We study the problem of recovering an underlying 3D shape from a set of images. Existing
learning based approaches usually resort to recurrent neural nets, eg, GRU, or intuitive …

Data augmentation has contributed to the rapid advancement of unsupervised learning on
3D point clouds. However, we argue that data augmentation is not ideal, as it requires a …

Depth-based reconstruction of three-dimensional (3D) shape of objects is one of core
problems in computer vision with a lot of commercial applications. However, the 3D …

Skeletonization algorithms are used as basic methods to solve tracking problems, pose
estimation, or predict animal group behavior. Traditional skeletonization techniques, based …

We present TransProteus, a dataset, and methods for predicting the 3D structure,
annotations and properties of materials inside transparent vessels from a single image …

The objective of our work is to reconstruct 3D object instances from a single RGB image of a
cluttered scene. 3D object instance reconstruction is an ill-posed problem due to the …

We present TransProteus, a dataset, and methods for predicting the 3D structure, masks,
and properties of materials, liquids, and objects inside transparent vessels from a single …

With the increasing popularity of wind turbines, the demand for integrity detecting of wind
turbines operating in natural or extreme environments is also increasing. To better detect the …

This thesis first introduces the basic principles of model‐based image sequence coding
technology, then discusses in detail the specific steps in various implementation algorithms …

Automation of chemistry experiments is a promising method for accelerating material
discovery, and has shown significant progress from existing researches. Among the …