This paper introduces an updated version of the well-known Virtual KITTI dataset which
consists of 5 sequence clones from the KITTI tracking benchmark. In addition, the dataset …

Test datasets should contain many different challenging aspects so that the robustness and
real-world applicability of algorithms can be assessed. In this work, we present a new test …

Mirrors generally lack a consistent visual appearance, making mirror detection very
challenging. Although recent works that are based on exploiting contextual contrasts and …

Glass surfaces are omnipresent in our daily lives and often go unnoticed by the majority of
us. While humans are generally able to infer their locations and thus avoid collisions, it can …

The mirror detection problem is important as mirrors can affect the performances of many
vision tasks. It is a difficult problem as it requires an understanding of global scene …

Mirror detection aims to identify the mirror regions in the given input image. Existing works
mainly focus on integrating the semantic features and structural features to mine specific …

Due to the impressive performance of deep neural networks (DNNs) for visual perception,
there is an increased demand for their use in automated systems. However, to use deep …

Label-free model evaluation, or AutoEval, estimates model accuracy on unlabeled test sets,
and is critical for understanding model behaviors in various unseen environments. In the …

Intuitively, unfamiliarity should lead to lack of confidence. In reality, current algorithms often
make highly confident yet wrong predictions when faced with relevant but unfamiliar …

A reliable stereo algorithm is critical for many robotics applications. But textureless and
specular regions can easily cause failure by making feature matching difficult …