mlsanityData to 14 Oct 2026

4DSTR: Advancing Generative 4D Gaussians with Spatial-Temporal Rectification for High-Quality and Consistent 4D Generation

arXiv 2511.07241 ↗First posted 10 Nov 2025cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

Remarkable advances in recent 2D image and 3D shape generation have induced a significant focus on dynamic 4D content generation. However, previous 4D generation methods commonly struggle to maintain spatial-temporal consistency and adapt poorly to rapid temporal variations, due to the lack of effective spatial-temporal modeling. To address these problems, we propose a novel 4D generation network called 4DSTR, which modulates generative 4D Gaussian Splatting with spatial-temporal rectification. Specifically, temporal correlation across generated 4D sequences is designed to rectify deformable scales and rotations and guarantee temporal consistency. Furthermore, an adaptive spatial densification and pruning strategy is proposed to address significant temporal variations by dynamically adding or deleting Gaussian points with the awareness of their pre-frame movements. Extensive experiments demonstrate that our 4DSTR achieves state-of-the-art performance in video-to-4D generation, excelling in reconstruction quality, spatial-temporal consistency, and adaptation to rapid temporal movements.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 35 of its 48 references that are in the map. First posted on arXiv 10 Nov 2025.

Builds on

35 of 48 references.

References · 35

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
  4. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,718
  5. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,356
  6. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,057
  7. 2023Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasetscited by 2,581
  8. 20234D Gaussian Splatting for Real-Time Dynamic Scene Renderingcited by 1,157
  9. 2023K-Planes: Explicit Radiance Fields in Space, Time, and Appearancecited by 746
  10. 2023Zero123++: a Single Image to Consistent Multi-view Diffusion Base Modelcited by 521
  11. 2021MOTR: End-to-End Multiple-Object Tracking with Transformercited by 381
  12. 2023Text-To-4D Dynamic Scene Generationcited by 205
23 more
  1. 2023Align Your Gaussians: Text-to-4D with Dynamic 3D Gaussians and Composed Diffusion Modelscited by 169
  2. 2023Consistent4D: Consistent 360deg Dynamic Object Generation from Monocular Videocited by 125
  3. 20234DGen: Grounded 4D Content Generation with Spatial-temporal Consistencycited by 117
  4. 20244Diffusion: Multi-view Video Diffusion Model for 4D Generationcited by 104
  5. 2024STAG4D: Spatial-Temporal Anchored Generative 4D Gaussianscited by 102
  6. 2024ReconDreamer: Crafting World Models for Driving Scene Reconstruction via Online Restorationcited by 89
  7. 2024TC4D: Trajectory-Conditioned Text-to-4D Generationcited by 77
  8. 2024Point Mamba: A Novel Point Cloud Backbone Based on State Space Model with Octree-Based Ordering Strategycited by 73
  9. 2022PSTNet: Point Spatio-Temporal Convolution on Point Cloud Sequencescited by 68
  10. 2024SC4D: Sparse-Controlled Video-to-4D Generation and Motion Transfercited by 61
  11. 2024DreamMesh4D: Video-to-4D Generation with Sparse-Controlled Gaussian-Mesh Hybrid Representationcited by 58
  12. 2023LAformer: Trajectory Prediction for Autonomous Driving with Lane-Aware Scene Constraintscited by 53
  13. 20244Real-Video: Learning Generalizable Photo-Realistic 4D Video Diffusioncited by 27
  14. 2022GATraj: A Graph- and Attention-based Multi-Agent Trajectory Prediction Modelcited by 26
  15. 2024DVLO: Deep Visual-LiDAR Odometry with Local-to-Global Feature Fusion and Bi-Directional Structure Alignmentcited by 26
  16. 2025HumanDreamer: Generating Controllable Human-Motion Videos via Decoupled Generationcited by 19
  17. 2025MVTokenFlow: High-quality 4D Content Generation using Multiview Token Flowcited by 17
  18. 20243DSFLabelling: Boosting 3D Scene Flow Estimation by Pseudo Auto-labellingcited by 16
  19. 2025TopoLiDM: Topology-Aware LiDAR Diffusion Models for Interpretable and Realistic LiDAR Point Cloud Generationcited by 7
  20. 2023Tracing the Influence of Predecessors on Trajectory Predictioncited by 4
  21. 2024NeuroGauss4D-PCI: 4D Neural Fields and Gaussian Deformation Fields for Point Cloud Interpolationcited by 3
  22. 2025DVLO4D: Deep Visual-Lidar Odometry with Sparse Spatial-temporal Fusioncited by 3
  23. 2023An End-to-End Framework of Road User Detection, Tracking, and Prediction from Monocular Imagescited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 5.

5 papers.

  1. 2026DriveVA: Video Action Models are Zero-Shot Driverscited by 23
  2. 2026MemoBench: Benchmarking World Modeling in Dynamically Changing Environmentscited by 12
  3. 2026RegFormer++: An Efficient Large-Scale 3D LiDAR Point Registration Network with Projection-Aware 2D Transformercited by 3
  4. 2026RL-ScanIQA: Reinforcement-Learned Scanpaths for Blind 360degImage Quality Assessmentcited by 2
  5. 2026MemReg: Streaming Outdoor LiDAR Point Cloud Registration with Hybrid Memory Bufferscited by 0