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...
Most methods for object class segmentation are formulated as a labelling problem over a single choice of quantisation of an image space - pixels, segments or group of segments. It...
Lubor Ladicky, Christopher Russell, Pushmeet Kohli...
State-of-the-art methods have recently achieved impressive performance for recognising the objects present in large databases of pre-collected images. There has been much less foc...
Spatial objects other than points and boxes can be stored in spatial indexes, but the techniques usually require the use of approximations that can be arbitrarily bad. This leads ...
Generating soft shadows in real time is difficult. Exact methods (such as ray tracing, and multiple light source simulation) are too slow, while approximate methods often overesti...
Xiao-Hua Cai, Yun-Tao Jia, Xi Wang, Shi-Min Hu, Ra...