mlsanityData to 7 Oct 2026

EX-4D: EXtreme Viewpoint 4D Video Synthesis via Depth Watertight Mesh

arXiv 2506.05554 ↗First posted 5 Jun 2025cs.CVcited by 32

Not on the map. Why?

Abstract (arXiv)

Generating high-quality camera-controllable videos from monocular input is a challenging task, particularly under extreme viewpoint. Existing methods often struggle with geometric inconsistencies and occlusion artifacts in boundaries, leading to degraded visual quality. In this paper, we introduce EX-4D, a novel framework that addresses these challenges through a Depth Watertight Mesh representation. The representation serves as a robust geometric prior by explicitly modeling both visible and occluded regions, ensuring geometric consistency in extreme camera pose. To overcome the lack of paired multi-view datasets, we propose a simulated masking strategy that generates effective training data only from monocular videos. Additionally, a lightweight LoRA-based video diffusion adapter is employed to synthesize high-quality, physically consistent, and temporally coherent videos. Extensive experiments demonstrate that EX-4D outperforms state-of-the-art methods in terms of physical consistency and extreme-view quality, enabling practical 4D video generation.

Key facts. Cited by 32 papers in the map (data through 7 Oct 2026). Builds on 34 of its 42 references that are in the map. First posted on arXiv 5 Jun 2025.

Builds on

34 of 42 references.

References · 34

  1. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
  2. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,466
  3. 2025Wan: Open and Advanced Large-Scale Video Generative Modelscited by 2,536
  4. 2023Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasetscited by 2,526
  5. 2024CogVideoX: Text-to-Video Diffusion Models with An Expert Transformercited by 2,198
  6. 2023VBench: Comprehensive Benchmark Suite for Video Generative Modelscited by 1,755
  7. 2022Make-A-Video: Text-to-Video Generation without Text-Video Datacited by 1,725
  8. 2024HunyuanVideo: A Systematic Framework For Large Video Generative Modelscited by 1,597
  9. 2023DUSt3R: Geometric 3D Vision Made Easycited by 1,526
  10. 2025VGGT: Visual Geometry Grounded Transformercited by 1,475
  11. 2023AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuningcited by 1,418
  12. 2018MVSNet: Depth Inference for Unstructured Multi-view Stereocited by 780
22 more
  1. 2023MotionCtrl: A Unified and Flexible Motion Controller for Video Generationcited by 568
  2. 2025Continuous 3D Perception Model with Persistent Statecited by 527
  3. 2024CameraCtrl: Enabling Camera Control for Text-to-Video Generationcited by 448
  4. 2020Modular Primitives for High-Performance Differentiable Renderingcited by 439
  5. 2024MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motioncited by 431
  6. 2024OpenVid-1M: A Large-Scale High-Quality Dataset for Text-to-video Generationcited by 332
  7. 2023DragNUWA: Fine-grained Control in Video Generation by Integrating Text, Image, and Trajectorycited by 260
  8. 2024Shape of Motion: 4D Reconstruction from a Single Videocited by 247
  9. 2017GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibriumcited by 208
  10. 2024DepthCrafter: Generating Consistent Long Depth Sequences for Open-world Videoscited by 202
  11. 2025Diffusion as Shader: 3D-aware Video Diffusion for Versatile Video Generation Controlcited by 184
  12. 2023SparseCtrl: Adding Sparse Controls to Text-to-Video Diffusion Modelscited by 172
  13. 2025Step-Video-T2V Technical Report: The Practice, Challenges, and Future of Video Foundation Modelcited by 163
  14. 2024AC3D: Analyzing and Improving 3D Camera Control in Video Diffusion Transformerscited by 151
  15. 2024ReconX: Reconstruct Any Scene from Sparse Views with Video Diffusion Modelcited by 139
  16. 2025TrajectoryCrafter: Redirecting Camera Trajectory for Monocular Videos via Diffusion Modelscited by 120
  17. 2024Generative Camera Dolly: Extreme Monocular Dynamic Novel View Synthesiscited by 116
  18. 2024CamI2V: Camera-Controlled Image-to-Video Diffusion Modelcited by 115
  19. 2024Trajectory Attention for Fine-grained Video Motion Controlcited by 63
  20. 2024GenXD: Generating Any 3D and 4D Scenescited by 49
  21. 2024Splatter a Video: Video Gaussian Representation for Versatile Processingcited by 31
  22. 2024X-Ray: A Sequential 3D Representation For Generationcited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 9; 2026: 23.

32 papers.

Sort:

By area:

  1. 2026NeoVerse: Enhancing 4D World Model with in-the-wild Monocular Videoscited by 39
  2. 2025Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillationcited by 37
  3. 2026WorldStereo: Bridging Camera-Guided Video Generation and Scene Reconstruction via 3D Geometric Memoriescited by 15
  4. 2026Vista4D: Video Reshooting with 4D Point Cloudscited by 15
  5. 2026AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memoriescited by 13
  6. 2025See4D: Pose-Free 4D Generation via Auto-Regressive Video Inpaintingcited by 11
  7. 2025Light-X: Generative 4D Video Rendering with Camera and Illumination Controlcited by 11
  8. 20254DWorldBench: A Comprehensive Evaluation Framework for 3D/4D World Generation Modelscited by 10
  9. 2026LaVR: Scene Latent Conditioned Generative Video Trajectory Re-Rendering using Large 4D Reconstruction Modelscited by 10
  10. 2025EgoReAct: Egocentric Video-Driven 3D Human Reaction Generationcited by 7
  11. 2025MV-Performer: Taming Video Diffusion Model for Faithful and Synchronized Multi-view Performer Synthesiscited by 4
  12. 2025CETCAM: Camera-Controllable Video Generation via Consistent and Extensible Tokenizationcited by 4
20 more
  1. 2026FreeOrbit4D: Training-Free Arbitrary Camera Redirection for Monocular Videos via Foreground-Complete 4D Reconstructioncited by 4
  2. 2026GeoStream: Toward Precise Camera Controlled Streaming Video Generationcited by 4
  3. 2025StereoPilot: Learning Unified and Efficient Stereo Conversion via Generative Priorscited by 3
  4. 2025ChronosObserver: Taming 4D World with Hyperspace Diffusion Samplingcited by 2
  5. 2026CamPilot: Improving Camera Control in Video Diffusion Model with Efficient Camera Reward Feedbackcited by 2
  6. 2026Light4D: Training-Free Extreme Viewpoint 4D Video Relightingcited by 2
  7. 2026Reshoot-Anything: A Self-Supervised Model for In-the-Wild Video Reshootingcited by 2
  8. 2026Embody4D: A Generalist Data Engine for Embodied 4D World Modelingcited by 1
  9. 2026LoViF 2026 The First Challenge on Holistic Quality Assessment for 4D World Model (PhyScore)cited by 1
  10. 2026Real2SAM2Real: Generative 3D Caches as Complementary Context for Video Diffusioncited by 1
  11. 2026Go-with-the-Track: Video Compositing and Motion Control with Point Trackingcited by 1
  12. 2026CameraAnything: Refilming Videos with Arbitrary Camera Controlcited by 1
  13. 2026Beyond Inpainting: Unleash 3D Understanding for Precise Camera-Controlled Video Generationcited by 0
  14. 2026Cinematic Compositing Using Character-Environment-Harmonized Video Generation Modelscited by 0
  15. 2026WarpHammer: Densifying Scene Warps with 3D Object Priors for Extreme View Synthesiscited by 0
  16. 2026PE-Field 4D: Video Generation Models as Canvascited by 0
  17. 2026ScaleVid: Geometry-Aware Video Object Scaling with Mesh-Free Inferencecited by 0
  18. 2026Manifold4D: Denoising on Point Cloud Rendered Manifolds for Video Re-shootingcited by 0
  19. 2026World in World: Explore the World with World Modelscited by 0
  20. 20264Director: Controlling Video World Models with Rigid 3D Geometrycited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024CAT4D: Create Anything in 4D with Multi-View Video Diffusion Models
  2. 2026Alignment Is All You Need For X-to-4D Generation
  3. 2025AdaViewPlanner: Adapting Video Diffusion Models for Viewpoint Planning in 4D Scenes
  4. 2023Make-It-4D: Synthesizing a Consistent Long-Term Dynamic Scene Video from a Single Image
  5. 2026Full-4D: Generating Full-Scope 4D Scenes from a Single-View Video
  6. 2026UniWorld-View: Large-Baseline View Synthesis via Video Diffusion Models
  7. 2025SWiT-4D: Sliding-Window Transformer for Lossless and Parameter-Free Temporal 4D Generation
  8. 20254DVD: Cascaded Dense-view Video Diffusion Model for High-quality 4D Content Generation