arXiv AI By Yonglong Zhang, Yang Liu

GAP-GDRNet: Geometry-Aware Monocular Visual Pose Sensing on a Single-Target Synthetic Spacecraft Dataset

Read the original on arXiv AI →

arXiv:2607. 02360v1 Announce Type: cross Abstract: Monocular relative pose sensing is a central perception problem in non-cooperative rendezvous and on-orbit servicing.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

arXiv AI
Jul 24

3D-Aware VLMs with Implicit and Explicit Geometries

arXiv:2607. 21595v1 Announce Type: cross Abstract: Despite rapid progress, most existing vision-language models (VLMs) built from 2D visual inputs often struggle when handling various 3D tasks that require fine-grained spatial understanding and reasoning.

By Wenhao Li, Xueying Jiang, Quanhao Qian, Deli Zhao, Ran Xu, Shijian Lu, Gongjie Zhang