mlsanityData to 14 Oct 2026

Neural Shell Texture Splatting: More Details and Fewer Primitives

arXiv 2507.20200 ↗First posted 27 Jul 2025cs.GR cs.CVcited by 14

Not on the map. Why?

Abstract (arXiv)

Gaussian splatting techniques have shown promising results in novel view synthesis, achieving high fidelity and efficiency. However, their high reconstruction quality comes at the cost of requiring a large number of primitives. We identify this issue as stemming from the entanglement of geometry and appearance in Gaussian Splatting. To address this, we introduce a neural shell texture, a global representation that encodes texture information around the surface. We use Gaussian primitives as both a geometric representation and texture field samplers, efficiently splatting texture features into image space. Our evaluation demonstrates that this disentanglement enables high parameter efficiency, fine texture detail reconstruction, and easy textured mesh extraction, all while using significantly fewer primitives.

Key facts. Cited by 14 papers in the map (data through 14 Oct 2026). Builds on 34 of its 54 references that are in the map. First posted on arXiv 27 Jul 2025.

Builds on

34 of 54 references.

References · 34

  1. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
  2. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,723
  3. 2021Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fieldscited by 2,032
  4. 2021Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fieldscited by 1,964
  5. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,712
  6. 2021Plenoxels: Radiance Fields without Neural Networkscited by 1,613
  7. 20242D Gaussian Splatting for Geometrically Accurate Radiance Fieldscited by 1,076
  8. 2021Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstructioncited by 964
  9. 2022Block-NeRF: Scalable Large Scene Neural View Synthesiscited by 724
  10. 2023Scaffold-GS: Structured 3D Gaussians for View-Adaptive Renderingcited by 695
  11. 2023Mip-Splatting: Alias-free 3D Gaussian Splattingcited by 667
  12. 2021Ref-NeRF: Structured View-Dependent Appearance for Neural Radiance Fieldscited by 575
22 more
  1. 2023Neuralangelo: High-Fidelity Neural Surface Reconstructioncited by 467
  2. 2021Mega-NeRF: Scalable Construction of Large-Scale NeRFs for Virtual Fly-Throughscited by 398
  3. 2023Compact 3D Gaussian Representation for Radiance Fieldcited by 372
  4. 2024HAC: Hash-grid Assisted Context for 3D Gaussian Splatting Compressioncited by 209
  5. 2024Taming 3DGS: High-Quality Radiance Fields with Limited Resourcescited by 204
  6. 2023CompGS: Smaller and Faster Gaussian Splatting with Vector Quantizationcited by 130
  7. 2024Pixel-GS: Density Control with Pixel-aware Gradient for 3D Gaussian Splattingcited by 113
  8. 2021NeuTex: Neural Texture Mapping for Volumetric Neural Renderingcited by 98
  9. 2023Adaptive Shells for Efficient Neural Radiance Field Renderingcited by 69
  10. 2019Learning a Neural 3D Texture Space from 2D Exemplarscited by 53
  11. 2024Texture-GS: Disentangling the Geometry and Texture for 3D Gaussian Splatting Editingcited by 47
  12. 2024DeferredGS: Decoupled and Editable Gaussian Splatting with Deferred Shadingcited by 41
  13. 2024Textured Gaussians for Enhanced 3D Scene Appearance Modelingcited by 40
  14. 2024GStex: Per-Primitive Texturing of 2D Gaussian Splatting for Decoupled Appearance and Geometry Modelingcited by 30
  15. 2024Ref-GS: Directional Factorization for 2D Gaussian Splattingcited by 29
  16. 2024BillBoard Splatting (BBSplat): Learnable Textured Primitives for Novel View Synthesiscited by 25
  17. 2018Deep Surface Light Fieldscited by 23
  18. 2023Compact Neural Graphics Primitives with Learned Hash Probingcited by 19
  19. 2024Deformable Radial Kernel Splattingcited by 17
  20. 2024Textured-GS: Gaussian Splatting with Spatially Defined Color and Opacitycited by 14
  21. 2024SVGS: Enhancing Gaussian Splatting Using Primitives with Spatially Varying Colorscited by 13
  22. 20242DGH: 2D Gaussian-Hermite Splatting for High-quality Rendering and Better Geometry Featurescited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 4; 2026: 10.

14 papers.

Sort:

  1. 2025ConeGS: Error-Guided Densification Using Pixel Cones for Improved Reconstruction With Fewer Primitivescited by 6
  2. 2025Nexels: Neurally-Textured Surfels for Real-Time Novel View Synthesis with Sparse Geometriescited by 4
  3. 2026Neural Harmonic Textures for High-Quality Primitive Based Neural Reconstructioncited by 4
  4. 2026Neural Gabor Splatting: Enhanced Gaussian Splatting with Neural Gabor for High-frequency Surface Reconstructioncited by 2
  5. 2026Depth Peeling for High-Fidelity Gaussian-Enhanced Surfel Renderingcited by 2
  6. 2025Neural Texture Splatting: Expressive 3D Gaussian Splatting for View Synthesis, Geometry, and Dynamic Reconstructioncited by 1
  7. 2025FACT-GS: Frequency-Aligned Complexity-Aware Texture Reparameterization for 2D Gaussian Splattingcited by 1
  8. 2026Hybrid Latents: Geometry-Appearance-Aware Surfel Splattingcited by 1
  9. 2026Heat Kernel Textures: the Geodesic Gaussians That Do Not Splatcited by 1
  10. 2026Learning View-Dependent Splatting Kernelscited by 0
  11. 2026Rectifying Mask via Entropy for Distractor-Free 3DGS in Ambiguous Scenarioscited by 0
  12. 2026Bake It Till You Make It: Ultrafast Spatial Texture-Atlas Splattingcited by 0
2 more
  1. 2026PointGT: Simultaneous Geometry and Texture Editing for Point-Based Representationscited by 0
  2. 2026P-CORE: Self-Supervised Surface Consistency for Point-Based Neural Editingcited by 0