# Uni4D: Unifying Visual Foundation Models for 4D Modeling from a Single Video

arXiv: https://arxiv.org/abs/2503.21761 · HTML: https://mlsanity.com/paper/2503.21761/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- Builds on 45 of its 73 references that are in the map.
- First posted on arXiv 27 Mar 2025.

## Builds on (most cited first, 30 of 45)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [DUSt3R: Geometric 3D Vision Made Easy](https://mlsanity.com/paper/2312.14132/) (2023)
- [Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data](https://mlsanity.com/paper/2401.10891/) (2024)
- [4D Gaussian Splatting for Real-Time Dynamic Scene Rendering](https://mlsanity.com/paper/2310.08528/) (2023)
- [ORB-SLAM: a Versatile and Accurate Monocular SLAM System](https://mlsanity.com/paper/1502.00956/) (2015)
- [Grounding Image Matching in 3D with MASt3R](https://mlsanity.com/paper/2406.09756/) (2024)
- [DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Cameras](https://mlsanity.com/paper/2108.10869/) (2021)
- [CoTracker: It is Better to Track Together](https://mlsanity.com/paper/2307.07635/) (2023)
- [MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion](https://mlsanity.com/paper/2410.03825/) (2024)
- [Dynamic View Synthesis from Dynamic Monocular Video](https://mlsanity.com/paper/2105.06468/) (2021)
- [Depth Pro: Sharp Monocular Metric Depth in Less Than a Second](https://mlsanity.com/paper/2410.02073/) (2024)
- [Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimation](https://mlsanity.com/paper/2404.15506/) (2024)
- [UniDepth: Universal Monocular Metric Depth Estimation](https://mlsanity.com/paper/2403.18913/) (2024)
- [Humans in 4D: Reconstructing and Tracking Humans with Transformers](https://mlsanity.com/paper/2305.20091/) (2023)
- [Recognize Anything: A Strong Image Tagging Model](https://mlsanity.com/paper/2306.03514/) (2023)
- [GeoWizard: Unleashing the Diffusion Priors for 3D Geometry Estimation from a Single Image](https://mlsanity.com/paper/2403.12013/) (2024)
- [Shape of Motion: 4D Reconstruction from a Single Video](https://mlsanity.com/paper/2407.13764/) (2024)
- [Sapiens: Foundation for Human Vision Models](https://mlsanity.com/paper/2408.12569/) (2024)
- [DynIBaR: Neural Dynamic Image-Based Rendering](https://mlsanity.com/paper/2211.11082/) (2022)
- [Global Structure-from-Motion Revisited](https://mlsanity.com/paper/2407.20219/) (2024)
- [DepthCrafter: Generating Consistent Long Depth Sequences for Open-world Videos](https://mlsanity.com/paper/2409.02095/) (2024)
- [BANMo: Building Animatable 3D Neural Models from Many Casual Videos](https://mlsanity.com/paper/2112.12761/) (2021)
- [Tracking Anything with Decoupled Video Segmentation](https://mlsanity.com/paper/2309.03903/) (2023)
- [Deep Patch Visual Odometry](https://mlsanity.com/paper/2208.04726/) (2022)
- [Robust Consistent Video Depth Estimation](https://mlsanity.com/paper/2012.05901/) (2020)

## Built on by (most cited first, 29 of 29)

- [Geo4D: Leveraging Video Generators for Geometric 4D Scene Reconstruction](https://mlsanity.com/paper/2504.07961/) (2025)
- [MoVieS: Motion-Aware 4D Dynamic View Synthesis in One Second](https://mlsanity.com/paper/2507.10065/) (2025)
- [VGGT4D: Mining Motion Cues in Visual Geometry Transformers for 4D Scene Reconstruction](https://mlsanity.com/paper/2511.19971/) (2025)
- [VGGT-Omega](https://mlsanity.com/paper/2605.15195/) (2026)
- [Viser: Imperative, Web-based 3D Visualization in Python](https://mlsanity.com/paper/2507.22885/) (2025)
- [Generative Video Motion Editing with 3D Point Tracks](https://mlsanity.com/paper/2512.02015/) (2025)
- [Vista4D: Video Reshooting with 4D Point Clouds](https://mlsanity.com/paper/2604.21915/) (2026)
- [Reconstructing 4D Spatial Intelligence: A Survey](https://mlsanity.com/paper/2507.21045/) (2025)
- [Track4World: Feedforward World-centric Dense 3D Tracking of All Pixels](https://mlsanity.com/paper/2603.02573/) (2026)
- [MoRe: Motion-aware Feed-forward 4D Reconstruction Transformer](https://mlsanity.com/paper/2603.05078/) (2026)
- [PAGE-4D: Disentangled pose and geometry estimation for vggt-4d perception](https://mlsanity.com/paper/2510.17568/) (2025)
- [E3D-Bench: A Benchmark for End-to-End 3D Geometric Foundation Models](https://mlsanity.com/paper/2506.01933/) (2025)
- [TrackingWorld: World-centric Monocular 3D Tracking of Almost All Pixels](https://mlsanity.com/paper/2512.08358/) (2025)
- [DynamicVerse: A Physically-Aware Multimodal Framework for 4D World Modeling](https://mlsanity.com/paper/2512.03000/) (2025)
- [HuPrior3R: Incorporating Human Priors for Better 3D Dynamic Reconstruction from Monocular Videos](https://mlsanity.com/paper/2512.06368/) (2025)
- [DAGE: Dual-Stream Architecture for Efficient and Fine-Grained Geometry Estimation](https://mlsanity.com/paper/2603.03744/) (2026)
- [FreeArtGS: Articulated Gaussian Splatting Under Free-moving Scenario](https://mlsanity.com/paper/2603.22102/) (2026)
- [Geometry-Aware Single-Image 4D Synthesis via Dense Trajectory Generation](https://mlsanity.com/paper/2512.05044/) (2025)
- [MoRight: Motion Control Done Right](https://mlsanity.com/paper/2604.07348/) (2026)
- [Visual Sync: Multi-Camera Synchronization via Cross-View Object Motion](https://mlsanity.com/paper/2512.02017/) (2025)
- [AeroDGS: Physically Consistent Dynamic Gaussian Splatting for Single-Sequence Aerial 4D Reconstruction](https://mlsanity.com/paper/2602.22376/) (2026)
- [Preserve, Reveal, Expand: Faithful 4D Video Editing with Region-Aware Conditioning](https://mlsanity.com/paper/2605.20961/) (2026)
- [UniQuery4R: Unified 4D Scene Reconstruction from a Single Query](https://mlsanity.com/paper/2608.17283/) (2026)
- [InsertAnywhere: Geometrically Grounded and Optics-Aware Video Object Insertion](https://mlsanity.com/paper/2512.17504/) (2025)
- [ArtHOI: Articulated Human-Object Interaction Synthesis by 4D Reconstruction from Video Priors](https://mlsanity.com/paper/2603.04338/) (2026)
- [Controllable Video Object Insertion via Multi-View Priors](https://mlsanity.com/paper/2604.14556/) (2026)
- [4DVGGT-D: 4D Visual Geometry Transformer with Improved Dynamic Depth Estimation](https://mlsanity.com/paper/2605.12027/) (2026)
- [MoSE3: Learning World-Space SE(3) at Every Pixel](https://mlsanity.com/paper/2610.03716/) (2026)
- [4LC: 4D Latent Cache for Efficient Conditioning in Dynamic World Modeling](https://mlsanity.com/paper/2610.17625/) (2026)

## Abstract (arXiv)

This paper presents a unified approach to understanding dynamic scenes from casual videos. Large pretrained vision foundation models, such as vision-language, video depth prediction, motion tracking, and segmentation models, offer promising capabilities. However, training a single model for comprehensive 4D understanding remains challenging. We introduce Uni4D, a multi-stage optimization framework that harnesses multiple pretrained models to advance dynamic 3D modeling, including static/dynamic reconstruction, camera pose estimation, and dense 3D motion tracking. Our results show state-of-the-art performance in dynamic 4D modeling with superior visual quality. Notably, Uni4D requires no retraining or fine-tuning, highlighting the effectiveness of repurposing visual foundation models for 4D understanding.