Monocular Visual 8D Pose Estimation for Articulated Bicycles and Cyclists

2025-10-22

AI Summary

To address the challenge of cyclist pose estimation in autonomous driving, this paper proposes the first category-level 8D pose estimation method for articulated bicycles and cyclists—estimating 3D translation, global rotation, and relative rotations of handlebars and pedals. Unlike conventional rigid 6D pose estimation, our approach explicitly models joint articulation to accurately capture steering intent and pedal dynamics. We introduce a joint learning framework that integrates synthetic and real-world image data to simultaneously predict 8D pose and 3D keypoints, optimized end-to-end via differentiable rendering and geometric constraints. Evaluated on real-world scenes, our method achieves localization accuracy comparable to state-of-the-art 6D approaches while significantly improving joint pose estimation accuracy. Results demonstrate the effectiveness, fine-grained articulation modeling capability, and cross-domain generalizability of our method.

Technology Category

• Computer Vision: Biometrics, Face, Gesture & Pose
• Intelligent Robots: State Estimation
• Planning, Routing, and Scheduling: Model-Based Reasoning

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

In Autonomous Driving, cyclists belong to the safety-critical class of Vulnerable Road Users (VRU), and accurate estimation of their pose is critical for cyclist crossing intention classification, behavior prediction, and collision avoidance. Unlike rigid objects, articulated bicycles are composed of movable rigid parts linked by joints and constrained by a kinematic structure. 6D pose methods can estimate the 3D rotation and translation of rigid bicycles, but 6D becomes insufficient when the steering/pedals angles of the bicycle vary. That is because: 1) varying the articulated pose of the bicycle causes its 3D bounding box to vary as well, and 2) the 3D box orientation is not necessarily aligned to the orientation of the steering which determines the actual intended travel direction. In this work, we introduce a method for category-level 8D pose estimation for articulated bicycles and cyclists from a single RGB image. Besides being able to estimate the 3D translation and rotation of a bicycle from a single image, our method also estimates the rotations of its steering handles and pedals with respect to the bicycle body frame. These two new parameters enable the estimation of a more fine-grained bicycle pose state and travel direction. Our proposed model jointly estimates the 8D pose and the 3D Keypoints of articulated bicycles, and trains with a mix of synthetic and real image data to generalize on real images. We include an evaluation section where we evaluate the accuracy of our estimated 8D pose parameters, and our method shows promising results by achieving competitive scores when compared against state-of-the-art category-level 6D pose estimators that use rigid canonical object templates for matching.

Problem

• Estimating articulated bicycle pose from single RGB images
• Predicting cyclist travel direction through steering and pedal angles
• Overcoming limitations of rigid object pose estimation methods

Innovation

• Estimates 8D pose from single RGB image
• Predicts steering and pedal rotation angles
• Uses synthetic and real data for training