Lune

ICML2025

Orient Anything: Learning Robust Object Orientation Estimation from Rendering 3D Models

Zehan Wang, Ziang Zhang, Tianyu Pang, Chao Du, Hengshuang Zhao, Zhou Zhao

2025年份

摘要

https://orient-anything.github.io/ Figure 1. We introduce a novel method for estimating the object orientation in images, represented by the red axis, while the blue and green axes indicate the upward and left sides of the object. More examples are provided in Appendix. Best viewed on screen with zoom.