The introduction of wearable video cameras (eg, GoPro) in the consumer market has
promoted video life-logging, motivating users to generate large amounts of video data. This …

Video stabilization is one of the most fundamental and challenging tasks in video
processing, which can be widely applied in many areas, such as video surveillance …

We present a novel video stabilization method which models camera motion with a bundle
of (multiple) camera paths. The proposed model is based on a mesh-based, spatially-variant …

The phone attitude is an essential input to many smartphone applications, which has been
known very difficult to accurately estimate especially over long time. Based on in-depth …

Low-light conditions present significant challenges for digital photography. This is a well-
known problem with a long history of treatment in the camera and mobile device industries …

We present a direct monocular visual odometry system which runs in real-time on a
smartphone. Being a direct method, it tracks and maps on the images themselves instead of …

We propose a novel motion model, SteadyFlow, to represent the motion between
neighboring video frames for stabilization. A SteadyFlow is a specific optical flow by …

We present a novel algorithm for efficient removal of rolling shutter distortions in
uncalibrated streaming videos. Our proposed method is calibration free as it does not need …

Many existing video stabilization methods often stabilize videos off-line, ie as a
postprocessing tool of pre-recorded videos. Some methods can stabilize videos online, but …

Rolling Shutter (RS) cameras are used across a wide range of consumer electronic devices--
from smart-phones to high-end cameras. It is well known, that if a RS camera is used with a …