# MILo: Mesh-In-the-Loop Gaussian Splatting for Detailed and Efficient Surface Reconstruction

arXiv: https://arxiv.org/abs/2506.24096 · HTML: https://mlsanity.com/paper/2506.24096/

## Key facts

- Cited by 37 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 56 references that are in the map.
- First posted on arXiv 30 Jun 2025.

## Builds on (most cited first, 30 of 33)

- [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)
- [Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields](https://mlsanity.com/paper/2103.13415/) (2021)
- [NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction](https://mlsanity.com/paper/2106.10689/) (2021)
- [Plenoxels: Radiance Fields without Neural Networks](https://mlsanity.com/paper/2112.05131/) (2021)
- [2D Gaussian Splatting for Geometrically Accurate Radiance Fields](https://mlsanity.com/paper/2403.17888/) (2024)
- [Volume Rendering of Neural Implicit Surfaces](https://mlsanity.com/paper/2106.12052/) (2021)
- [Neuralangelo: High-Fidelity Neural Surface Reconstruction](https://mlsanity.com/paper/2306.03092/) (2023)
- [Modular Primitives for High-Performance Differentiable Rendering](https://mlsanity.com/paper/2011.03277/) (2020)
- [Extracting Triangular 3D Models, Materials, and Lighting From Images](https://mlsanity.com/paper/2111.12503/) (2021)
- [NeuS2: Fast Learning of Neural Implicit Surfaces for Multi-view Reconstruction](https://mlsanity.com/paper/2212.05231/) (2022)
- [Gaussian Opacity Fields: Efficient Adaptive Surface Reconstruction in Unbounded Scenes](https://mlsanity.com/paper/2404.10772/) (2024)
- [BakedSDF: Meshing Neural SDFs for Real-Time View Synthesis](https://mlsanity.com/paper/2302.14859/) (2023)
- [3D Gaussian Splatting as Markov Chain Monte Carlo](https://mlsanity.com/paper/2404.09591/) (2024)
- [Mini-Splatting: Representing Scenes with a Constrained Number of Gaussians](https://mlsanity.com/paper/2403.14166/) (2024)
- [Taming 3DGS: High-Quality Radiance Fields with Limited Resources](https://mlsanity.com/paper/2406.15643/) (2024)
- [High-quality Surface Reconstruction using Gaussian Surfels](https://mlsanity.com/paper/2404.17774/) (2024)
- [Flexible Isosurface Extraction for Gradient-Based Mesh Optimization](https://mlsanity.com/paper/2308.05371/) (2023)
- [3D Gaussian Ray Tracing: Fast Tracing of Particle Scenes](https://mlsanity.com/paper/2407.07090/) (2024)
- [NeuSG: Neural Implicit Surface Reconstruction with 3D Gaussian Splatting Guidance](https://mlsanity.com/paper/2312.00846/) (2023)
- [RaDe-GS: Rasterizing Depth in Gaussian Splatting](https://mlsanity.com/paper/2406.01467/) (2024)
- [3DGUT: Enabling Distorted Cameras and Secondary Rays in Gaussian Splatting](https://mlsanity.com/paper/2412.12507/) (2024)
- [GSDF: 3DGS Meets SDF for Improved Rendering and Reconstruction](https://mlsanity.com/paper/2403.16964/) (2024)
- [Nerfbusters: Removing Ghostly Artifacts from Casually Captured NeRFs](https://mlsanity.com/paper/2304.10532/) (2023)
- [VCR-GauS: View Consistent Depth-Normal Regularizer for Gaussian Surface Reconstruction](https://mlsanity.com/paper/2406.05774/) (2024)
- [Neural Signed Distance Function Inference through Splatting 3D Gaussians Pulled on Zero-Level Set](https://mlsanity.com/paper/2410.14189/) (2024)
- [Binary Opacity Grids: Capturing Fine Geometric Detail for Mesh-Based View Synthesis](https://mlsanity.com/paper/2402.12377/) (2024)
- [Radiant Foam: Real-Time Differentiable Ray Tracing](https://mlsanity.com/paper/2502.01157/) (2025)
- [MAtCha Gaussians: Atlas of Charts for High-Quality Geometry and Photorealism From Sparse Views](https://mlsanity.com/paper/2412.06767/) (2024)
- [Efficient Scene Modeling via Structure-Aware and Region-Prioritized 3D Gaussians](https://mlsanity.com/paper/2411.12788/) (2024)

## Built on by (most cited first, 30 of 37)

- [Faster-GS: Analyzing and Improving Gaussian Splatting Optimization](https://mlsanity.com/paper/2602.09999/) (2026)
- [ARTDECO: Towards Efficient and High-Fidelity On-the-Fly 3D Reconstruction with Structured Scene Representation](https://mlsanity.com/paper/2510.08551/) (2025)
- [Radiance Meshes for Volumetric Reconstruction](https://mlsanity.com/paper/2512.04076/) (2025)
- [Triangle Splatting+: Differentiable Rendering with Opaque Triangles](https://mlsanity.com/paper/2509.25122/) (2025)
- [Geometry-Grounded Gaussian Splatting](https://mlsanity.com/paper/2601.17835/) (2026)
- [MAGICIAN: Efficient Long-Term Planning with Imagined Gaussians for Active Mapping](https://mlsanity.com/paper/2603.22650/) (2026)
- [From Blobs to Spokes: High-Fidelity Surface Reconstruction via Oriented Gaussians](https://mlsanity.com/paper/2604.07337/) (2026)
- [Confidence-Based Mesh Extraction from 3D Gaussians](https://mlsanity.com/paper/2603.24725/) (2026)
- [Material-informed Gaussian Splatting for 3D World Reconstruction in a Digital Twin](https://mlsanity.com/paper/2511.20348/) (2025)
- [ObjSplat: Geometry-Aware Gaussian Surfels for Active Object Reconstruction](https://mlsanity.com/paper/2601.06997/) (2026)
- [PolarGS: Polarimetric Cues for Ambiguity-Free Gaussian Splatting with Accurate Geometry Recovery](https://mlsanity.com/paper/2512.00794/) (2025)
- [Hybrid Latents: Geometry-Appearance-Aware Surfel Splatting](https://mlsanity.com/paper/2604.14928/) (2026)
- [Revisiting Photometric Ambiguity for Accurate Gaussian-Splatting Surface Reconstruction](https://mlsanity.com/paper/2605.12494/) (2026)
- [ArtMesh: Part-Aware Articulated Mesh Fields with Motion-Consistent Dynamics](https://mlsanity.com/paper/2605.16582/) (2026)
- [NewtPhys: Do Foundation Models Understand Newtonian Physics?](https://mlsanity.com/paper/2606.03986/) (2026)
- [Geometry Gaussians: Decoupling Appearance and Geometry in Gaussian Splatting](https://mlsanity.com/paper/2606.05124/) (2026)
- [Surflo: Consistent 3D Surface Flow Model with Global State](https://mlsanity.com/paper/2606.13644/) (2026)
- [FlowObject: Flow Steering for Bridging Generative Priors and Reconstruction Fidelity](https://mlsanity.com/paper/2606.19019/) (2026)
- [GS-2M: Material-aware Gaussian Splatting for High-fidelity Mesh Reconstruction](https://mlsanity.com/paper/2509.22276/) (2025)
- [COREA: Coupled Relightable 3D Gaussians and SDFs for Efficient Normal Alignment](https://mlsanity.com/paper/2512.07107/) (2025)
- [SSR-GS: Separating Specular Reflection in Gaussian Splatting for Glossy Surface Reconstruction](https://mlsanity.com/paper/2603.05152/) (2026)
- [Ref-DGS: Reflective Dual Gaussian Splatting](https://mlsanity.com/paper/2603.07664/) (2026)
- [Detailed Geometry and Appearance from Opportunistic Motion](https://mlsanity.com/paper/2603.26665/) (2026)
- [LightHarmony3D: Harmonizing Illumination and Shadows for Object Insertion in 3D Gaussian Splatting](https://mlsanity.com/paper/2603.29209/) (2026)
- [2D-SuGaR: Surface-Aware Gaussian Splatting for Geometrically Accurate Mesh Reconstruction](https://mlsanity.com/paper/2605.00569/) (2026)
- [City-Mesh3R: Simulation-Ready City-Scale 3D Mesh Reconstruction from Multi-View Images](https://mlsanity.com/paper/2605.30310/) (2026)
- [Triangle Splatting SLAM](https://mlsanity.com/paper/2605.31419/) (2026)
- [TRON: Tracing Rays to Orchestrate a Neural Renderer for 3D Gaussian Reconstructions](https://mlsanity.com/paper/2606.11314/) (2026)
- [FLAT: Feedforward Latent Triangle Splatting for Geometrically Accurate Scene Generation](https://mlsanity.com/paper/2606.24876/) (2026)
- [Intrinsic decomposition and editing of 3D Gaussian splats](https://mlsanity.com/paper/2606.31637/) (2026)

## Abstract (arXiv)

While recent advances in Gaussian Splatting have enabled fast reconstruction of high-quality 3D scenes from images, extracting accurate surface meshes remains a challenge. Current approaches extract the surface through costly post-processing steps, resulting in the loss of fine geometric details or requiring significant time and leading to very dense meshes with millions of vertices. More fundamentally, the a posteriori conversion from a volumetric to a surface representation limits the ability of the final mesh to preserve all geometric structures captured during training. We present MILo, a novel Gaussian Splatting framework that bridges the gap between volumetric and surface representations by differentiably extracting a mesh from the 3D Gaussians. We design a fully differentiable procedure that constructs the mesh-including both vertex locations and connectivity-at every iteration directly from the parameters of the Gaussians, which are the only quantities optimized during training. Our method introduces three key technical contributions: a bidirectional consistency framework ensuring both representations-Gaussians and the extracted mesh-capture the same underlying geometry during training; an adaptive mesh extraction process performed at each training iteration, which uses Gaussians as differentiable pivots for Delaunay triangulation; a novel method for computing signed distance values from the 3D Gaussians that enables precise surface extraction while avoiding geometric erosion. Our approach can reconstruct complete scenes, including backgrounds, with state-of-the-art quality while requiring an order of magnitude fewer mesh vertices than previous methods. Due to their light weight and empty interior, our meshes are well suited for downstream applications such as physics simulations or animation.