Dense prediction tasks typically employ encoder-decoder architectures, b...
Direct prediction of 3D body pose and shape remains a challenge even for...
In this work, we propose a technique to convert CNN models for semantic
...
Existing marker-less motion capture methods often assume known backgroun...
We present the first image-based generative model of people in clothing ...
3D models provide a common ground for different representations of human...
We propose a technique that propagates information forward through video...
Separating an image into reflectance and shading layers poses a challeng...
This paper introduces a fast and efficient segmentation technique for 2D...
Bilateral filters have wide spread use due to their edge-preserving
prop...
This paper presents a convolutional layer that is able to process sparse...
Computer vision is hard because of a large variability in lighting, shap...