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

arXiv: https://arxiv.org/abs/2506.05554 · HTML: https://mlsanity.com/paper/2506.05554/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 42 references that are in the map.
- First posted on arXiv 5 Jun 2025.

## Builds on (most cited first, 30 of 34)

- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets](https://mlsanity.com/paper/2311.15127/) (2023)
- [CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://mlsanity.com/paper/2408.06072/) (2024)
- [VBench: Comprehensive Benchmark Suite for Video Generative Models](https://mlsanity.com/paper/2311.17982/) (2023)
- [Make-A-Video: Text-to-Video Generation without Text-Video Data](https://mlsanity.com/paper/2209.14792/) (2022)
- [HunyuanVideo: A Systematic Framework For Large Video Generative Models](https://mlsanity.com/paper/2412.03603/) (2024)
- [DUSt3R: Geometric 3D Vision Made Easy](https://mlsanity.com/paper/2312.14132/) (2023)
- [VGGT: Visual Geometry Grounded Transformer](https://mlsanity.com/paper/2503.11651/) (2025)
- [AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning](https://mlsanity.com/paper/2307.04725/) (2023)
- [MVSNet: Depth Inference for Unstructured Multi-view Stereo](https://mlsanity.com/paper/1804.02505/) (2018)
- [MotionCtrl: A Unified and Flexible Motion Controller for Video Generation](https://mlsanity.com/paper/2312.03641/) (2023)
- [Continuous 3D Perception Model with Persistent State](https://mlsanity.com/paper/2501.12387/) (2025)
- [CameraCtrl: Enabling Camera Control for Text-to-Video Generation](https://mlsanity.com/paper/2404.02101/) (2024)
- [MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion](https://mlsanity.com/paper/2410.03825/) (2024)
- [Modular Primitives for High-Performance Differentiable Rendering](https://mlsanity.com/paper/2011.03277/) (2020)
- [OpenVid-1M: A Large-Scale High-Quality Dataset for Text-to-video Generation](https://mlsanity.com/paper/2407.02371/) (2024)
- [DragNUWA: Fine-grained Control in Video Generation by Integrating Text, Image, and Trajectory](https://mlsanity.com/paper/2308.08089/) (2023)
- [Shape of Motion: 4D Reconstruction from a Single Video](https://mlsanity.com/paper/2407.13764/) (2024)
- [GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium](https://mlsanity.com/paper/1706.08500/) (2017)
- [DepthCrafter: Generating Consistent Long Depth Sequences for Open-world Videos](https://mlsanity.com/paper/2409.02095/) (2024)
- [Diffusion as Shader: 3D-aware Video Diffusion for Versatile Video Generation Control](https://mlsanity.com/paper/2501.03847/) (2025)
- [SparseCtrl: Adding Sparse Controls to Text-to-Video Diffusion Models](https://mlsanity.com/paper/2311.16933/) (2023)
- [Step-Video-T2V Technical Report: The Practice, Challenges, and Future of Video Foundation Model](https://mlsanity.com/paper/2502.10248/) (2025)
- [AC3D: Analyzing and Improving 3D Camera Control in Video Diffusion Transformers](https://mlsanity.com/paper/2411.18673/) (2024)
- [ReconX: Reconstruct Any Scene from Sparse Views with Video Diffusion Model](https://mlsanity.com/paper/2408.16767/) (2024)
- [TrajectoryCrafter: Redirecting Camera Trajectory for Monocular Videos via Diffusion Models](https://mlsanity.com/paper/2503.05638/) (2025)
- [CamI2V: Camera-Controlled Image-to-Video Diffusion Model](https://mlsanity.com/paper/2410.15957/) (2024)
- [Generative Camera Dolly: Extreme Monocular Dynamic Novel View Synthesis](https://mlsanity.com/paper/2405.14868/) (2024)

## Built on by (most cited first, 30 of 32)

- [NeoVerse: Enhancing 4D World Model with in-the-wild Monocular Videos](https://mlsanity.com/paper/2601.00393/) (2026)
- [Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation](https://mlsanity.com/paper/2509.19296/) (2025)
- [WorldStereo: Bridging Camera-Guided Video Generation and Scene Reconstruction via 3D Geometric Memories](https://mlsanity.com/paper/2603.02049/) (2026)
- [Vista4D: Video Reshooting with 4D Point Clouds](https://mlsanity.com/paper/2604.21915/) (2026)
- [AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories](https://mlsanity.com/paper/2602.14941/) (2026)
- [See4D: Pose-Free 4D Generation via Auto-Regressive Video Inpainting](https://mlsanity.com/paper/2510.26796/) (2025)
- [Light-X: Generative 4D Video Rendering with Camera and Illumination Control](https://mlsanity.com/paper/2512.05115/) (2025)
- [4DWorldBench: A Comprehensive Evaluation Framework for 3D/4D World Generation Models](https://mlsanity.com/paper/2511.19836/) (2025)
- [LaVR: Scene Latent Conditioned Generative Video Trajectory Re-Rendering using Large 4D Reconstruction Models](https://mlsanity.com/paper/2601.14674/) (2026)
- [EgoReAct: Egocentric Video-Driven 3D Human Reaction Generation](https://mlsanity.com/paper/2512.22808/) (2025)
- [FreeOrbit4D: Training-Free Arbitrary Camera Redirection for Monocular Videos via Foreground-Complete 4D Reconstruction](https://mlsanity.com/paper/2601.18993/) (2026)
- [CETCAM: Camera-Controllable Video Generation via Consistent and Extensible Tokenization](https://mlsanity.com/paper/2512.19020/) (2025)
- [MV-Performer: Taming Video Diffusion Model for Faithful and Synchronized Multi-view Performer Synthesis](https://mlsanity.com/paper/2510.07190/) (2025)
- [CamPilot: Improving Camera Control in Video Diffusion Model with Efficient Camera Reward Feedback](https://mlsanity.com/paper/2601.16214/) (2026)
- [GeoStream: Toward Precise Camera Controlled Streaming Video Generation](https://mlsanity.com/paper/2606.15162/) (2026)
- [StereoPilot: Learning Unified and Efficient Stereo Conversion via Generative Priors](https://mlsanity.com/paper/2512.16915/) (2025)
- [ChronosObserver: Taming 4D World with Hyperspace Diffusion Sampling](https://mlsanity.com/paper/2512.01481/) (2025)
- [Light4D: Training-Free Extreme Viewpoint 4D Video Relighting](https://mlsanity.com/paper/2602.11769/) (2026)
- [Reshoot-Anything: A Self-Supervised Model for In-the-Wild Video Reshooting](https://mlsanity.com/paper/2604.21776/) (2026)
- [Embody4D: A Generalist Data Engine for Embodied 4D World Modeling](https://mlsanity.com/paper/2605.01799/) (2026)
- [LoViF 2026 The First Challenge on Holistic Quality Assessment for 4D World Model (PhyScore)](https://mlsanity.com/paper/2605.05187/) (2026)
- [Real2SAM2Real: Generative 3D Caches as Complementary Context for Video Diffusion](https://mlsanity.com/paper/2606.00299/) (2026)
- [Go-with-the-Track: Video Compositing and Motion Control with Point Tracking](https://mlsanity.com/paper/2606.20891/) (2026)
- [CameraAnything: Refilming Videos with Arbitrary Camera Control](https://mlsanity.com/paper/2607.24591/) (2026)
- [Beyond Inpainting: Unleash 3D Understanding for Precise Camera-Controlled Video Generation](https://mlsanity.com/paper/2601.10214/) (2026)
- [Cinematic Compositing Using Character-Environment-Harmonized Video Generation Models](https://mlsanity.com/paper/2606.20233/) (2026)
- [WarpHammer: Densifying Scene Warps with 3D Object Priors for Extreme View Synthesis](https://mlsanity.com/paper/2606.31258/) (2026)
- [PE-Field 4D: Video Generation Models as Canvas](https://mlsanity.com/paper/2607.15667/) (2026)
- [ScaleVid: Geometry-Aware Video Object Scaling with Mesh-Free Inference](https://mlsanity.com/paper/2608.12232/) (2026)
- [Manifold4D: Denoising on Point Cloud Rendered Manifolds for Video Re-shooting](https://mlsanity.com/paper/2608.28174/) (2026)

## 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.