5 papers
MV-ROPE: Multi-view Constraints for Robust Category-level Object Pose and Size Estimation
Jiaqi Yang, Yucong Chen, Xiangting Meng +6
Recently there has been a growing interest in category-level object pose and size estimation, and prevailing methods commonly rely on single view RGB-D images. However, one disadva…
Scale jump-aware pose graph relaxation for monocular SLAM with re-initializations
Runze Yuan, Ran Cheng, Lige Liu +2
Pose graph relaxation has become an indispensable addition to SLAM enabling efficient global registration of sensor reference frames under the objective of satisfying pair-wise rel…
Unsupervised Voice-Face Representation Learning by Cross-Modal Prototype Contrast
Boqing Zhu, Kele Xu, Changjian Wang +4
We present an approach to learn voice-face representations from the talking face videos, without any identity labels. Previous works employ cross-modal instance discrimination task…
S3E-GNN: Sparse Spatial Scene Embedding with Graph Neural Networks for Camera Relocalization
Ran Cheng, Xinyu Jiang, Yuan Chen +2
Camera relocalization is the key component of simultaneous localization and mapping (SLAM) systems. This paper proposes a learning-based approach, named Sparse Spatial Scene Embedd…
Spotlights: Probing Shapes from Spherical Viewpoints
Jiaxin Wei, Lige Liu, Ran Cheng +6
Recent years have witnessed the surge of learned representations that directly build upon point clouds. Though becoming increasingly expressive, most existing representations still…