Computer Vision

We present several mixed reality based remote collaboration settings by using consumer head-mounted displays, including an AR system linked with an AR system, a VR system with virtual body, a VR system without virtual body and a desktop computer.

In this paper, we propose a depth image and video codec based on block compression, that exploits typical characteristics of depth streams, drawing inspiration from S3TC texture compression and geometric wavelets.

We propose Paxel, a generic framework for modeling the interaction between a projector and a high-frequency pattern surface.

We propose an end-to-end solution for presenting movie quality animated graphics to the user while still allowing the sense of presence afforded by free viewpoint head motion.

In this paper, we propose to learn appearance measures for patches that are combined using deformable models.

We evaluated the proposed methods using more than ten multi-projection datasets ranging from a toy castle set up consisting of three cameras and one projector up to a half dome display system with more than 30 devices.

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.

We propose a weakly-supervised approach that takes image-sentence pairs as input and learns to visually ground (i.e., localize) arbitrary linguistic phrases, in the form of spatial attention masks.

In this paper, we study non-linear tensor factorization methods based on deep variational autoencoders.