# VGGT-Omega

arXiv: https://arxiv.org/abs/2605.15195 · HTML: https://mlsanity.com/paper/2605.15195/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- Builds on 188 of its 245 references that are in the map.
- First posted on arXiv 14 May 2026.

## Builds on (most cited first, 30 of 188)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023)
- [OpenVLA: An Open-Source Vision-Language-Action Model](https://mlsanity.com/paper/2406.09246/) (2024)
- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [Scalability in Perception for Autonomous Driving: Waymo Open Dataset](https://mlsanity.com/paper/1912.04838/) (2019)
- [Vision Transformers for Dense Prediction](https://mlsanity.com/paper/2103.13413/) (2021)
- [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)
- [SuperGlue: Learning Feature Matching with Graph Neural Networks](https://mlsanity.com/paper/1911.11763/) (2019)
- [DINOv3](https://mlsanity.com/paper/2508.10104/) (2025)
- [LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning](https://mlsanity.com/paper/2306.03310/) (2023)
- [Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time](https://mlsanity.com/paper/2203.05482/) (2022)
- [Transformer Feed-Forward Layers Are Key-Value Memories](https://mlsanity.com/paper/2012.14913/) (2020)
- [SuperPoint: Self-Supervised Interest Point Detection and Description](https://mlsanity.com/paper/1712.07629/) (2017)
- [Habitat: A Platform for Embodied AI Research](https://mlsanity.com/paper/1904.01201/) (2019)
- [Scaling Vision Transformers](https://mlsanity.com/paper/2106.04560/) (2021)
- [Grounding Image Matching in 3D with MASt3R](https://mlsanity.com/paper/2406.09756/) (2024)
- [Chameleon: Mixed-Modal Early-Fusion Foundation Models](https://mlsanity.com/paper/2405.09818/) (2024)

## Built on by (most cited first, 26 of 26)

- [WAM4D: Fast 4D World Action Model via Spatial Register Tokens](https://mlsanity.com/paper/2606.14048/) (2026)
- [Code as Worlds: Agentic Discovery of Executable World Representations for Physical Reasoning](https://mlsanity.com/paper/2608.27549/) (2026)
- [Geometric Action Model for Robot Policy Learning](https://mlsanity.com/paper/2606.17046/) (2026)
- [GEM-4D: Geometry-Enhanced Video World Models for Robot Manipulation](https://mlsanity.com/paper/2605.22882/) (2026)
- [MoWorld: A Flash World Model](https://mlsanity.com/paper/2607.06216/) (2026)
- [GeoWorldAD: Geometry World Action Model for Autonomous Driving](https://mlsanity.com/paper/2607.17521/) (2026)
- [UniNav: A Unified World-Action Diffusion Model for Visual Navigation](https://mlsanity.com/paper/2608.03244/) (2026)
- [ViSTR-Bench: Can MLLMs Reason from Continuous Visual Cues in Dynamic Scenes?](https://mlsanity.com/paper/2607.20868/) (2026)
- [Revisiting Local Context for Long-Horizon Streaming 3D Reconstruction](https://mlsanity.com/paper/2608.27529/) (2026)
- [ReconPlusGen: Injecting Reconstruction Prior into Multi-view 3D Generation through Noise Inversion and Modulation](https://mlsanity.com/paper/2609.11129/) (2026)
- [CausalWM: Causal Chain-of-Thought Reasoning for Embodied World Model](https://mlsanity.com/paper/2609.23184/) (2026)
- [SpatialBench: Is Your Spatial Foundation Model an All-Round Player?](https://mlsanity.com/paper/2605.27367/) (2026)
- [RoGe: Novel View Synthesis via End-to-End Implicit Reconstruction and Generation](https://mlsanity.com/paper/2609.02847/) (2026)
- [What Matters in Designing World Action Models: An Empirical Study](https://mlsanity.com/paper/2609.24048/) (2026)
- [VGGT-Diff: Visual Geometry Meets Diffusion for Sparse-View Novel View Synthesis](https://mlsanity.com/paper/2609.33253/) (2026)
- [MeteoVerse: Unified Weather-Controllable Video World Model](https://mlsanity.com/paper/2609.36810/) (2026)
- [HelixWorld: A Real-time Interactive Audio-Visual World Model](https://mlsanity.com/paper/2609.38123/) (2026)
- [SPOON: Towards Coherent Compositional 3D Scene Generation from Uncalibrated Multi-view Images](https://mlsanity.com/paper/2609.39590/) (2026)
- [Ego4WAM: What Matters When Scaling Egocentric Human Data for Robot Learning?](https://mlsanity.com/paper/2609.40341/) (2026)
- [Less Context, Better Geometry: Masked Geometric Encoder for Robust 3D Foundation Models](https://mlsanity.com/paper/2610.06813/) (2026)
- [DistScene: Object-to-Scene Distillation for 3D Scene Generation](https://mlsanity.com/paper/2610.06960/) (2026)
- [Seek-and-View Reasoning for Multi-View Spatial Understanding](https://mlsanity.com/paper/2610.11810/) (2026)
- [OuroWorld: Bringing Any 3D World Alive as Diverse, Endlessly Looping 3D Cinemagraphs](https://mlsanity.com/paper/2610.12461/) (2026)
- [ScenePlacer: Reformulating Scene-Level Object Pose Estimation as Visibility Field Learning](https://mlsanity.com/paper/2610.15734/) (2026)
- [Totem: Object-Centric 3D Memory for World-Consistent Video Generation](https://mlsanity.com/paper/2610.15807/) (2026)
- [WorldRecon: Generative Multi-View Mesh Reconstruction for Large-Scale 3D World](https://mlsanity.com/paper/2610.18846/) (2026)

## Abstract (arXiv)

Recent feed-forward reconstruction models, such as VGGT, have proven competitive with traditional optimization-based reconstructors while also providing geometry-aware features useful for other tasks. Here, we show that the quality of these models scales predictably with model and data size. We do so by introducing VGGT-Omega, which substantially improves reconstruction accuracy, efficiency, and capabilities for both static and dynamic scenes. To enable training this model at an unprecedented scale, we introduce architectural changes that improve training efficiency, a high-quality data annotation pipeline that supports dynamic scenes, and a self-supervised learning protocol. We simplify VGGT's architecture by using a single dense prediction head with multi-task supervision and removing the expensive high-resolution convolutional layers. We also use registers to aggregate scene information into a compact representation and introduce register attention, which restricts inter-frame information exchange to these registers, in part replacing global attention. In this way, during training, VGGT-Omega uses only about 30% of the GPU memory of its predecessor, allowing us to train with 15x more supervised data than prior work and to leverage vast amounts of unlabeled video data. VGGT-Omega achieves strong results for reconstruction of static and dynamic scenes across multiple benchmarks, for example, improving over the previous best camera estimation accuracy on Sintel by 77%. We also show that the learned registers can improve vision-language-action models and support alignment with language, suggesting that reconstruction can be a powerful and scalable proxy task for spatial understanding. Project Page: http://vggt-omega.github.io/