ECCV2022論文サマリ

tag: 3d

Is Geometry Enough for Matching in Visual Localization?
by: Haruhi Shida
3D autonomous driving visual localiztion
TEMOS: Generating Diverse Human Motions from Textual Descriptions
by: Kosuke Fukazawa
3D Multi modal Motion Synthesis Text to Motion
MotionCLIP: Exposing Human Motion Generation to CLIP Space
by: Kosuke Fukazawa
3D Multi modal Motion Synthesis Text to Motion
CATRE: Iterative Point Clouds Alignment for Category-Level Object Pose Refinement
by: Naoya Chiba
3D 3D object detection Point cloud Pose estimation
Multimodal Object Detection via Probabilistic Ensembling
by: Haruhi Shida
3D 3D object detection Multimodal Ensembling