2022年2月14日 · We propose Geometric Transformer to learn geometric feature for robust superpoint matching. It encodes pair-wise distances and triplet-wise angles, making it robust in low-overlap cases and invariant to rigid transformation.

2023年7月25日 · We propose Geometric Transformer, or GeoTransformer for short, to learn geometric feature for robust superpoint matching. It encodes pair-wise distances and triplet-wise angles, making it invariant to rigid transformation and robust in low-overlap cases.

From 21 Dec 2023 to 06 Jan 2024 the INSPIRE team works on a reduced schedule and it will take a bit longer than usual to address your requests. Best wishes for the season! Munich, Max Planck Inst. Quantenopt.

2022年2月14日 · Geometric Transformer for Fast and Robust Point Cloud Registration. Zheng Qin, Hao Yu, Changjian Wang, Yulan Guo, Yuxing Peng, and Kai Xu. We study the problem of extracting accurate correspondences for point cloud registration.

Rotation-Invariant Transformer for Point Cloud Matching by: Hao Yu, Zheng Qin, Ji Hou, Mahdi Saleh, Dongsheng Li, Benjamin Busam and Slobodan Ilic. The intrinsic rotation invariance lies at the core of matching point clouds with handcrafted descriptors.

Hao Yu. Ph.D Candidate, Technische Universität München. Verified email at tum.de - Homepage. 3D Computer Vision. Articles Cited by Public access Co-authors. Title. ... Z Qin, H Yu, C Wang, Y Guo, Y Peng, S Ilic, D Hu, K Xu. IEEE Transactions on Pattern Analysis and Machine Intelligence 45 (8), 9806-9821, 2023. 110:

Hao Yu. I am a PhD candidate at the Chair for Computer Aided Medical Procedures & Augmented Reality of Technical University of Munich, supervised by PD Dr. Slobodan Ilic and Dr. Benjamin Busam . Before that, I finished my Master and Bachelor study in National University of Defense Technology, China.

We propose Geometric Trans-former to learn geometric feature for robust superpoint matching. It encodes pair-wise distances and triplet-wise angles, making it robust in low-overlap cases and invari-ant to rigid transformation.

2024年3月25日 · Here, a novel 1D monoclinic phase iridium-ruthenium oxide solid solution (m-Ir x Ru 1-x O 2) is reported. For m-Ir x Ru 1-x O 2 with different metal proportions, the optimal m-Ir 0.91 Ru 0.09 O 2-δ catalyst exhibits excellent OER activity under acidic conditions with an overpotential of 180 mV at 10 mA cm −2.

Yuhao QIN, PhD Student | Cited by 34 | of Tsinghua University, Beijing (TH) | Read 13 publications | Contact Yuhao QIN