mlsanityData to 14 Oct 2026

Mirror-3DGS: Incorporating Mirror Reflections into 3D Gaussian Splatting

arXiv 2404.01168 ↗First posted 1 Apr 2024cs.CV cs.GRcited by 18

Not on the map. Why?

Abstract (arXiv)

3D Gaussian Splatting (3DGS) has significantly advanced 3D scene reconstruction and novel view synthesis. However, like Neural Radiance Fields (NeRF), 3DGS struggles with accurately modeling physical reflections, particularly in mirrors, leading to incorrect reconstructions and inconsistent reflective properties. To address this challenge, we introduce Mirror-3DGS, a novel framework designed to accurately handle mirror geometries and reflections, thereby generating realistic mirror reflections. By incorporating mirror attributes into 3DGS and leveraging plane mirror imaging principles, Mirror-3DGS simulates a mirrored viewpoint from behind the mirror, enhancing the realism of scene renderings. Extensive evaluations on both synthetic and real-world scenes demonstrate that our method can render novel views with improved fidelity in real-time, surpassing the state-of-the-art Mirror-NeRF, especially in mirror regions.

Key facts. Cited by 18 papers in the map (data through 14 Oct 2026). Builds on 46 of its 56 references that are in the map. First posted on arXiv 1 Apr 2024.

Builds on

46 of 56 references.

References · 46

  1. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  2. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
  3. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,723
  4. 2021Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fieldscited by 2,032
  5. 2021Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fieldscited by 1,964
  6. 2021Plenoxels: Radiance Fields without Neural Networkscited by 1,613
  7. 2020D-NeRF: Neural Radiance Fields for Dynamic Scenescited by 1,465
  8. 20234D Gaussian Splatting for Real-Time Dynamic Scene Renderingcited by 1,157
  9. 2021Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstructioncited by 964
  10. 2023DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creationcited by 843
  11. 2023Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstructioncited by 759
  12. 2023K-Planes: Explicit Radiance Fields in Space, Time, and Appearancecited by 746
34 more
  1. 2023Dynamic 3D Gaussians: Tracking by Persistent Dynamic View Synthesiscited by 737
  2. 2023Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fieldscited by 671
  3. 2023HexPlane: A Fast Representation for Dynamic Scenescited by 587
  4. 2021Ref-NeRF: Structured View-Dependent Appearance for Neural Radiance Fieldscited by 575
  5. 2022Point-NeRF: Point-based Neural Radiance Fieldscited by 503
  6. 2020NeRV: Neural Reflectance and Visibility Fields for Relighting and View Synthesiscited by 496
  7. 2023Gaussian Splatting SLAMcited by 415
  8. 2023SplaTAM: Splat, Track & Map 3D Gaussians for Dense RGB-D SLAMcited by 388
  9. 2022Fast Dynamic Radiance Fields with Time-Aware Neural Voxelscited by 346
  10. 2023Spacetime Gaussian Feature Splatting for Real-Time Dynamic View Synthesiscited by 344
  11. 2023GaussianDreamer: Fast Generation from Text to 3D Gaussians by Bridging 2D and 3D Diffusion Modelscited by 255
  12. 2019Differentiable Surface Splatting for Point-based Geometry Processingcited by 239
  13. 2021Editing Conditional Radiance Fieldscited by 222
  14. 2023MERF: Memory-Efficient Radiance Fields for Real-time View Synthesis in Unbounded Scenescited by 218
  15. 2021Neural-PIL: Neural Pre-Integrated Lighting for Reflectance Decompositioncited by 205
  16. 2020Neural Reflectance Fields for Appearance Acquisitioncited by 196
  17. 2021Point-Based Neural Rendering with Per-View Optimizationcited by 190
  18. 2022Modeling Indirect Illumination for Inverse Renderingcited by 168
  19. 2021NeRFReN: Neural Radiance Fields with Reflectionscited by 122
  20. 2022DeVRF: Fast Deformable Voxel Radiance Fields for Dynamic Scenescited by 103
  21. 2021NeRF-SR: High-Quality Neural Radiance Fields using Supersamplingcited by 95
  22. 2023SINE: Semantic-driven Image-based NeRF Editing with Prior-guided Editing Fieldcited by 94
  23. 2022SAMURAI: Shape And Material from Unconstrained Real-world Arbitrary Image collectionscited by 89
  24. 2023GIR: 3D Gaussian Inverse Rendering for Relightable Scene Factorizationcited by 87
  25. 2023Neural Point Catacaustics for Novel-View Synthesis of Reflectionscited by 82
  26. 2022Deforming Radiance Fields with Cagescited by 78
  27. 2022Removing Objects From Neural Radiance Fieldscited by 66
  28. 2023NeMF: Inverse Volume Rendering with Neural Microflake Fieldcited by 34
  29. 2023Learning Depth Estimation for Transparent and Mirror Surfacescited by 34
  30. 2023SpecNeRF: Gaussian Directional Encoding for Specular Reflectionscited by 30
  31. 2023Mirror-NeRF: Learning Neural Radiance Fields for Mirrors with Whitted-Style Ray Tracingcited by 22
  32. 2022SqueezeNeRF: Further factorized FastNeRF for memory-efficient inferencecited by 16
  33. 2023TraM-NeRF: Tracing Mirror and Near-Perfect Specular Reflections through Neural Radiance Fieldscited by 7
  34. 2023Neural Video Fields Editingcited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 8; 2025: 5; 2026: 5.

18 papers.

Sort:

By area:

  1. 20243D Gaussian Splatting: Survey, Technologies, Challenges, and Opportunitiescited by 78
  2. 2024Wild-GS: Real-Time Novel View Synthesis from Unconstrained Photo Collectionscited by 56
  3. 2024InstanceGaussian: Appearance-Semantic Joint Gaussian Representation for 3D Instance-Level Perceptioncited by 35
  4. 2025A Survey on 3D Gaussian Splatting Applications: Segmentation, Editing, and Generationcited by 19
  5. 2024Reflecting Reality: Enabling Diffusion Models to Produce Faithful Mirror Reflectionscited by 16
  6. 2025Digital Twin Generation from Visual Data: A Surveycited by 7
  7. 2025TinySplat: Feedforward Approach for Generating Compact 3D Scene Representationcited by 7
  8. 2024Faster and Better 3D Splatting via Group Trainingcited by 6
  9. 2025Reflections Unlock: Geometry-Aware Reflection Disentanglement in 3D Gaussian Splatting for Photorealistic Scenes Renderingcited by 4
  10. 2024RefGaussian: Disentangling Reflections from 3D Gaussian Splatting for Realistic Renderingcited by 3
  11. 2024Hybrid Fourier Score Distillation for Efficient One Image to 3D Object Generationcited by 2
  12. 2024Gaussian Splatting in Mirrors: Reflection-Aware Rendering via Virtual Camera Optimizationcited by 2
6 more
  1. 2025Interpretable Single-View 3D Gaussian Splatting using Unsupervised Hierarchical Disentangled Representation Learningcited by 1
  2. 2026Practical High-Fidelity Novel-View Synthesis of Mounted Lepidopteracited by 0
  3. 2026PhysMirror: Physics-Aware Mirror Object Generationcited by 0
  4. 2026PanoLess: Environment Reconstruction from Partial Reflective Viewscited by 0
  5. 2026MVMD: A Multi-View Approach for Enhanced Mirror Detectioncited by 0
  6. 2026PhysReflect: Geometry and Perception Guided Diffusion for Physically-Plausible Mirror Reflectionscited by 0