Object detection or localization is an incremental step in progression from coarse to fine
digital image inference. It not only provides the classes of the image objects, but also …

The machine learning community has been overwhelmed by a plethora of deep learning--
based approaches. Many challenging computer vision tasks, such as detection, localization …

Image guided depth completion is the task of generating a dense depth map from a sparse
depth map and a high quality image. In this task, how to fuse the color and depth modalities …

Spatial pooling has been proven highly effective to capture long-range contextual
information for pixel-wise prediction tasks, such as scene parsing. In this paper, beyond …

In this paper, we propose a robust and efficient end-to-end non-local spatial propagation
network for depth completion. The proposed network takes RGB and sparse depth images …

Current state-of-the-art methods for image segmentation form a dense image representation
where the color, shape and texture information are all processed together inside a deep …

Full-image dependencies provide useful contextual information to benefit visual
understanding problems. In this work, we propose a Criss-Cross Network (CCNet) for …

In the stereo matching task, matching cost aggregation is crucial in both traditional methods
and deep neural network models in order to accurately estimate disparities. We propose two …

Existing semantic segmentation approaches either aim to improve the object's inner
consistency by modeling the global context, or refine objects detail along their boundaries …

Unsupervised domain adaptation without accessing expensive annotation processes of
target data has achieved remarkable successes in semantic segmentation. However, most …