mlsanityData to 14 Oct 2026

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

arXiv 2506.13110 ↗First posted 16 Jun 2025cs.CVcited by 11

Not on the map. Why?

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

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

40 of 52 references.

References · 40

  1. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
  2. 2021Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fieldscited by 1,964
  3. 2021Vision Transformers for Dense Predictioncited by 1,803
  4. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,712
  5. 2019Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfercited by 1,495
  6. 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,274
  7. 20242D Gaussian Splatting for Geometrically Accurate Radiance Fieldscited by 1,076
  8. 2021PlenOctrees for Real-time Rendering of Neural Radiance Fieldscited by 905
  9. 2018MegaDepth: Learning Single-View Depth Prediction from Internet Photoscited by 737
  10. 2021Ref-NeRF: Structured View-Dependent Appearance for Neural Radiance Fieldscited by 575
  11. 2014Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecturecited by 483
  12. 2023Neuralangelo: High-Fidelity Neural Surface Reconstructioncited by 467
28 more
  1. 2024Depth Pro: Sharp Monocular Metric Depth in Less Than a Secondcited by 404
  2. 2021Extracting Triangular 3D Models, Materials, and Lighting From Imagescited by 366
  3. 2018GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Posecited by 342
  4. 2021Omnidata: A Scalable Pipeline for Making Multi-Task Mid-Level Vision Datasets from 3D Scanscited by 336
  5. 2022NeuS2: Fast Learning of Neural Implicit Surfaces for Multi-view Reconstructioncited by 314
  6. 2024GeoWizard: Unleashing the Diffusion Priors for 3D Geometry Estimation from a Single Imagecited by 286
  7. 2024PGSR: Planar-based Gaussian Splatting for Efficient and High-Fidelity Surface Reconstructioncited by 285
  8. 2023Unleashing Text-to-Image Diffusion Models for Visual Perceptioncited by 269
  9. 2023GaussianShader: 3D Gaussian Splatting with Shading Functions for Reflective Surfacescited by 252
  10. 2023GS-IR: 3D Gaussian Splatting for Inverse Renderingcited by 224
  11. 2023NeRO: Neural Geometry and BRDF Reconstruction of Reflective Objects from Multiview Imagescited by 163
  12. 2024High-quality Surface Reconstruction using Gaussian Surfelscited by 161
  13. 2023NeuSG: Neural Implicit Surface Reconstruction with 3D Gaussian Splatting Guidancecited by 138
  14. 2022MonoViT: Self-Supervised Monocular Depth Estimation with a Vision Transformercited by 136
  15. 2021Transformer-Based Attention Networks for Continuous Pixel-Wise Predictioncited by 125
  16. 2024Rethinking Inductive Biases for Surface Normal Estimationcited by 124
  17. 2021NeRFReN: Neural Radiance Fields with Reflectionscited by 122
  18. 2023The Surprising Effectiveness of Diffusion Models for Optical Flow and Monocular Depth Estimationcited by 116
  19. 2024GSDF: 3DGS Meets SDF for Improved Rendering and Reconstructioncited by 83
  20. 2024Fine-Tuning Image-Conditional Diffusion Models is Easier than You Thinkcited by 83
  21. 2023DiffusionDepth: Diffusion Denoising Approach for Monocular Depth Estimationcited by 82
  22. 2023Stanford-ORB: A Real-World 3D Object Inverse Rendering Benchmarkcited by 51
  23. 2024VCR-GauS: View Consistent Depth-Normal Regularizer for Gaussian Surface Reconstructioncited by 50
  24. 2024TensoSDF: Roughness-aware Tensorial Representation for Robust Geometry and Material Reconstructioncited by 26
  25. 2023Seeing Through the Glass: Neural 3D Reconstruction of Object Inside a Transparent Containercited by 10
  26. 2024Stealing Stable Diffusion Prior for Robust Monocular Depth Estimationcited by 7
  27. 2023Instant-NeRF: Instant On-Device Neural Radiance Field Training via Algorithm-Accelerator Co-Designed Near-Memory Processingcited by 6
  28. 2024Planar Reflection-Aware Neural Radiance Fieldscited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 5; 2026: 6.

11 papers.

  1. 2025GOGS: High-Fidelity Geometry and Relighting for Glossy Objects via Gaussian Surfelscited by 2
  2. 2025Structural Energy-Guided Sampling for View-Consistent Text-to-3Dcited by 1
  3. 2025GTAvatar: Bridging Gaussian Splatting and Texture Mapping for Relightable and Editable Gaussian Avatarscited by 1
  4. 2026GTSR: Subsurface Scattering Awared 3D Gaussians for Translucent Surface Reconstructioncited by 1
  5. 20263D-IDE: 3D Implicit Depth Emergentcited by 1
  6. 2026In Depth We Trust: Reliable Monocular Depth Supervision for Gaussian Splattingcited by 1
  7. 2025Spec-Gloss Surfels and Normal-Diffuse Priors for Relightable Glossy Objectscited by 0
  8. 2025Pygmalion Effect in Vision: Image-to-Clay Translation for Reflective Geometry Reconstructioncited by 0
  9. 2026GLINT: Modeling Scene-Scale Transparency via Gaussian Radiance Transportcited by 0
  10. 2026Structural Energy Guidance for View-Consistent Text-to-3D Generationcited by 0
  11. 2026ReVeal: A Reconstruction-Aware Real-to-Sim Framework for VLA Policy Evaluationcited by 0