Visual Computing

We present a geometric calibration method to accurately register a galvanoscopic scanning laser projection system (GLP) based on 2D vector input data onto an arbitrarily complex 3D-shaped projection surface.

We introduce a spatial pyramid-like structure to the image and learn CNNs for image sub-regions at different scales.

We propose the use of a fully automatic soft color segmentation algorithm for content generation for such an augmented reality application.

We present two novel unbiased techniques for sampling free paths in heterogeneous participating media.

We present the potential of computational intelligence to empower authors and content creators in creating their own interactive animated stories.

Our system allows the user to act several loops of motion using a variety of capture devices and automatically extracts a looping cycle from this potentially noisy input.

We present a novel, purely affinity-based natural image matting algorithm.

We propose a novel calibration method based on the usage of directionally encoded light rays for estimating the intrinsic parameters.

We demonstrate that highly accurate object segmentation in videos can be enabled by using a convolutional neural network (convnet) trained with static images only.

The proposed one-shot learning achieves performance that is competitive with supervised methods but uses only a single example rather than the hundreds required for the fully supervised case.