RetimeGS: Continuous-Time Reconstruction of 4D Gaussian Splatting
Not on the map. Why?
Abstract (arXiv)
Temporal retiming, the ability to reconstruct and render dynamic scenes at arbitrary timestamps, is crucial for applications such as slow-motion playback, temporal editing, and post-production. However, most existing 4D Gaussian Splatting (4DGS) methods overfit at discrete frame indices but struggle to represent continuous-time frames, leading to ghosting artifacts when interpolating between timestamps. We identify this limitation as a form of temporal aliasing and propose RetimeGS, a simple yet effective 4DGS representation that explicitly defines the temporal behavior of the 3D Gaussian and mitigates temporal aliasing. To achieve smooth and consistent interpolation, we incorporate optical flow-guided initialization and supervision, triple-rendering supervision, and other targeted strategies. Together, these components enable ghost-free, temporally coherent rendering even under large motions. Experiments on datasets featuring fast motion, non-rigid deformation, and severe occlusions demonstrate that RetimeGS achieves superior quality and coherence over state-of-the-art methods.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 45 of its 50 references that are in the map. First posted on arXiv 14 Mar 2026.
Builds on
45 of 50 references.
References · 45
- 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
- 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
- 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
- 2025Wan: Open and Advanced Large-Scale Video Generative Modelscited by 2,536
- 2025VGGT: Visual Geometry Grounded Transformercited by 1,475
- 20234D Gaussian Splatting for Real-Time Dynamic Scene Renderingcited by 1,144
- 2023Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstructioncited by 753
- 2023Dynamic 3D Gaussians: Tracking by Persistent Dynamic View Synthesiscited by 731
- 2023Mip-Splatting: Alias-free 3D Gaussian Splattingcited by 661
- 2023CoTracker: It is Better to Track Togethercited by 516
- 2023Real-time Photorealistic Dynamic Scene Representation and Rendering with 4D Gaussian Splattingcited by 470
- 2023Spacetime Gaussian Feature Splatting for Real-Time Dynamic View Synthesiscited by 341
33 more
- 2023SC-GS: Sparse-Controlled Gaussian Splatting for Editable Dynamic Scenescited by 339
- 2024gsplat: An Open-Source Library for Gaussian Splattingcited by 279
- 2024Shape of Motion: 4D Reconstruction from a Single Videocited by 247
- 20243D Gaussian Splatting as Markov Chain Monte Carlocited by 210
- 20244D-Rotor Gaussian Splatting: Towards Efficient Novel View Synthesis for Dynamic Scenescited by 185
- 2024MoSca: Dynamic Gaussian Fusion from Casual Videos via 4D Motion Scaffoldscited by 177
- 2024SEA-RAFT: Simple, Efficient, Accurate RAFT for Optical Flowcited by 169
- 2022FILM: Frame Interpolation for Large Motioncited by 149
- 2024L4GM: Large 4D Gaussian Reconstruction Modelcited by 143
- 20243D Geometry-aware Deformable Gaussian Splatting for Dynamic View Synthesiscited by 109
- 2024Per-Gaussian Embedding-Based Deformation for Deformable 3D Gaussian Splattingcited by 104
- 2023DNA-Rendering: A Diverse Neural Actor Repository for High-Fidelity Human-centric Renderingcited by 103
- 2024Motion-aware 3D Gaussian Splatting for Efficient Dynamic Scene Reconstructioncited by 100
- 2024GaussianFlow: Splatting Gaussian Dynamics for 4D Content Creationcited by 99
- 2023GauFRe: Gaussian Deformation Fields for Real-time Dynamic Novel View Synthesiscited by 95
- 2024Fully Explicit Dynamic Gaussian Splattingcited by 75
- 2024MotionGS: Exploring Explicit Motion Guidance for Deformable 3D Gaussian Splattingcited by 62
- 2024Representing Long Volumetric Video with Temporal Gaussian Hierarchycited by 58
- 2025FreeTimeGS: Free Gaussian Primitives at Anytime and Anywhere for Dynamic Scene Reconstructioncited by 53
- 2023SWinGS: Sliding Windows for Dynamic 3D Gaussian Splattingcited by 46
- 20254DGT: Learning a 4D Gaussian Transformer Using Real-World Monocular Videoscited by 46
- 2024SplineGS: Robust Motion-Adaptive Spline for Real-Time Dynamic 3D Gaussians from Monocular Videocited by 44
- 2025WAFT: Warping-Alone Field Transforms for Optical Flowcited by 32
- 2024DGD: Dynamic 3D Gaussians Distillationcited by 23
- 2025DGS-LRM: Real-Time Deformable 3D Gaussian Reconstruction From Monocular Videoscited by 14
- 2025Dynamic Scene Reconstruction: Recent Advance in Real-time Rendering and Streamingcited by 8
- 2025AceVFI: A Comprehensive Survey of Advances in Video Frame Interpolationcited by 8
- 2025In-2-4D: Inbetweening from Two Single-View Images to 4D Generationcited by 7
- 2025StreamSplat: Towards Online Dynamic 3D Reconstruction from Uncalibrated Video Streamscited by 7
- 2025Forge4D: Feed-Forward 4D Human Reconstruction and Interpolation from Uncalibrated Sparse-view Videoscited by 7
- 20254DSloMo: 4D Reconstruction for High Speed Scene with Asynchronous Capturecited by 6
- 2024PAPR in Motion: Seamless Point-level 3D Scene Interpolationcited by 5
- 2025Global Motion Corresponder for 3D Point-Based Scene Interpolation under Large Motioncited by 1
Built on by
Not cited yet.