mlsanityData to 14 Oct 2026

D-FCGS: Feedforward Compression of Dynamic Gaussian Splatting for Free-Viewpoint Videos

arXiv 2507.05859 ↗First posted 8 Jul 2025cs.CV cs.MMcited by 7

Not on the map. Why?

Abstract (arXiv)

Free-Viewpoint Video (FVV) enables immersive 3D experiences, but efficient compression of dynamic 3D representation remains a major challenge. Existing dynamic 3D Gaussian Splatting methods couple reconstruction with optimization-dependent compression and customized motion formats, limiting generalization and standardization. To address this, we propose D-FCGS, a novel Feedforward Compression framework for Dynamic Gaussian Splatting. Key innovations include: (1) a standardized Group-of-Frames (GoF) structure with I-P coding, leveraging sparse control points to extract inter-frame motion tensors; (2) a dual prior-aware entropy model that fuses hyperprior and spatial-temporal priors for accurate rate estimation; (3) a control-point-guided motion compensation mechanism and refinement network to enhance view-consistent fidelity. Trained on Gaussian frames derived from multi-view videos, D-FCGS generalizes across diverse scenes in a zero-shot fashion. Experiments show that it matches the rate-distortion performance of optimization-based methods, achieving over 17 times compression compared to the baseline while preserving visual quality across viewpoints. This work advances feedforward compression of dynamic 3DGS, facilitating scalable FVV transmission and storage for immersive applications.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 54 of its 70 references that are in the map. First posted on arXiv 8 Jul 2025.

Builds on

54 of 70 references.

References · 54

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  3. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
  4. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,723
  5. 20234D Gaussian Splatting for Real-Time Dynamic Scene Renderingcited by 1,157
  6. 2018Variational image compression with a scale hyperpriorcited by 935
  7. 2020Accelerating 3D Deep Learning with PyTorch3Dcited by 784
  8. 2023Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstructioncited by 759
  9. 2023K-Planes: Explicit Radiance Fields in Space, Time, and Appearancecited by 746
  10. 2023Dynamic 3D Gaussians: Tracking by Persistent Dynamic View Synthesiscited by 737
  11. 2016End-to-end Optimized Image Compressioncited by 696
  12. 2023Scaffold-GS: Structured 3D Gaussians for View-Adaptive Renderingcited by 695
38 more
  1. 2018Joint Autoregressive and Hierarchical Priors for Learned Image Compressioncited by 664
  2. 2020Learned Image Compression with Discretized Gaussian Mixture Likelihoods and Attention Modulescited by 590
  3. 2023Real-time Photorealistic Dynamic Scene Representation and Rendering with 4D Gaussian Splattingcited by 476
  4. 2023LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPScited by 436
  5. 2023Compact 3D Gaussian Representation for Radiance Fieldcited by 372
  6. 2023SC-GS: Sparse-Controlled Gaussian Splatting for Editable Dynamic Scenescited by 347
  7. 2023Spacetime Gaussian Feature Splatting for Real-Time Dynamic View Synthesiscited by 344
  8. 2023Gaussian-Flow: 4D Reconstruction with Dynamic 3D Gaussian Particlecited by 211
  9. 2024HAC: Hash-grid Assisted Context for 3D Gaussian Splatting Compressioncited by 209
  10. 2023EAGLES: Efficient Accelerated 3D Gaussians with Lightweight EncodingScited by 196
  11. 20244D-Rotor Gaussian Splatting: Towards Efficient Novel View Synthesis for Dynamic Scenescited by 189
  12. 2023HyperReel: High-Fidelity 6-DoF Video with Ray-Conditioned Samplingcited by 174
  13. 20243DGStream: On-the-Fly Training of 3D Gaussians for Efficient Streaming of Photo-Realistic Free-Viewpoint Videoscited by 160
  14. 2023Compact 3D Scene Representation via Self-Organizing Gaussian Gridscited by 151
  15. 2022Streaming Radiance Fields for 3D Video Synthesiscited by 119
  16. 20243D Geometry-aware Deformable Gaussian Splatting for Dynamic View Synthesiscited by 109
  17. 2024ContextGS: Compact 3D Gaussian Splatting with Anchor Level Context Modelcited by 102
  18. 2024Motion-aware 3D Gaussian Splatting for Efficient Dynamic Scene Reconstructioncited by 100
  19. 2024CompGS: Efficient 3D Scene Representation via Compressed Gaussian Splattingcited by 82
  20. 2023Neural Residual Radiance Fields for Streamably Free-Viewpoint Videoscited by 77
  21. 2024End-to-End Rate-Distortion Optimized 3D Gaussian Representationcited by 75
  22. 2023A Compact Dynamic 3D Gaussian Representation for Real-Time Dynamic View Synthesiscited by 59
  23. 2024Representing Long Volumetric Video with Temporal Gaussian Hierarchycited by 58
  24. 2024Fast Feedforward 3D Gaussian Splatting Compressioncited by 52
  25. 2024Grid4D: 4D Decomposed Hash Encoding for High-Fidelity Dynamic Gaussian Splattingcited by 49
  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. 2025Swift4D:Adaptive divide-and-conquer Gaussian Splatting for compact and efficient reconstruction of dynamic scenecited by 42
  29. 2025CAT-3DGS: A Context-Adaptive Triplane Approach to Rate-Distortion-Optimized 3DGS Compressioncited by 41
  30. 2025Instant Gaussian Stream: Fast and Generalizable Streaming of Dynamic Scene Reconstruction via Gaussian Splattingcited by 36
  31. 2024Dynamic 3D Gaussian Fields for Urban Areascited by 35
  32. 2024HEMGS: A Hybrid Entropy Model for 3D Gaussian Splatting Data Compressioncited by 31
  33. 2025MoDec-GS: Global-to-Local Motion Decomposition and Temporal Interval Adjustment for Compact Dynamic 3D Gaussian Splattingcited by 30
  34. 2024V^3: Viewing Volumetric Videos on Mobiles via Streamable 2D Dynamic Gaussianscited by 29
  35. 2024QUEEN: QUantized Efficient ENcoding of Dynamic Gaussians for Streaming Free-viewpoint Videoscited by 25
  36. 2025Compression of 3D Gaussian Splatting with Optimized Feature Planes and Standard Video Codecscited by 25
  37. 2024Implicit Gaussian Splatting with Efficient Multi-Level Tri-Plane Representationcited by 21
  38. 2024JointRF: End-to-End Joint Optimization for Dynamic Neural Radiance Field Representation and Compressioncited by 13

50 most cited of 54 All 54 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 7.

7 papers.

  1. 2026Lightweight High-Fidelity Low-Bitrate Talking Face Compression for 3D Video Conferencecited by 0
  2. 2026QuARC-GS: Quantized Anchored Residual Coding for Compact Dynamic Scene Streaming with Gaussian Splattingcited by 0
  3. 2026M3ISR: A Multi-Modal Multi-View Benchmark for 3D/4D Gaussian Splatting and Feedforward Compressioncited by 0
  4. 2026Robust, Estimator-Agnostic Dynamic 3DGS Compressioncited by 0
  5. 2026FeCoSplat: Feedback-Guided Compression for Feed-Forward 3D Gaussian Splattingcited by 0
  6. 2026Gaussian Splatting-based Volumetric Video Compression with Sparse 4D Anchorscited by 0
  7. 2026TETRIS-4DGS: Efficient Post-Training Compression of 4D Gaussian Splattingcited by 0