Learning-based surface reconstruction based on unsigned distance functio...
Multi-output deep neural networks(MONs) contain multiple task branches, ...
Most learning-based approaches to category-level 6D pose estimation are
...
Learning-based multi-view stereo (MVS) has by far centered around 3D
con...
Context has proven to be one of the most important factors in object lay...
With the large-scale deployment of industrial internet of things (IIoT)
...
We introduce the concept of geometric stability to the problem of 6D obj...
We study the problem of symmetry detection of 3D shapes from single-view...
In depth-sensing applications ranging from home robotics to AR/VR, it wi...
Indoor scenes exhibit rich hierarchical structure in 3D object layouts. ...
We introduce a novel RGB-D patch descriptor designed for detecting copla...
Active vision is inherently attention-driven: The agent selects views of...