mlsanityData to 7 Oct 2026

World from Motion: Generative Dynamic Gaussian Reconstruction from Monocular Video

arXiv 2607.01202 ↗First posted 1 Jul 2026cs.CV cs.AI cs.GRcited by 0

Not on the map. Why?

Abstract (arXiv)

We present World from Motion, a method for generating freely renderable dynamic 3D Gaussian representations from monocular videos. Our approach conditions a video model on dense, pixel-aligned renderings that encode appearance, geometry, and 3D scene motion along both input and target camera trajectories to correct rendering artifacts and fill in missing regions from an initial reconstruction. To train this model, we construct a dataset of aligned multiview video pairs and dynamic 3DGS representations, with simulated artifacts characteristic of monocular reconstruction. At test time, we distill the model's generations, including newly observed regions and motions, back into a single consistent, high-quality dynamic 3DGS, improving both novel-view synthesis and the underlying 3D motion. Our method sets a new state of the art in 4D reconstruction and seamlessly generalizes to in-the-wild videos with large viewpoint changes and dynamic motions.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 58 of its 70 references that are in the map. First posted on arXiv 1 Jul 2026.

Builds on

58 of 70 references.

References · 58

  1. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
  2. 2022Scalable Diffusion Models with Transformerscited by 5,931
  3. 2022Classifier-Free Diffusion Guidancecited by 5,717
  4. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,550
  5. 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 3,006
  6. 2020RAFT: Recurrent All-Pairs Field Transforms for Optical Flowcited by 2,385
  7. 2021SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equationscited by 1,903
  8. 2023DUSt3R: Geometric 3D Vision Made Easycited by 1,526
  9. 2025VGGT: Visual Geometry Grounded Transformercited by 1,475
  10. 2023Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Modelscited by 1,465
  11. 2020D-NeRF: Neural Radiance Fields for Dynamic Scenescited by 1,459
  12. 2023ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillationcited by 1,207
38 more
  1. 2020Nerfies: Deformable Neural Radiance Fieldscited by 1,194
  2. 2015ORB-SLAM: a Versatile and Accurate Monocular SLAM Systemcited by 983
  3. 2020Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenescited by 750
  4. 2023Dynamic 3D Gaussians: Tracking by Persistent Dynamic View Synthesiscited by 731
  5. 2021DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Camerascited by 673
  6. 2025Depth Anything 3: Recovering the Visual Space from Any Viewscited by 626
  7. 2023CoTracker: It is Better to Track Togethercited by 516
  8. 2025VACE: All-in-One Video Creation and Editingcited by 467
  9. 2024CameraCtrl: Enabling Camera Control for Text-to-Video Generationcited by 448
  10. 2024MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motioncited by 431
  11. 2024ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesiscited by 392
  12. 2022Fast Dynamic Radiance Fields with Time-Aware Neural Voxelscited by 344
  13. 2025GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Controlcited by 325
  14. 2023ReconFusion: 3D Reconstruction with Diffusion Priorscited by 317
  15. 2023TAPIR: Tracking Any Point with per-frame Initialization and temporal Refinementcited by 281
  16. 2025ReCamMaster: Camera-Controlled Generative Rendering from A Single Videocited by 278
  17. 2024Shape of Motion: 4D Reconstruction from a Single Videocited by 247
  18. 2024MegaSaM: Accurate, Fast, and Robust Structure and Motion from Casual Dynamic Videoscited by 224
  19. 2022SparseFusion: Distilling View-conditioned Diffusion for 3D Reconstructioncited by 216
  20. 2022Monocular Dynamic View Synthesis: A Reality Checkcited by 199
  21. 2023Robust Dynamic Radiance Fieldscited by 193
  22. 2024MoSca: Dynamic Gaussian Fusion from Casual Videos via 4D Motion Scaffoldscited by 177
  23. 2025ViPE: Video Pose Engine for 3D Geometric Perceptioncited by 162
  24. 2024CAT4D: Create Anything in 4D with Multi-View Video Diffusion Modelscited by 160
  25. 2025Difix3D+: Improving 3D Reconstructions with Single-Step Diffusion Modelscited by 160
  26. 2023DreamCraft3D: Hierarchical 3D Generation with Bootstrapped Diffusion Priorcited by 157
  27. 2025Video World Models with Long-term Spatial Memorycited by 124
  28. 2025TrajectoryCrafter: Redirecting Camera Trajectory for Monocular Videos via Diffusion Modelscited by 120
  29. 2024BootsTAP: Bootstrapped Training for Tracking-Any-Pointcited by 115
  30. 2024Eliminating Oversaturation and Artifacts of High Guidance Scales in Diffusion Modelscited by 107
  31. 20243DGS-Enhancer: Enhancing Unbounded 3D Gaussian Splatting with View-consistent 2D Diffusion Priorscited by 106
  32. 2025VMem: Consistent Interactive Video Scene Generation with Surfel-Indexed View Memorycited by 102
  33. 2024Dynamic Gaussian Marbles for Novel View Synthesis of Casual Monocular Videoscited by 96
  34. 2025WildGS-SLAM: Monocular Gaussian Splatting SLAM in Dynamic Environmentscited by 48
  35. 20254DGT: Learning a 4D Gaussian Transformer Using Real-World Monocular Videoscited by 46
  36. 2026NeoVerse: Enhancing 4D World Model with in-the-wild Monocular Videoscited by 39
  37. 2023DynPoint: Dynamic Neural Point For View Synthesiscited by 37
  38. 2025Any4D: Unified Feed-Forward Metric 4D Reconstructioncited by 32

50 most cited of 58 All 58 (JSON)

Built on by

Not cited yet.