmbodiedScan: A Holistic Multi-Modal 3D Perception Suite Towards Embodied AI](https://mlsanity.com/paper/2312.16170/) (2023)
- [iSDF: Real-Time Neural Signed Distance Fields for Robot Perception](https://mlsanity.com/paper/2204.02296/) (2022)
- [GSDF: 3DGS Meets SDF for Improved Rendering and Reconstruction](https://mlsanity.com/paper/2403.16964/) (2024)
- [3DGSR: Implicit Surface Reconstruction with 3D Gaussian Splatting](https://mlsanity.com/paper/2404.00409/) (2024)
- [A Survey on Metaverse: Fundamentals, Security, and Privacy](https://mlsanity.com/paper/2203.02662/) (2022)
- [R3LIVE: A Robust, Real-time, RGB-colored, LiDAR-Inertial-Visual tightly-coupled state Estimation and mapping package](https://mlsanity.com/paper/2109.07982/) (2021)
- [LVI-SAM: Tightly-coupled Lidar-Visual-Inertial Odometry via Smoothing and Mapping](https://mlsanity.com/paper/2104.10831/) (2021)
- [SHINE-Mapping: Large-Scale 3D Mapping Using Sparse Hierarchical Implicit Neural Representations](https://mlsanity.com/paper/2210.02299/) (2022)
- [FAST-LIVO2: Fast, Direct LiDAR-Inertial-Visual Odometry](https://mlsanity.com/paper/2408.14035/) (2024)
- [LIV-GaussMap: LiDAR-Inertial-Visual Fusion for Real-time 3D Radiance Field Map Rendering](https://mlsanity.com/paper/2401.14857/) (2024)
- [The Oxford Spires Dataset: Benchmarking Large-Scale LiDAR-Visual Localisation, Reconstruction and Radiance Field Methods](https://mlsanity.com/paper/2411.10546/) (2024)
- [H2-Mapping: Real-time Dense Mapping Using Hierarchical Hybrid Representation](https://mlsanity.com/paper/2306.03207/) (2023)
- [LI-GS: Gaussian Splatting with LiDAR Incorporated for Accurate Large-Scale Reconstruction](https://mlsanity.com/paper/2409.12899/) (2024)
- [StEik: Stabilizing the Optimization of Neural Signed Distance Functions and Finer Shape Representation](https://mlsanity.com/paper/2305.18414/) (2023)
- [SiLVR: Scalable Lidar-Visual Reconstruction with Neural Radiance Fields for Robotic Inspection](https://mlsanity.com/paper/2403.06877/) (2024)
- [Neural Surface Reconstruction and Rendering for LiDAR-Visual Systems](https://mlsanity.com/paper/2409.05310/) (2024)
- [Towards Large-Scale Incremental Dense Mapping using Robot-centric Implicit Neural Representation](https://mlsanity.com/paper/2306.10472/) (2023)

## Built on by (most cited first, 8 of 8)

- [ObjSplat: Geometry-Aware Gaussian Surfels for Active Object Reconstruction](https://mlsanity.com/paper/2601.06997/) (2026)
- [Towards Next-Generation SLAM: A Survey on 3DGS-SLAM Focusing on Performance, Robustness, and Future Directions](https://mlsanity.com/paper/2602.04251/) (2026)
- [LIVE-GS: Online LiDAR-Inertial-Visual State Estimation and Globally Consistent Mapping with 3D Gaussian Splatting](https://mlsanity.com/paper/2507.23273/) (2025)
- [COREA: Coupled Relightable 3D Gaussians and SDFs for Efficient Normal Alignment](https://mlsanity.com/paper/2512.07107/) (2025)
- [Geo-NVS-w: Geometry-Aware Novel View Synthesis In-the-Wild with an SDF Renderer](https://mlsanity.com/paper/2601.08371/) (2026)
- [Transforming Omnidirectional RGB-LiDAR data into 3D Gaussian Splatting](https://mlsanity.com/paper/2603.06061/) (2026)
- [Gaussian-Voxel Duet: A Dual-Scaffolding Hybrid Representation for Fast and Accurate Monocular Surface Reconstruction](https://mlsanity.com/paper/2605.26616/) (2026)
- [Real-Time LiDAR Gaussian Splatting SLAM](https://mlsanity.com/paper/2607.04127/) (2026)

## Abstract (arXiv)

Digital twins are fundamental to the development of autonomous driving and embodied artificial intelligence. However, achieving high-granularity surface reconstruction and high-fidelity rendering remains a challenge. Gaussian splatting offers efficient photorealistic rendering but struggles with geometric inconsistencies due to fragmented primitives and sparse observational data in robotics applications. Existing regularization methods, which rely on render-derived constraints, often fail in complex environments. Moreover, effectively integrating sparse LiDAR data with Gaussian splatting remains challenging. We propose a unified LiDAR-visual system that synergizes Gaussian splatting with a neural signed distance field. The accurate LiDAR point clouds enable a trained neural signed distance field to offer a manifold geometry field. This motivates us to offer an SDF-based Gaussian initialization for physically grounded primitive placement and a comprehensive geometric regularization for geometrically consistent rendering and reconstruction. Experiments demonstrate superior reconstruction accuracy and rendering quality across diverse trajectories. To benefit the community, the codes are released at https://github.com/hku-mars/GS-SDF.