mlsanityData to 14 Oct 2026

4DNeX: Feed-Forward 4D Generative Modeling Made Easy

arXiv 2508.13154 ↗First posted 18 Aug 2025cs.CVcited by 34

On the map: Diffusion models → 3D, point cloud and scene generation

Abstract (arXiv)

We present 4DNeX, the first feed-forward framework for generating 4D (i.e., dynamic 3D) scene representations from a single image. In contrast to existing methods that rely on computationally intensive optimization or require multi-frame video inputs, 4DNeX enables efficient, end-to-end image-to-4D generation by fine-tuning a pretrained video diffusion model. Specifically, 1) to alleviate the scarcity of 4D data, we construct 4DNeX-10M, a large-scale dataset with high-quality 4D annotations generated using advanced reconstruction approaches. 2) we introduce a unified 6D video representation that jointly models RGB and XYZ sequences, facilitating structured learning of both appearance and geometry. 3) we propose a set of simple yet effective adaptation strategies to repurpose pretrained video diffusion models for 4D modeling. 4DNeX produces high-quality dynamic point clouds that enable novel-view video synthesis. Extensive experiments demonstrate that 4DNeX outperforms existing 4D generation methods in efficiency and generalizability, offering a scalable solution for image-to-4D modeling and laying the foundation for generative 4D world models that simulate dynamic scene evolution.

Key facts. Cited by 34 papers in the map (data through 14 Oct 2026). Placed in 3D, point cloud and scene generation, one of 14 directions in Diffusion models. Builds on 56 of its 63 references that are in the map. First posted on arXiv 18 Aug 2025.

Builds on

56 of 63 references.

Closest ancestors · 16

Same direction, newest first

  1. 2025Geo4D: Leveraging Video Generators for Geometric 4D Scene Reconstruction10 Apr
  2. 2025GeometryCrafter: Consistent Geometry Estimation for Open-world Videos with Diffusion Priors1 Apr
  3. 2025TrajectoryCrafter: Redirecting Camera Trajectory for Monocular Videos via Diffusion Models7 Mar
  4. 2024SynCamMaster: Synchronizing Multi-Camera Video Generation from Diverse Viewpoints10 Dec
  5. 2024World-consistent Video Diffusion with Explicit 3D Modeling2 Dec
  6. 2024CAT4D: Create Anything in 4D with Multi-View Video Diffusion Models27 Nov
  7. 2024DimensionX: Create Any 3D and 4D Scenes from a Single Image with Controllable Video Diffusion7 Nov
  8. 2024ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesis3 Sep
  9. 20244Real: Towards Photorealistic 4D Scene Generation via Video Diffusion Models11 Jun
  10. 2024EG4D: Explicit Generation of 4D Object without Score Distillation28 May
  11. 2024CAT3D: Create Anything in 3D with Multi-View Diffusion Models16 May
  12. 2024STAG4D: Spatial-Temporal Anchored Generative 4D Gaussians22 Mar
4 more
  1. 20234DGen: Grounded 4D Content Generation with Spatial-temporal Consistency28 Dec
  2. 2023A Unified Approach for Text- and Image-guided 4D Scene Generation28 Nov
  3. 2023Animate124: Animating One Image to 4D Dynamic Scene24 Nov
  4. 2022DreamFusion: Text-to-3D using 2D Diffusion29 Sep

Other references · 40

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 2020Denoising Diffusion Implicit Modelscited by 9,781
  4. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
  5. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
  6. 2022Classifier-Free Diffusion Guidancecited by 5,847
  7. 2022Flow Matching for Generative Modelingcited by 5,702
  8. 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,703
  9. 2025Wan: Open and Advanced Large-Scale Video Generative Modelscited by 2,708
  10. 2022Video Diffusion Modelscited by 2,305
  11. 2024CogVideoX: Text-to-Video Diffusion Models with An Expert Transformercited by 2,261
  12. 2023VBench: Comprehensive Benchmark Suite for Video Generative Modelscited by 1,822
28 more
  1. 2022Imagen Video: High Definition Video Generation with Diffusion Modelscited by 1,778
  2. 2022Make-A-Video: Text-to-Video Generation without Text-Video Datacited by 1,742
  3. 2023DUSt3R: Geometric 3D Vision Made Easycited by 1,567
  4. 2025VGGT: Visual Geometry Grounded Transformercited by 1,539
  5. 2020D-NeRF: Neural Radiance Fields for Dynamic Scenescited by 1,465
  6. 20234D Gaussian Splatting for Real-Time Dynamic Scene Renderingcited by 1,157
  7. 2022CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformerscited by 985
  8. 2024LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creationcited by 739
  9. 2025Continuous 3D Perception Model with Persistent Statecited by 548
  10. 2023DL3DV-10K: A Large-Scale Scene Dataset for Deep Learning-based 3D Visioncited by 537
  11. 2023DynamiCrafter: Animating Open-domain Images with Video Diffusion Priorscited by 471
  12. 2024MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motioncited by 442
  13. 2025GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Controlcited by 341
  14. 2024MegaSaM: Accurate, Fast, and Robust Structure and Motion from Casual Dynamic Videoscited by 228
  15. 2023Text-To-4D Dynamic Scene Generationcited by 205
  16. 2023DreamGaussian4D: Generative 4D Gaussian Splattingcited by 194
  17. 20234D-fy: Text-to-4D Generation Using Hybrid Score Distillation Samplingcited by 185
  18. 2025ViPE: Video Pose Engine for 3D Geometric Perceptioncited by 170
  19. 2024L4GM: Large 4D Gaussian Reconstruction Modelcited by 144
  20. 2023Consistent4D: Consistent 360deg Dynamic Object Generation from Monocular Videocited by 125
  21. 2024Collaborative Video Diffusion: Consistent Multi-video Generation with Camera Controlcited by 117
  22. 20243DTopia-XL: Scaling High-quality 3D Asset Generation via Primitive Diffusioncited by 101
  23. 2024GaussianFlow: Splatting Gaussian Dynamics for 4D Content Creationcited by 100
  24. 2025TesserAct: Learning 4D Embodied World Modelscited by 94
  25. 2025Vchitect-2.0: Parallel Transformer for Scaling Up Video Diffusion Modelscited by 60
  26. 2024GenXD: Generating Any 3D and 4D Scenescited by 50
  27. 2024Efficient4D: Fast Dynamic 3D Object Generation from a Single-view Videocited by 44
  28. 2025Free4D: Tuning-free 4D Scene Generation with Spatial-Temporal Consistencycited by 35

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 9; 2026: 25.

34 papers.

Sort:

By area:

  1. 2026Gen3R: 3D Scene Generation Meets Feed-Forward Reconstructioncited by 31
  2. 2026MVISTA-4D: View-Consistent 4D World Model with Test-Time Action Inference for Robotic Manipulationcited by 17
  3. 2025Simulating the Visual World with Artificial Intelligence: A Roadmapcited by 15
  4. 2025Light-X: Generative 4D Video Rendering with Camera and Illumination Controlcited by 12
  5. 2026Kinema4D: Kinematic 4D World Modeling for Spatiotemporal Embodied Simulationcited by 12
  6. 2026World-R1: Reinforcing 3D Constraints for Text-to-Video Generationcited by 11
  7. 2025One4D: Unified 4D Generation and Reconstruction via Decoupled LoRA Controlcited by 8
  8. 2025EgoX: Egocentric Video Generation from a Single Exocentric Videocited by 8
  9. 2025Diff4Splat: Controllable 4D Scene Generation with Latent Dynamic Reconstruction Modelscited by 7
  10. 2025UnityVideo: Unified Multi-Modal Multi-Task Learning for Enhancing World-Aware Video Generationcited by 7
  11. 2026Feed-Forward 3D Scene Modeling: A Problem-Driven Perspectivecited by 6
  12. 2025WorldReel: 4D Video Generation with Consistent Geometry and Motion Modelingcited by 5
22 more
  1. 2026Motion Attribution for Video Generationcited by 5
  2. 2026Full-4D: Generating Full-Scope 4D Scenes from a Single-View Videocited by 5
  3. 2025Advances in 4D Representation: Geometry, Motion, and Interactioncited by 4
  4. 2026Syn4D: A Multiview Synthetic 4D Datasetcited by 4
  5. 2026MMPhysVideo: Physically Plausible Video Generation Through Joint RGB-Perception Modelingcited by 3
  6. 2026Enhancing Video Physical Consistency via Role-aware Joint Training and Modality-decoupled Denoisingcited by 3
  7. 2025Geometry-Aware Single-Image 4D Synthesis via Dense Trajectory Generationcited by 2
  8. 2026Light4D: Training-Free Extreme Viewpoint 4D Video Relightingcited by 2
  9. 2026PointAction: 3D Points as Universal Action Representations for Robot Controlcited by 2
  10. 2026HiReFF: High-Resolution Feedforward Human Reconstruction from Uncalibrated Sparse-View Videocited by 1
  11. 2026Track the Noise, Move the World:3D-Grounded Motion-Consistent Noise for Controllable Video Generationcited by 1
  12. 2026OctWorld: Long-Range World-Consistent Video Generation with Octree-Based 3D Mappingcited by 1
  13. 2026Divide and Conquer: Decoupled Representation Alignment for Multimodal World Modelscited by 0
  14. 2026ST-Gen4D: Embedding 4D Spatiotemporal Cognition into World Model for 4D Generationcited by 0
  15. 2026Hallo4D: Multi-Modal Hallucination Mitigation for Consistent Spatio-Temporal Generationcited by 0
  16. 2026Beyond Pixels: From Video Priors to 4D Worldscited by 0
  17. 2026Streaming4D: Accelerate 4D World Models via Block-wise Video Generation and Incremental Reconstructioncited by 0
  18. 2026World in World: Explore the World with World Modelscited by 0
  19. 2026From Static to Dynamic: On-Policy Distillation from Image to Video Diffusion Modelscited by 0
  20. 2026FracGen: Learning How Objects Stretch and Tear with Physics-Informed Video Generationcited by 0
  21. 2026WorldAlign: Decoupled 4D Reward for World-Consistent Video Generationcited by 0
  22. 2026GeoFix: Geometry Fixing for 4D Consistent Generationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Diffusion4D: Fast Spatial-temporal Consistent 4D Generation via Video Diffusion Models
  2. 2026Alignment Is All You Need For X-to-4D Generation
  3. 20244Diffusion: Multi-view Video Diffusion Model for 4D Generation
  4. 20254DVD: Cascaded Dense-view Video Diffusion Model for High-quality 4D Content Generation
  5. 2024SV4D: Dynamic 3D Content Generation with Multi-Frame and Multi-View Consistency
  6. 2024Learning Coherent Matrixized Representation in Latent Space for Volumetric 4D Generation
  7. 2026Orthogonal Spatial-temporal Distributional Transfer for 4D Generation
  8. 20254Real-Video-V2: Fused View-Time Attention and Feedforward Reconstruction for 4D Scene Generation