LA-Pose: Latent Action Pretraining Meets Pose Estimation

• URL: http://arxiv.org/abs/2604.27448v1
• Date: Thu, 30 Apr 2026 05:43:10 GMT
• Title: LA-Pose: Latent Action Pretraining Meets Pose Estimation
• Abstract summary: This paper revisits camera pose estimation through the lens of self-supervised pretraining.<n>We employ inverse- and forward-dynamics models to learn latent action representations, similar to Genie from driving videos.<n>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.
• Score: 14.57887023967546
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: 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.

Related papers

• ER-Pose: Rethinking Keypoint-Driven Representation Learning for Real-Time Human Pose Estimation [2.2248409468073143]
  Single-stage multi-person pose estimation aims to jointly perform human localization and keypoint prediction.<n>Box-driven single-stage pose estimation is implicitly constrained by bounding-box supervision during training.<n>We propose a keypoint-driven learning paradigm that elevates pose estimation to a primary prediction objective.<n>On MS COCO and CrowdPose, ER-Pose-n achieves AP improvements of 3.2/6.7 without pre-training and 7.4/4.9 with pre-training respectively.
  arXiv  Detail & Related papers  (2026-03-09T17:49:46Z)
• GeoMotion: Rethinking Motion Segmentation via Latent 4D Geometry [61.24189040578178]
  We propose a fully learning-based approach that directly infers moving objects from latent feature representations via attention mechanisms.<n>Our key insight is to bypass explicit correspondence estimation and instead let the model learn to implicitly disentangle object and camera motion.<n>Our approach achieves state-of-the-art motion segmentation performance with high efficiency.
  arXiv  Detail & Related papers  (2026-02-25T11:36:33Z)
• Universal Pose Pretraining for Generalizable Vision-Language-Action Policies [83.39008378156647]
  Existing Vision-Language-Action (VLA) models often suffer from feature collapse and low training efficiency.<n>We propose Pose-VLA, a decoupled paradigm that separates VLA training into a pre-training phase for extracting universal 3D spatial priors.<n>Our framework follows a two-stage pre-training pipeline, establishing fundamental spatial grounding via poses followed by motion alignment.
  arXiv  Detail & Related papers  (2026-02-23T11:00:08Z)
• An Efficient Occupancy World Model via Decoupled Dynamic Flow and Image-assisted Training [50.71892161377806]
  DFIT-OccWorld is an efficient 3D occupancy world model that leverages decoupled dynamic flow and image-assisted training strategy.<n>Our model forecasts future dynamic voxels by warping existing observations using voxel flow, whereas static voxels are easily obtained through pose transformation.
  arXiv  Detail & Related papers  (2024-12-18T12:10:33Z)
• On the Benefits of 3D Pose and Tracking for Human Action Recognition [77.07134833715273]
  We show the benefits of using tracking and 3D poses for action recognition. We propose a Lagrangian Action Recognition model by fusing 3D pose and contextualized appearance over tracklets. Our method achieves state-of-the-art performance on the AVA v2.2 dataset.
  arXiv  Detail & Related papers  (2023-04-03T17:59:49Z)
• SC-wLS: Towards Interpretable Feed-forward Camera Re-localization [29.332038781334443]
  Visual re-localization aims to recover camera poses in a known environment, which is vital for applications like robotics or augmented reality. Feed-forward absolute camera pose regression methods directly output poses by a network, but suffer from low accuracy. We propose a feed-forward method termed SC-wLS that exploits all scene coordinate estimates for weighted least squares pose regression.
  arXiv  Detail & Related papers  (2022-10-23T15:15:48Z)
• PoseTriplet: Co-evolving 3D Human Pose Estimation, Imitation, and Hallucination under Self-supervision [102.48681650013698]
  Existing self-supervised 3D human pose estimation schemes have largely relied on weak supervisions to guide the learning. We propose a novel self-supervised approach that allows us to explicitly generate 2D-3D pose pairs for augmenting supervision. This is made possible via introducing a reinforcement-learning-based imitator, which is learned jointly with a pose estimator alongside a pose hallucinator.
  arXiv  Detail & Related papers  (2022-03-29T14:45:53Z)
• Distribution-Aware Single-Stage Models for Multi-Person 3D Pose Estimation [29.430404703883084]
  We present a novel Distribution-Aware Single-stage (DAS) model for tackling the challenging multi-person 3D pose estimation problem. The proposed DAS model simultaneously localizes person positions and their corresponding body joints in the 3D camera space in a one-pass manner. Comprehensive experiments on benchmarks CMU Panoptic and MuPoTS-3D demonstrate the superior efficiency of the proposed DAS model.
  arXiv  Detail & Related papers  (2022-03-15T07:30:27Z)
• Reassessing the Limitations of CNN Methods for Camera Pose Regression [27.86655424544118]
  We propose a model that can directly regress the camera pose from images with significantly higher accuracy than existing methods of the same class. We first analyse why regression methods are still behind the state-of-the-art, and we bridge the performance gap with our new approach.
  arXiv  Detail & Related papers  (2021-08-16T17:55:26Z)
• AutoTrajectory: Label-free Trajectory Extraction and Prediction from Videos using Dynamic Points [92.91569287889203]
  We present a novel, label-free algorithm, AutoTrajectory, for trajectory extraction and prediction. To better capture the moving objects in videos, we introduce dynamic points. We aggregate dynamic points to instance points, which stand for moving objects such as pedestrians in videos.
  arXiv  Detail & Related papers  (2020-07-11T08:43:34Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.