We introduce TextureNet, a neural network architecture designed to extract features from high-resolution signals associated with 3D surface meshes (e.g., color texture maps).
We present a new, practical method that can reliably identify background features in complex video, leading to accurate camera path estimation and background layering.
We propose an image-based clothes changing system, exploiting body factor extraction and content-aware image warping.Paper
We introduce Rekall, a library that exposes a data model and programming model for compositional video event specification.Arxiv
We are aimed to determine the swimming motion pattern of an extinct species -- Eurypterid. Our final result provide evidence for supporting one of the swimming motion hypothesis.