# GS-2DGS: Geometrically Supervised 2DGS for Reflective Object Reconstruction

arXiv: https://arxiv.org/abs/2506.13110 · HTML: https://mlsanity.com/paper/2506.13110/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 40 of its 52 references that are in the map.
- First posted on arXiv 16 Jun 2025.

## Builds on (most cited first, 30 of 40)

- [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)
- [Vision Transformers for Dense Prediction](https://mlsanity.com/paper/2103.13413/) (2021)
- [NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction](https://mlsanity.com/paper/2106.10689/) (2021)
- [Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer](https://mlsanity.com/paper/1907.01341/) (2019)
- [Depth Map Prediction from a Single Image using a Multi-Scale Deep Network](https://mlsanity.com/paper/1406.2283/) (2014)
- [2D Gaussian Splatting for Geometrically Accurate Radiance Fields](https://mlsanity.com/paper/2403.17888/) (2024)
- [PlenOctrees for Real-time Rendering of Neural Radiance Fields](https://mlsanity.com/paper/2103.14024/) (2021)
- [MegaDepth: Learning Single-View Depth Prediction from Internet Photos](https://mlsanity.com/paper/1804.00607/) (2018)
- [Ref-NeRF: Structured View-Dependent Appearance for Neural Radiance Fields](https://mlsanity.com/paper/2112.03907/) (2021)
- [Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecture](https://mlsanity.com/paper/1411.4734/) (2014)
- [Neuralangelo: High-Fidelity Neural Surface Reconstruction](https://mlsanity.com/paper/2306.03092/) (2023)
- [Depth Pro: Sharp Monocular Metric Depth in Less Than a Second](https://mlsanity.com/paper/2410.02073/) (2024)
- [Extracting Triangular 3D Models, Materials, and Lighting From Images](https://mlsanity.com/paper/2111.12503/) (2021)
- [GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Pose](https://mlsanity.com/paper/1803.02276/) (2018)
- [Omnidata: A Scalable Pipeline for Making Multi-Task Mid-Level Vision Datasets from 3D Scans](https://mlsanity.com/paper/2110.04994/) (2021)
- [NeuS2: Fast Learning of Neural Implicit Surfaces for Multi-view Reconstruction](https://mlsanity.com/paper/2212.05231/) (2022)
- [GeoWizard: Unleashing the Diffusion Priors for 3D Geometry Estimation from a Single Image](https://mlsanity.com/paper/2403.12013/) (2024)
- [PGSR: Planar-based Gaussian Splatting for Efficient and High-Fidelity Surface Reconstruction](https://mlsanity.com/paper/2406.06521/) (2024)
- [Unleashing Text-to-Image Diffusion Models for Visual Perception](https://mlsanity.com/paper/2303.02153/) (2023)
- [GaussianShader: 3D Gaussian Splatting with Shading Functions for Reflective Surfaces](https://mlsanity.com/paper/2311.17977/) (2023)
- [GS-IR: 3D Gaussian Splatting for Inverse Rendering](https://mlsanity.com/paper/2311.16473/) (2023)
- [NeRO: Neural Geometry and BRDF Reconstruction of Reflective Objects from Multiview Images](https://mlsanity.com/paper/2305.17398/) (2023)
- [High-quality Surface Reconstruction using Gaussian Surfels](https://mlsanity.com/paper/2404.17774/) (2024)
- [NeuSG: Neural Implicit Surface Reconstruction with 3D Gaussian Splatting Guidance](https://mlsanity.com/paper/2312.00846/) (2023)
- [MonoViT: Self-Supervised Monocular Depth Estimation with a Vision Transformer](https://mlsanity.com/paper/2208.03543/) (2022)
- [Transformer-Based Attention Networks for Continuous Pixel-Wise Prediction](https://mlsanity.com/paper/2103.12091/) (2021)
- [Rethinking Inductive Biases for Surface Normal Estimation](https://mlsanity.com/paper/2403.00712/) (2024)
- [NeRFReN: Neural Radiance Fields with Reflections](https://mlsanity.com/paper/2111.15234/) (2021)
- [The Surprising Effectiveness of Diffusion Models for Optical Flow and Monocular Depth Estimation](https://mlsanity.com/paper/2306.01923/) (2023)

## Built on by (most cited first, 11 of 11)

- [GOGS: High-Fidelity Geometry and Relighting for Glossy Objects via Gaussian Surfels](https://mlsanity.com/paper/2508.14563/) (2025)
- [Structural Energy-Guided Sampling for View-Consistent Text-to-3D](https://mlsanity.com/paper/2508.16917/) (2025)
- [GTAvatar: Bridging Gaussian Splatting and Texture Mapping for Relightable and Editable Gaussian Avatars](https://mlsanity.com/paper/2512.09162/) (2025)
- [GTSR: Subsurface Scattering Awared 3D Gaussians for Translucent Surface Reconstruction](https://mlsanity.com/paper/2603.22036/) (2026)
- [3D-IDE: 3D Implicit Depth Emergent](https://mlsanity.com/paper/2604.03296/) (2026)
- [In Depth We Trust: Reliable Monocular Depth Supervision for Gaussian Splatting](https://mlsanity.com/paper/2604.05715/) (2026)
- [Spec-Gloss Surfels and Normal-Diffuse Priors for Relightable Glossy Objects](https://mlsanity.com/paper/2510.02069/) (2025)
- [Pygmalion Effect in Vision: Image-to-Clay Translation for Reflective Geometry Reconstruction](https://mlsanity.com/paper/2511.21098/) (2025)
- [GLINT: Modeling Scene-Scale Transparency via Gaussian Radiance Transport](https://mlsanity.com/paper/2603.26181/) (2026)
- [Structural Energy Guidance for View-Consistent Text-to-3D Generation](https://mlsanity.com/paper/2605.19876/) (2026)
- [ReVeal: A Reconstruction-Aware Real-to-Sim Framework for VLA Policy Evaluation](https://mlsanity.com/paper/2609.23910/) (2026)

## Abstract (arXiv)

3D modeling of highly reflective objects remains challenging due to strong view-dependent appearances. While previous SDF-based methods can recover high-quality meshes, they are often time-consuming and tend to produce over-smoothed surfaces. In contrast, 3D Gaussian Splatting (3DGS) offers the advantage of high speed and detailed real-time rendering, but extracting surfaces from the Gaussians can be noisy due to the lack of geometric constraints. To bridge the gap between these approaches, we propose a novel reconstruction method called GS-2DGS for reflective objects based on 2D Gaussian Splatting (2DGS). Our approach combines the rapid rendering capabilities of Gaussian Splatting with additional geometric information from foundation models. Experimental results on synthetic and real datasets demonstrate that our method significantly outperforms Gaussian-based techniques in terms of reconstruction and relighting and achieves performance comparable to SDF-based methods while being an order of magnitude faster. Code is available at https://github.com/hirotong/GS2DGS