mlsanityData to 14 Oct 2026

Efficient Density Control for 3D Gaussian Splatting

arXiv 2411.10133 ↗First posted 15 Nov 2024cs.CVcited by 13

Not on the map. Why?

Abstract (arXiv)

3D Gaussian Splatting (3DGS) has demonstrated outstanding performance in novel view synthesis, achieving a balance between rendering quality and real-time performance. 3DGS employs Adaptive Density Control (ADC) to increase the number of Gaussians. However, the clone and split operations within ADC are not sufficiently efficient, impacting optimization speed and detail recovery. Additionally, overfitted Gaussians that affect rendering quality may exist, and the original ADC is unable to remove them. To address these issues, we propose two key innovations: (1) Long-Axis Split, which precisely controls the position, shape, and opacity of child Gaussians to minimize the difference before and after splitting. (2) Recovery-Aware Pruning, which leverages differences in recovery speed after resetting opacity to prune overfitted Gaussians, thereby improving generalization performance. Experimental results show that our method significantly enhances rendering quality. Due to resubmission reasons, this version has been abandoned. The improved version is available at https://xiaobin2001.github.io/improved-gs-web .

Key facts. Cited by 13 papers in the map (data through 14 Oct 2026). Builds on 28 of its 36 references that are in the map. First posted on arXiv 15 Nov 2024.

Builds on

28 of 36 references.

References · 28

  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. 2021Plenoxels: Radiance Fields without Neural Networkscited by 1,613
  6. 20234D Gaussian Splatting for Real-Time Dynamic Scene Renderingcited by 1,157
  7. 2023DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creationcited by 843
  8. 2023Mip-Splatting: Alias-free 3D Gaussian Splattingcited by 667
  9. 2023LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPScited by 436
  10. 2023Gaussian Splatting SLAMcited by 415
  11. 2023SplaTAM: Splat, Track & Map 3D Gaussians for Dense RGB-D SLAMcited by 388
  12. 2023DrivingGaussian: Composite Gaussian Splatting for Surrounding Dynamic Autonomous Driving Scenescited by 360
16 more
  1. 2023Text-to-3D using Gaussian Splattingcited by 299
  2. 2023GS-SLAM: Dense Visual SLAM with 3D Gaussian Splattingcited by 278
  3. 2024Mini-Splatting: Representing Scenes with a Constrained Number of Gaussianscited by 213
  4. 2023Gaussian-Flow: 4D Reconstruction with Dynamic 3D Gaussian Particlecited by 211
  5. 2024Taming 3DGS: High-Quality Radiance Fields with Limited Resourcescited by 204
  6. 2024GaussianPro: 3D Gaussian Splatting with Progressive Propagationcited by 200
  7. 2023EAGLES: Efficient Accelerated 3D Gaussians with Lightweight EncodingScited by 196
  8. 2024SplattingAvatar: Realistic Real-Time Human Avatars with Mesh-Embedded Gaussian Splattingcited by 172
  9. 2023HUGS: Human Gaussian Splatscited by 154
  10. 2024Revising Densification in Gaussian Splattingcited by 128
  11. 2024Pixel-GS: Density Control with Pixel-aware Gradient for 3D Gaussian Splattingcited by 113
  12. 2023Human Gaussian Splatting: Real-time Rendering of Animatable Avatarscited by 105
  13. 2024Spec-Gaussian: Anisotropic View-Dependent Appearance for 3D Gaussian Splattingcited by 74
  14. 2024Deblurring 3D Gaussian Splattingcited by 66
  15. 2024VCR-GauS: View Consistent Depth-Normal Regularizer for Gaussian Surface Reconstructioncited by 50
  16. 2023CG3D: Compositional Generation for Text-to-3D via Gaussian Splattingcited by 42

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 8; 2026: 4.

13 papers.

Sort: