mlsanityData to 14 Oct 2026

Normal-GS: 3D Gaussian Splatting with Normal-Involved Rendering

arXiv 2410.20593 ↗First posted 27 Oct 2024cs.CVcited by 7

Not on the map. Why?

Abstract (arXiv)

Rendering and reconstruction are long-standing topics in computer vision and graphics. Achieving both high rendering quality and accurate geometry is a challenge. Recent advancements in 3D Gaussian Splatting (3DGS) have enabled high-fidelity novel view synthesis at real-time speeds. However, the noisy and discrete nature of 3D Gaussian primitives hinders accurate surface estimation. Previous attempts to regularize 3D Gaussian normals often degrade rendering quality due to the fundamental disconnect between normal vectors and the rendering pipeline in 3DGS-based methods. Therefore, we introduce Normal-GS, a novel approach that integrates normal vectors into the 3DGS rendering pipeline. The core idea is to model the interaction between normals and incident lighting using the physically-based rendering equation. Our approach re-parameterizes surface colors as the product of normals and a designed Integrated Directional Illumination Vector (IDIV). To optimize memory usage and simplify optimization, we employ an anchor-based 3DGS to implicitly encode locally-shared IDIVs. Additionally, Normal-GS leverages optimized normals and Integrated Directional Encoding (IDE) to accurately model specular effects, enhancing both rendering quality and surface normal precision. Extensive experiments demonstrate that Normal-GS achieves near state-of-the-art visual quality while obtaining accurate surface normals and preserving real-time rendering performance.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 43 of its 59 references that are in the map. First posted on arXiv 27 Oct 2024.

Builds on

43 of 59 references.

References · 43

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  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. 20242D Gaussian Splatting for Geometrically Accurate Radiance Fieldscited by 1,076
  7. 2021PlenOctrees for Real-time Rendering of Neural Radiance Fieldscited by 905
  8. 2023DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creationcited by 843
  9. 2023Scaffold-GS: Structured 3D Gaussians for View-Adaptive Renderingcited by 695
  10. 2023pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstructioncited by 684
  11. 2023Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fieldscited by 671
  12. 2023SuGaR: Surface-Aligned Gaussian Splatting for Efficient 3D Mesh Reconstruction and High-Quality Mesh Renderingcited by 616
31 more
  1. 2021Ref-NeRF: Structured View-Dependent Appearance for Neural Radiance Fieldscited by 575
  2. 2024MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Imagescited by 566
  3. 2023LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPScited by 436
  4. 2021Mega-NeRF: Scalable Construction of Large-Scale NeRFs for Virtual Fly-Throughscited by 398
  5. 2023Gaussian Grouping: Segment and Edit Anything in 3D Scenescited by 393
  6. 2023PhysGaussian: Physics-Integrated 3D Gaussians for Generative Dynamicscited by 377
  7. 2023Compact 3D Gaussian Representation for Radiance Fieldcited by 372
  8. 2024DNGaussian: Optimizing Sparse-View 3D Gaussian Radiance Fields with Global-Local Depth Normalizationcited by 256
  9. 2023GaussianDreamer: Fast Generation from Text to 3D Gaussians by Bridging 2D and 3D Diffusion Modelscited by 255
  10. 2023GaussianShader: 3D Gaussian Splatting with Shading Functions for Reflective Surfacescited by 252
  11. 2023Compressed 3D Gaussian Splatting for Accelerated Novel View Synthesiscited by 239
  12. 2023GS-IR: 3D Gaussian Splatting for Inverse Renderingcited by 224
  13. 2024HAC: Hash-grid Assisted Context for 3D Gaussian Splatting Compressioncited by 209
  14. 2024GaussianPro: 3D Gaussian Splatting with Progressive Propagationcited by 200
  15. 2021Point-Based Neural Rendering with Per-View Optimizationcited by 190
  16. 2024High-quality Surface Reconstruction using Gaussian Surfelscited by 161
  17. 2023Compact 3D Scene Representation via Self-Organizing Gaussian Gridscited by 151
  18. 2023Tri-MipRF: Tri-Mip Representation for Efficient Anti-Aliasing Neural Radiance Fieldscited by 143
  19. 2023NeuSG: Neural Implicit Surface Reconstruction with 3D Gaussian Splatting Guidancecited by 138
  20. 2024DN-Splatter: Depth and Normal Priors for Gaussian Splatting and Meshingcited by 138
  21. 2024Recent Advances in 3D Gaussian Splattingcited by 131
  22. 2023F2-NeRF: Fast Neural Radiance Field Training with Free Camera Trajectoriescited by 118
  23. 2022NeILF: Neural Incident Light Field for Physically-based Material Estimationcited by 105
  24. 2023GIR: 3D Gaussian Inverse Rendering for Relightable Scene Factorizationcited by 87
  25. 2024GSDF: 3DGS Meets SDF for Improved Rendering and Reconstructioncited by 83
  26. 2023NeILF++: Inter-Reflectable Light Fields for Geometry and Material Estimationcited by 74
  27. 2024Spec-Gaussian: Anisotropic View-Dependent Appearance for 3D Gaussian Splattingcited by 74
  28. 20243D Gaussian Splatting with Deferred Reflectioncited by 63
  29. 2024DeferredGS: Decoupled and Editable Gaussian Splatting with Deferred Shadingcited by 41
  30. 2024Spectrally Pruned Gaussian Fields with Neural Compensationcited by 33
  31. 2024SAGS: Structure-Aware 3D Gaussian Splattingcited by 21

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 2; 2025: 3; 2026: 2.

7 papers.