In recent years, tremendous progress has been made in surgical practice for example with
Minimally Invasive Surgery (MIS). To overcome challenges coming from deported eye-to …

We present a fast inverse-graphics framework for instance-level 3D scene understanding.
We train a deep convolutional network that learns to map image regions to the full 3D shape …

We formulate a probabilistic framework for simultaneous region-based 2D segmentation and
2D to 3D pose tracking, using a known 3D model. Given such a model, we aim to maximise …

The design and manipulation of typefaces and fonts is an area requiring substantial
expertise; it can take many years of study to become a proficient typographer. At the same …

We propose a formulation of monocular SLAM which combines live dense reconstruction
with shape priors-based 3D tracking and reconstruction. Current live dense SLAM …

We address the problem of 3D shape completion from sparse and noisy point clouds, a
fundamental problem in computer vision and robotics. Recent approaches are either data …

We present a novel end-to-end framework named as GSNet (G eometric and S cene-aware
Net work), which jointly estimates 6DoF poses and reconstructs detailed 3D car shapes from …

Estimating the 3-D pose of instruments is an important part of robotic minimally invasive
surgery for automation of basic procedures as well as providing safety features, such as …

In this paper we introduce a new shape-driven approach for object segmentation. Given a
training set of shapes, we first use deep Boltzmann machine to learn the hierarchical …

Image based applications such as target tracking, tumor detection, texture extraction
requires an efficient image segmentation process. The partitioning of image into various non …