mlsanityData to 14 Oct 2026

SpeeDe3DGS: Speedy Deformable 3D Gaussian Splatting with Temporal Pruning and Motion Grouping

arXiv 2506.07917 ↗First posted 9 Jun 2025cs.GR cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

Dynamic extensions of 3D Gaussian Splatting (3DGS) achieve high-quality reconstructions through neural motion fields, but per-Gaussian neural inference makes these models computationally expensive. Building on DeformableGS, we introduce Speedy Deformable 3D Gaussian Splatting (SpeeDe3DGS), which bridges this efficiency-fidelity gap through three complementary modules: Temporal Sensitivity Pruning (TSP) removes low-impact Gaussians via temporally aggregated sensitivity analysis, Temporal Sensitivity Sampling (TSS) perturbs timestamps to suppress floaters and improve temporal coherence, and GroupFlow distills the learned deformation field into shared SE(3) transformations for efficient groupwise motion. On the 50 dynamic scenes in MonoDyGauBench, integrating TSP and TSS into DeformableGS accelerates rendering by 6.78× on average while maintaining neural-field fidelity and using 10× fewer primitives. Adding GroupFlow culminates in 13.71× faster rendering and 2.53× shorter training, surpassing all baselines in speed while preserving superior image quality.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 53 of its 60 references that are in the map. First posted on arXiv 9 Jun 2025.

Builds on

53 of 60 references.

References · 53

  1. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
  2. 2020D-NeRF: Neural Radiance Fields for Dynamic Scenescited by 1,465
  3. 2020Nerfies: Deformable Neural Radiance Fieldscited by 1,198
  4. 20234D Gaussian Splatting for Real-Time Dynamic Scene Renderingcited by 1,157
  5. 2023Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstructioncited by 759
  6. 2023K-Planes: Explicit Radiance Fields in Space, Time, and Appearancecited by 746
  7. 2023Dynamic 3D Gaussians: Tracking by Persistent Dynamic View Synthesiscited by 737
  8. 2023HexPlane: A Fast Representation for Dynamic Scenescited by 587
  9. 2023Real-time Photorealistic Dynamic Scene Representation and Rendering with 4D Gaussian Splattingcited by 476
  10. 2023LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPScited by 436
  11. 2021Dynamic View Synthesis from Dynamic Monocular Videocited by 420
  12. 2023Compact 3D Gaussian Representation for Radiance Fieldcited by 372
38 more
  1. 2023SC-GS: Sparse-Controlled Gaussian Splatting for Editable Dynamic Scenescited by 347
  2. 2022Fast Dynamic Radiance Fields with Time-Aware Neural Voxelscited by 346
  3. 2023Spacetime Gaussian Feature Splatting for Real-Time Dynamic View Synthesiscited by 344
  4. 2020Neural Radiance Flow for 4D View Synthesis and Video Processingcited by 270
  5. 2024Shape of Motion: 4D Reconstruction from a Single Videocited by 250
  6. 2024Mini-Splatting: Representing Scenes with a Constrained Number of Gaussianscited by 213
  7. 2023Gaussian-Flow: 4D Reconstruction with Dynamic 3D Gaussian Particlecited by 211
  8. 2022Monocular Dynamic View Synthesis: A Reality Checkcited by 200
  9. 2023EAGLES: Efficient Accelerated 3D Gaussians with Lightweight EncodingScited by 196
  10. 2024MoSca: Dynamic Gaussian Fusion from Casual Videos via 4D Motion Scaffoldscited by 179
  11. 2024HUGS: Holistic Urban 3D Scene Understanding via Gaussian Splattingcited by 142
  12. 2024Reducing the Memory Footprint of 3D Gaussian Splattingcited by 133
  13. 2023DynMF: Neural Motion Factorization for Real-time Dynamic View Synthesis with 3D Gaussian Splattingcited by 124
  14. 2024RadSplat: Radiance Field-Informed Gaussian Splatting for Robust Real-Time Rendering with 900+ FPScited by 113
  15. 2023NeRF-DS: Neural Radiance Fields for Dynamic Specular Objectscited by 111
  16. 2022DeVRF: Fast Deformable Voxel Radiance Fields for Dynamic Scenescited by 103
  17. 2024PUP 3D-GS: Principled Uncertainty Pruning for 3D Gaussian Splattingcited by 95
  18. 2024Speedy-Splat: Fast 3D Gaussian Splatting with Sparse Pixels and Sparse Primitivescited by 95
  19. 2021Neural Trajectory Fields for Dynamic Novel View Synthesiscited by 86
  20. 2024CompGS: Efficient 3D Scene Representation via Compressed Gaussian Splattingcited by 82
  21. 2023FisherRF: Active View Selection and Uncertainty Quantification for Radiance Fields using Fisher Informationcited by 64
  22. 2024SpotlessSplats: Ignoring Distractors in 3D Gaussian Splattingcited by 61
  23. 2023A Compact Dynamic 3D Gaussian Representation for Real-Time Dynamic View Synthesiscited by 59
  24. 2024LP-3DGS: Learning to Prune 3D Gaussian Splattingcited by 55
  25. 2023Representing Volumetric Videos as Dynamic MLP Mapscited by 51
  26. 2024Trimming the Fat: Efficient Compression of 3D Gaussian Splats through Pruningcited by 47
  27. 2024MEGA: Memory-Efficient 4D Gaussian Splatting for Dynamic Scenescited by 47
  28. 2024Superpoint Gaussian Splatting for Real-Time High-Fidelity Dynamic Scene Reconstructioncited by 45
  29. 2022Neural Deformable Voxel Grid for Fast Optimization of Dynamic View Synthesiscited by 43
  30. 2023Masked Space-Time Hash Encoding for Efficient Dynamic Scene Reconstructioncited by 43
  31. 2025Swift4D:Adaptive divide-and-conquer Gaussian Splatting for compact and efficient reconstruction of dynamic scenecited by 42
  32. 2023Strivec: Sparse Tri-Vector Radiance Fieldscited by 28
  33. 2023ResFields: Residual Neural Fields for Spatiotemporal Signalscited by 27
  34. 2024DAS3R: Dynamics-Aware Gaussian Splatting for Static Scene Reconstructioncited by 26
  35. 2024LGS: A Light-weight 4D Gaussian Splatting for Efficient Surgical Scene Reconstructioncited by 21
  36. 2024ELMGS: Enhancing memory and computation scaLability through coMpression for 3D Gaussian Splattingcited by 20
  37. 2025POp-GS: Next Best View in 3D-Gaussian Splatting with P-Optimalitycited by 18
  38. 2025DeGauss: Dynamic-Static Decomposition with Gaussian Splatting for Distractor-free 3D Reconstructioncited by 16

50 most cited of 53 All 53 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 5.

5 papers.

  1. 2026Multi4D: High-Fidelity Dynamic Gaussian Splatting via Multi-Level Competitive Allocationcited by 0
  2. 2026Grassmannian Splatting I: Moving rank-2 Spacetime Surfels for Dynamic Scene Renderingcited by 0
  3. 2026Towards Alias-Free 4D Gaussian Representations with Motion-Aware Filteringcited by 0
  4. 2026From Splats to Silicon: Rethinking Computational Efficiency of 3DGScited by 0
  5. 2026Gaussian Splatting for Real-Time Scene Reconstruction: Methods, Systems, and Trade-offscited by 0