To the best of our knowledge, the most recent light detection and ranging (lidar)-based
surveys have been focused only on specific applications such as reconstruction and …

Monocular depth estimation is vital for scene understanding and downstream tasks. We
focus on the supervised setup, in which ground-truth depth is available only at training time …

Monocular depth prediction plays a crucial role in understanding 3D scene geometry.
Although recent methods have achieved impressive progress in evaluation metrics such as …

Rapid advances in 2D perception have led to systems that accurately detect objects in real-
world images. However, these systems make predictions in 2D, ignoring the 3D structure of …

Access to large, diverse RGB-D datasets is critical for training RGB-D scene understanding
algorithms. However, existing datasets still cover only a limited number of views or a …

Self-supervised learning aims to learn representations from the data itself without explicit
manual supervision. Existing efforts ignore a crucial aspect of self-supervised learning-the …

While convolutional neural networks have shown a tremendous impact on various computer
vision tasks, they generally demonstrate limitations in explicitly modeling long-range …

A key requirement for leveraging supervised deep learning methods is the availability of
large, labeled datasets. Unfortunately, in the context of RGB-D scene understanding, very …

Generation of 3D data by deep neural network has been attracting increasing attention in
the research community. The majority of extant works resort to regular representations such …

In this paper, we propose a novel Pattern-Affinitive Propagation (PAP) framework to jointly
predict depth, surface normal and semantic segmentation. The motivation behind it comes …