Active Object Reconstruction Using a Guided View Planner

Inspired by the recent advance of image-based object reconstruction using deep learning, we present an active reconstruction model using a guided view planner. We aim to reconstruct a 3D model using images observed from a planned sequence of informative and discriminative views. But where are such informative and discriminative views around an object? To address this we propose a unified model for view planning and object reconstruction, which is utilized to learn a guided information acquisition model and to aggregate information from a sequence of images for reconstruction. Experiments show that our model (1) increases our reconstruction accuracy with an increasing number of views (2) and generally predicts a more informative sequence of views for object reconstruction compared to other alternative methods.

Authors

• Xin Yang Dalian University of Technology
• Yuanbo Wang Dalian University of Technology
• Yaru Wang
• Baocai Yin Beijing University of Technology
• Qiang Zhang University of Science and Technology of China, Hefei, China
• Xiaopeng Wei Dalian University of Technology
• Hongbo Fu City University of Hong Kong

Keywords

• Computer Vision: 2D and 3D Computer Vision
• Computer Vision: Structural and Model-Based Approaches, Knowledge Representation and Reasoning
• Robotics: Robotics and Vision