Semantic image segmentation (SiS) plays a fundamental role in a broad variety of computer
vision applications, providing key information for the global understanding of an image. This …

Estimating depth from single RGB images and videos is of widespread interest due to its
applications in many areas, including autonomous driving, 3D reconstruction, digital …

Depth estimation is a challenging task of 3D reconstruction to enhance the accuracy sensing
of environment awareness. This work brings a new solution with improvements, which …

Local Transformer-based classification models have recently achieved promising results
with relatively low computational costs. However, the effect of aggregating spatial global …

In the past two decades, there has been a lot of work on computer vision technology that
incorporates many tasks which implement basic filtering to image classification. The major …

Depth map super-resolution is a task with high practical application requirements in the
industry. Existing color-guided depth map super-resolution methods usually necessitate an …

Human beings can recognize new objects with only a few labeled examples, however, few-
shot learning remains a challenging problem for machine learning systems. Most previous …

Multi-task approaches to joint depth and segmentation prediction are well-studied for
monocular images. Yet, predictions from a single-view are inherently limited, while multiple …

Quantifying the predictive uncertainty emerged as a possible solution to common challenges
like overconfidence or lack of explainability and robustness of deep neural networks, albeit …

In this paper, we propose a dual-module network architecture that employs a domain
discriminative feature module to encourage the domain invariant feature module to learn …