Indoor Wall Frame Installation
Indoor wall frame installation is being revolutionized by the integration of robotics and advanced computer vision techniques, aiming to automate and optimize this construction task. Current research focuses on developing robust methods for scene understanding and robot task planning using 4D BIM models, often incorporating transformer-based architectures and algorithms for efficient feature extraction, object detection, and motion estimation from both image and event-based camera data. This work holds significant implications for improving construction efficiency, safety, and reducing labor costs, while also advancing the broader fields of computer vision, robotics, and construction automation.
Papers
Frame-Voyager: Learning to Query Frames for Video Large Language Models
Sicheng Yu, Chengkai Jin, Huanyu Wang, Zhenghao Chen, Sheng Jin, Zhongrong Zuo, Xiaolei Xu, Zhenbang Sun, Bingni Zhang, Jiawei Wu, Hao Zhang, Qianru Sun
Media Framing through the Lens of Event-Centric Narratives
Rohan Das, Aditya Chandra, I-Ta Lee, Maria Leonor Pacheco