Lintao Zheng

TL;DR: A 3D Attention Model that selects the best views to scan from, as well as the most informative regions in each view to focus on, to achieve efficient object recognition is developed, which leads to focus-driven features which are quite robust against object occlusion.

TL;DR: A novel fusion-aware 3D point convolution which operates directly on the geometric surface being reconstructed and exploits effectively the inter-frame correlation for high-quality 3D feature learning is proposed.

TL;DR: This work harnesses a time-varying tensor field to guide robot movement, and shows that tensor fields are well suited for guiding autonomous scanning for two reasons: first, they contain sparse and controllable singularities that allow generating a locally smooth robot path, and second, their topological structure can be used for globally efficient path routing within a partially reconstructed scene.

TL;DR: In this paper, online reconstruction based on RGB-D sequences has thus far been restrained to relatively slow camera motions (e.g., slow camera motion) due to the slow camera movements.

TL;DR: This work proposes a novel approach to robot‐operated active understanding of unknown indoor scenes, based on online RGBD reconstruction with semantic segmentation, and shows that this method achieves efficient and accurate online scene parsing during exploratory scanning.