Xiu Li

• Doctor of Philosophy
• PhD Student at Tsinghua University

We present a method to combine markerless motion capture and dense pose feature estimation into a single framework. We demonstrate that dense pose information can help for multiview/single-view motion capture, and multiview motion capture can help the collection of a high-quality dataset for training the dense pose detector. Specifically, we first...

This paper proposes a new method for Non-Rigid Structure-from-Motion (NRSfM) from a long monocular video sequence observing a non-rigid object performing recurrent and possibly repetitive dynamic action. Departing from the traditional idea of using linear low-order or lowrank shape model for the task of NRSfM, our method exploits the property of sh...

Unmanned aerial vehicles capable of hazardous terrain landing are desirable for intelligence collection. A crucial point is the landing gears autonomous adaptation to the rough surface, which is especially difficult in unknown and constrained environment. To enable this capability, this paper proposes a novel biomimetic system that ascertains terra...

In the News & Analysis story “Drones flying high as new tool for field biologists” (2 May, p. [459][1]), R. Schiffman presents a new useful application of unmanned aerial vehicles (UAVs) in the field of monitoring wildlife, but the drones still have some limitations. The quadrotor UAVs that they