# LA-Pose: Latent Action Pretraining Meets Pose Estimation

arXiv: https://arxiv.org/abs/2604.27448 · HTML: https://mlsanity.com/paper/2604.27448/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 35 of its 40 references that are in the map.
- First posted on arXiv 30 Apr 2026.

## Builds on (most cited first, 30 of 35)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [Scalability in Perception for Autonomous Driving: Waymo Open Dataset](https://mlsanity.com/paper/1912.04838/) (2019)
- [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)
- [VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training](https://mlsanity.com/paper/2203.12602/) (2022)
- [Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture](https://mlsanity.com/paper/2301.08243/) (2023)
- [V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning](https://mlsanity.com/paper/2506.09985/) (2025)
- [Unsupervised Learning of Depth and Ego-Motion from Video](https://mlsanity.com/paper/1704.07813/) (2017)
- [Genie: Generative Interactive Environments](https://mlsanity.com/paper/2402.15391/) (2024)
- [Argoverse: 3D Tracking and Forecasting with Rich Maps](https://mlsanity.com/paper/1911.02620/) (2019)
- [GAIA-1: A Generative World Model for Autonomous Driving](https://mlsanity.com/paper/2309.17080/) (2023)
- [Continuous 3D Perception Model with Persistent State](https://mlsanity.com/paper/2501.12387/) (2025)
- [Revisiting Feature Prediction for Learning Visual Representations from Video](https://mlsanity.com/paper/2404.08471/) (2024)
- [Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Pass](https://mlsanity.com/paper/2501.13928/) (2025)
- [Vista: A Generalizable Driving World Model with High Fidelity and Versatile Controllability](https://mlsanity.com/paper/2405.17398/) (2024)
- [Latent Action Pretraining from Videos](https://mlsanity.com/paper/2410.11758/) (2024)
- [MapAnything: Universal Feed-Forward Metric 3D Reconstruction](https://mlsanity.com/paper/2509.13414/) (2025)
- [MoGe-2: Accurate Monocular Geometry with Metric Scale and Sharp Details](https://mlsanity.com/paper/2507.02546/) (2025)
- [PandaSet: Advanced Sensor Suite Dataset for Autonomous Driving](https://mlsanity.com/paper/2112.12610/) (2021)
- [GAIA-2: A Controllable Multi-View Generative World Model for Autonomous Driving](https://mlsanity.com/paper/2503.20523/) (2025)
- [GenAD: Generalized Predictive Model for Autonomous Driving](https://mlsanity.com/paper/2403.09630/) (2024)
- [PoseDiffusion: Solving Pose Estimation via Diffusion-aided Bundle Adjustment](https://mlsanity.com/paper/2306.15667/) (2023)
- [GameFactory: Creating New Games with Generative Interactive Videos](https://mlsanity.com/paper/2501.08325/) (2025)
- [AdaWorld: Learning Adaptable World Models with Latent Actions](https://mlsanity.com/paper/2503.18938/) (2025)
- [The Matrix: Infinite-Horizon World Generation with Real-Time Moving Control](https://mlsanity.com/paper/2412.03568/) (2024)
- [GEM: A Generalizable Ego-Vision Multimodal World Model for Fine-Grained Ego-Motion, Object Dynamics, and Scene Composition Control](https://mlsanity.com/paper/2412.11198/) (2024)
- [RayZer: A Self-supervised Large View Synthesis Model](https://mlsanity.com/paper/2505.00702/) (2025)

## Abstract (arXiv)

This paper revisits camera pose estimation through the lens of self-supervised pretraining, focusing on inverse-dynamics pretraining as a scalable alternative to the current trend of fully supervised training with 3D annotations. Concretely, we employ inverse- and forward-dynamics models to learn latent action representations, similar to Genie from large-scale driving videos. Our idea is simple yet effective. Existing methods use latent actions in their original capacity, that is, as action conditioning of world-models or as proxies of robot action parameters in policy networks. Our method, dubbed LA-Pose, repurposes the latent action features as inputs to a camera pose estimator, finetuned on a limited set of high-quality 3D annotations. This formulation enables accurate and generalizable pose prediction while maintaining feed-forward efficiency. Extensive experiments on driving benchmarks show that LA-Pose achieves competitive and even superior performance to state-of-the-art methods while using orders of magnitude less labeled data. Concretely, on the Waymo and PandaSet benchmarks, LA-Pose achieves over 10% higher pose accuracy than recent feed-forward methods. To our knowledge, this work is the first to demonstrate the power of inverse-dynamics self-supervised learning for pose estimation.