Reconstructing transparent objects is a challenging problem. While producing reasonable results for quite complex objects, existing approaches require custom calibration or somewh...
Sai-Kit Yeung, Tai-Pang Wu, Chi-keung Tang, Tony F...
Combining information from the higher level and the lower level has long been recognized as an essential component in holistic image understanding. However, an efficient inferenc...
We present a framework for the automatic recognition of complex multi-agent events in settings where structure is imposed by rules that agents must follow while performing activit...
Nearly every structured prediction problem in computer vision requires approximate inference due to large and complex dependencies among output labels. While graphical models prov...
Without specialized sensor technology or custom, multichip cameras, high dynamic range imaging typically involves time-sequential capture of multiple photographs. The obvious down...
Mushfiqur Rouf, Rafal Mantiuk, Wolfgang Heidrich, ...