# 4DGT: Learning a 4D Gaussian Transformer Using Real-World Monocular Videos

arXiv: https://arxiv.org/abs/2506.08015 · HTML: https://mlsanity.com/paper/2506.08015/

## Key facts

- Cited by 49 papers in the map (data through 14 Oct 2026).
- Builds on 57 of its 74 references that are in the map.
- First posted on arXiv 9 Jun 2025.

## Builds on (most cited first, 30 of 57)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Gaussian Error Linear Units (GELUs)](https://mlsanity.com/paper/1606.08415/) (2016)
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [Depth Anything V2](https://mlsanity.com/paper/2406.09414/) (2024)
- [Nerfies: Deformable Neural Radiance Fields](https://mlsanity.com/paper/2011.12948/) (2020)
- [4D Gaussian Splatting for Real-Time Dynamic Scene Rendering](https://mlsanity.com/paper/2310.08528/) (2023)
- [2D Gaussian Splatting for Geometrically Accurate Radiance Fields](https://mlsanity.com/paper/2403.17888/) (2024)
- [LRM: Large Reconstruction Model for Single Image to 3D](https://mlsanity.com/paper/2311.04400/) (2023)
- [Scaling Egocentric Vision: The EPIC-KITCHENS Dataset](https://mlsanity.com/paper/1804.02748/) (2018)
- [Accelerating 3D Deep Learning with PyTorch3D](https://mlsanity.com/paper/2007.08501/) (2020)
- [K-Planes: Explicit Radiance Fields in Space, Time, and Appearance](https://mlsanity.com/paper/2301.10241/) (2023)
- [FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision](https://mlsanity.com/paper/2407.08608/) (2024)
- [Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives](https://mlsanity.com/paper/2311.18259/) (2023)
- [Real-time Photorealistic Dynamic Scene Representation and Rendering with 4D Gaussian Splatting](https://mlsanity.com/paper/2310.10642/) (2023)
- [MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion](https://mlsanity.com/paper/2410.03825/) (2024)
- [UniDepth: Universal Monocular Metric Depth Estimation](https://mlsanity.com/paper/2403.18913/) (2024)
- [GS-LRM: Large Reconstruction Model for 3D Gaussian Splatting](https://mlsanity.com/paper/2404.19702/) (2024)
- [GRM: Large Gaussian Reconstruction Model for Efficient 3D Reconstruction and Generation](https://mlsanity.com/paper/2403.14621/) (2024)
- [TAPIR: Tracking Any Point with per-frame Initialization and temporal Refinement](https://mlsanity.com/paper/2306.08637/) (2023)
- [gsplat: An Open-Source Library for Gaussian Splatting](https://mlsanity.com/paper/2409.06765/) (2024)
- [ImageDream: Image-Prompt Multi-view Diffusion for 3D Generation](https://mlsanity.com/paper/2312.02201/) (2023)
- [Shape of Motion: 4D Reconstruction from a Single Video](https://mlsanity.com/paper/2407.13764/) (2024)

## Built on by (most cited first, 30 of 49)

- [NeoVerse: Enhancing 4D World Model with in-the-wild Monocular Videos](https://mlsanity.com/paper/2601.00393/) (2026)
- [Lyra 2.0: Explorable Generative 3D Worlds](https://mlsanity.com/paper/2604.13036/) (2026)
- [Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation](https://mlsanity.com/paper/2509.19296/) (2025)
- [Advances in Feed-Forward 3D Reconstruction and View Synthesis: A Survey](https://mlsanity.com/paper/2507.14501/) (2025)
- [ActionMesh: Animated 3D Mesh Generation with Temporal 3D Diffusion](https://mlsanity.com/paper/2601.16148/) (2026)
- [Mesh4D: 4D Mesh Reconstruction and Tracking from Monocular Video](https://mlsanity.com/paper/2601.05251/) (2026)
- [GLaD: Geometric Latent Distillation for Vision-Language-Action Models](https://mlsanity.com/paper/2512.09619/) (2025)
- [Off The Grid: Detection of Primitives for Feed-Forward 3D Gaussian Splatting](https://mlsanity.com/paper/2512.15508/) (2025)
- [PhysGM: Large Physical Gaussian Model for Feed-Forward 4D Synthesis](https://mlsanity.com/paper/2508.13911/) (2025)
- [ART: Articulated Reconstruction Transformer](https://mlsanity.com/paper/2512.14671/) (2025)
- [Forge4D: Feed-Forward 4D Human Reconstruction and Interpolation from Uncalibrated Sparse-view Videos](https://mlsanity.com/paper/2509.24209/) (2025)
- [Feed-Forward 3D Scene Modeling: A Problem-Driven Perspective](https://mlsanity.com/paper/2604.14025/) (2026)
- [UFO-4D: Unposed Feedforward 4D Reconstruction from Two Images](https://mlsanity.com/paper/2602.24290/) (2026)
- [Advances in 4D Representation: Geometry, Motion, and Interaction](https://mlsanity.com/paper/2510.19255/) (2025)
- [MotionCrafter: Dense Geometry and Motion Reconstruction with a 4D VAE](https://mlsanity.com/paper/2602.08961/) (2026)
- [NymeriaPlus: Enriching Nymeria Dataset with Additional Annotations and Data](https://mlsanity.com/paper/2603.18496/) (2026)
- [SLARM: Streaming and Language-Aligned Reconstruction Model for Dynamic Scenes](https://mlsanity.com/paper/2603.22893/) (2026)
- [Fast Spatial Memory with Elastic Test-Time Training](https://mlsanity.com/paper/2604.07350/) (2026)
- [ViPS: Video-informed Pose Spaces for Auto-Rigged Meshes](https://mlsanity.com/paper/2604.17623/) (2026)
- [UniWorld-View: Large-Baseline View Synthesis via Video Diffusion Models](https://mlsanity.com/paper/2608.04701/) (2026)
- [DrivingScene: A Multi-Task Online Feed-Forward 3D Gaussian Splatting Method for Dynamic Driving Scenes](https://mlsanity.com/paper/2510.24734/) (2025)
- [LSRM: High-Fidelity Object-Centric Reconstruction via Scaled Context Windows](https://mlsanity.com/paper/2604.05182/) (2026)
- [Face Anything: 4D Face Reconstruction from Any Image Sequence](https://mlsanity.com/paper/2604.19702/) (2026)
- [No Pose, No Problem in 4D: Feed-Forward Dynamic Gaussians from Unposed Multi-View Videos](https://mlsanity.com/paper/2605.22190/) (2026)
- [Learning Global Motion with Compact Gaussians for Feed-Forward 4D Reconstruction](https://mlsanity.com/paper/2605.31595/) (2026)
- [Lift4D: Harmonizing Single-View 3D Estimation for 4D Reconstruction In-the-Wild](https://mlsanity.com/paper/2606.23688/) (2026)
- [Fast 4D Mesh Generation by Spatio-Temporal Attention Chains](https://mlsanity.com/paper/2605.19786/) (2026)
- [Envision4D: Envisioning Visual Futures via Feed-forward 4D Gaussian Splatting for Autonomous Driving](https://mlsanity.com/paper/2606.10656/) (2026)
- [HiReFF: High-Resolution Feedforward Human Reconstruction from Uncalibrated Sparse-View Video](https://mlsanity.com/paper/2606.29333/) (2026)
- [ReViV: Reconstructing the Viewer and the View in 4D from Monocular Egocentric Video](https://mlsanity.com/paper/2607.17790/) (2026)

## Abstract (arXiv)

We propose 4DGT, a 4D Gaussian-based Transformer model for dynamic scene reconstruction, trained entirely on real-world monocular posed videos. Using 4D Gaussian as an inductive bias, 4DGT unifies static and dynamic components, enabling the modeling of complex, time-varying environments with varying object lifespans. We proposed a novel density control strategy in training, which enables our 4DGT to handle longer space-time input and remain efficient rendering at runtime. Our model processes 64 consecutive posed frames in a rolling-window fashion, predicting consistent 4D Gaussians in the scene. Unlike optimization-based methods, 4DGT performs purely feed-forward inference, reducing reconstruction time from hours to seconds and scaling effectively to long video sequences. Trained only on large-scale monocular posed video datasets, 4DGT can outperform prior Gaussian-based networks significantly in real-world videos and achieve on-par accuracy with optimization-based methods on cross-domain videos. Project page: https://4dgt.github.io