Lintao Zheng

Learn More
We address the problem of autonomously exploring unknown objects in a scene by consecutive depth acquisitions. The goal is to reconstruct the scene while online identifying the objects from among a large collection of 3D shapes. Fine-grained shape identification demands a meticulous series of observations attending to varying views and parts of the object(More)
Understanding 3D environments is a vital element of modern computer vision research due to paramount relevance in many vision systems, spanning a wide field of application scenarios from self-driving cars to autonomous robots [Qi et al. 2016]. At the present time, object recognition mainly employs two methods: volumetric CNNs [Wu Z 2015] and multi-view CNNs(More)
— Active vision is inherently attention-driven: The agent selects views of observation to best approach the vision task while improving its internal representation of the scene being observed. Inspired by the recent success of attention-based models in 2D vision tasks based on single RGB images, we propose to address the multi-view depth-based active object(More)
  • 1