3D Model
3D models are digital representations of three-dimensional objects, with research focusing on efficient and accurate creation methods, often leveraging AI and machine learning. Current efforts concentrate on generating 3D models from various inputs, including single images, videos, text descriptions, and existing 3D references, employing techniques like diffusion models, Gaussian splatting, and neural radiance fields. These advancements have significant implications for diverse fields, including medicine (e.g., accurate body measurements), manufacturing (e.g., digital twins), entertainment (e.g., animation and game development), and cultural heritage preservation (e.g., reconstruction of historical artifacts).
Papers
Visual Localization using Imperfect 3D Models from the Internet
Vojtech Panek, Zuzana Kukelova, Torsten Sattler
WildRefer: 3D Object Localization in Large-scale Dynamic Scenes with Multi-modal Visual Data and Natural Language
Zhenxiang Lin, Xidong Peng, Peishan Cong, Yuenan Hou, Xinge Zhu, Sibei Yang, Yuexin Ma
NOPE: Novel Object Pose Estimation from a Single Image
Van Nguyen Nguyen, Thibault Groueix, Yinlin Hu, Mathieu Salzmann, Vincent Lepetit
IST-Net: Prior-free Category-level Pose Estimation with Implicit Space Transformation
Jianhui Liu, Yukang Chen, Xiaoqing Ye, Xiaojuan Qi
6D Object Pose Estimation from Approximate 3D Models for Orbital Robotics
Maximilian Ulmer, Maximilian Durner, Martin Sundermeyer, Manuel Stoiber, Rudolph Triebel