mlsanityData to 7 Oct 2026

Instant4D: 4D Gaussian Splatting in Minutes

arXiv 2510.01119 ↗First posted 1 Oct 2025cs.CVcited by 10

Not on the map. Why?

Abstract (arXiv)

Dynamic view synthesis has seen significant advances, yet reconstructing scenes from uncalibrated, casual video remains challenging due to slow optimization and complex parameter estimation. In this work, we present Instant4D, a monocular reconstruction system that leverages native 4D representation to efficiently process casual video sequences within minutes, without calibrated cameras or depth sensors. Our method begins with geometric recovery through deep visual SLAM, followed by grid pruning to optimize scene representation. Our design significantly reduces redundancy while maintaining geometric integrity, cutting model size to under 10% of its original footprint. To handle temporal dynamics efficiently, we introduce a streamlined 4D Gaussian representation, achieving a 30x speed-up and reducing training time to within two minutes, while maintaining competitive performance across several benchmarks. Our method reconstruct a single video within 10 minutes on the Dycheck dataset or for a typical 200-frame video. We further apply our model to in-the-wild videos, showcasing its generalizability. Our project website is published at https://instant4d.github.io/.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 38 of its 50 references that are in the map. First posted on arXiv 1 Oct 2025.

Builds on

38 of 50 references.

References · 38

  1. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
  2. 2024SAM 2: Segment Anything in Images and Videoscited by 2,784
  3. 2023DUSt3R: Geometric 3D Vision Made Easycited by 1,526
  4. 2020D-NeRF: Neural Radiance Fields for Dynamic Scenescited by 1,459
  5. 2024Depth Anything V2cited by 1,385
  6. 2020Nerfies: Deformable Neural Radiance Fieldscited by 1,194
  7. 20234D Gaussian Splatting for Real-Time Dynamic Scene Renderingcited by 1,144
  8. 2024Grounding Image Matching in 3D with MASt3Rcited by 960
  9. 2023Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstructioncited by 753
  10. 2021DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Camerascited by 673
  11. 2023pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstructioncited by 668
  12. 2025Continuous 3D Perception Model with Persistent Statecited by 527
26 more
  1. 2023Real-time Photorealistic Dynamic Scene Representation and Rendering with 4D Gaussian Splattingcited by 470
  2. 2024MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motioncited by 431
  3. 2024UniDepth: Universal Monocular Metric Depth Estimationcited by 375
  4. 2024Shape of Motion: 4D Reconstruction from a Single Videocited by 247
  5. 2023Track Anything: Segment Anything Meets Videoscited by 230
  6. 2024MegaSaM: Accurate, Fast, and Robust Structure and Motion from Casual Dynamic Videoscited by 224
  7. 2024Taming 3DGS: High-Quality Radiance Fields with Limited Resourcescited by 198
  8. 2023Robust Dynamic Radiance Fieldscited by 193
  9. 2024MoSca: Dynamic Gaussian Fusion from Casual Videos via 4D Motion Scaffoldscited by 177
  10. 2020Novel View Synthesis of Dynamic Scenes with Globally Coherent Depths from a Monocular Cameracited by 166
  11. 2022CroCo: Self-Supervised Pre-training for 3D Vision Tasks by Cross-View Completioncited by 158
  12. 20243DGStream: On-the-Fly Training of 3D Gaussians for Efficient Streaming of Photo-Realistic Free-Viewpoint Videoscited by 156
  13. 2024Dynamic Gaussian Marbles for Novel View Synthesis of Casual Monocular Videoscited by 96
  14. 20234K4D: Real-Time 4D View Synthesis at 4K Resolutioncited by 91
  15. 2022Surface Representation for Point Cloudscited by 84
  16. 2024Fully Explicit Dynamic Gaussian Splattingcited by 75
  17. 2024Towards Realistic Scene Generation with LiDAR Diffusion Modelscited by 67
  18. 2024Representing Long Volumetric Video with Temporal Gaussian Hierarchycited by 58
  19. 2024Grid4D: 4D Decomposed Hash Encoding for High-Fidelity Dynamic Gaussian Splattingcited by 49
  20. 2021Learning Inner-Group Relations on Point Cloudscited by 29
  21. 20244D Gaussian Splatting in the Wild with Uncertainty-Aware Regularizationcited by 28
  22. 2023Fast View Synthesis of Casual Videos with Soup-of-Planescited by 22
  23. 2025MonoFusion: Sparse-View 4D Reconstruction via Monocular Fusioncited by 18
  24. 20244D Gaussian Splatting: Modeling Dynamic Scenes with Native 4D Primitivescited by 15
  25. 2024Template-free Articulated Gaussian Splatting for Real-time Reposable Dynamic View Synthesiscited by 13
  26. 2024RoDyGS: Robust Dynamic Gaussian Splatting for Casual Videoscited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 9.

10 papers.

  1. 2026pySpatial: Generating 3D Visual Programs for Zero-Shot Spatial Reasoningcited by 12
  2. 2026FreeOrbit4D: Training-Free Arbitrary Camera Redirection for Monocular Videos via Foreground-Complete 4D Reconstructioncited by 4
  3. 2025SUCCESS-GS: Survey of Compactness and Compression for Efficient Static and Dynamic Gaussian Splattingcited by 2
  4. 2026ViPS: Video-informed Pose Spaces for Auto-Rigged Meshescited by 2
  5. 2026MoCam: Unified Novel View Synthesis via Structured Denoising Dynamicscited by 2
  6. 2026M^3: Dense Matching Meets Multi-View Foundation Models for Monocular Gaussian Splatting SLAMcited by 1
  7. 2026WildGHand: Learning Anti-Perturbation Gaussian Hand Avatars from Monocular In-the-Wild Videoscited by 0
  8. 2026Geometric 4D Stitching for Grounded 4D Generationcited by 0
  9. 2026Multi4D: High-Fidelity Dynamic Gaussian Splatting via Multi-Level Competitive Allocationcited by 0
  10. 2026Unified Panoramic-Gaussian Representation for Monocular 4D Scene Synthesiscited by 0