Recently, the coronavirus disease 2019 (COVID-19) has caused a pandemic disease in
over 200 countries, influencing billions of humans. To control the infection, identifying and …

Recent work has shown that CNN-based depth and ego-motion estimators can be learned
using unlabelled monocular videos. However, the performance is limited by unidentified …

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

We introduce a comprehensive benchmark for local features and robust estimation
algorithms, focusing on the downstream task—the accuracy of the reconstructed camera …

Establishing correspondences between two images requires both local and global spatial
context. Given putative correspondences of feature points in two views, in this paper, we …

This work focuses on mitigating two limitations in the joint learning of local feature detectors
and descriptors. First, the ability to estimate the local shape (scale, orientation, etc.) of …

Matching local features across images is a fundamental problem in computer vision.
Targeting towards high accuracy and efficiency, we propose Seeded Graph Matching …

Incorporating smoothness constraints into feature matching is known to enable ultra-robust
matching. However, such formulations are both complex and slow, making them unsuitable …

Person re-identification (Re-ID) has achieved great improvement with deep learning and a
large amount of labelled training data. However, it remains a challenging task for adapting a …

We propose MAGSAC++ and Progressive NAPSAC sampler, P-NAPSAC in short. In
MAGSAC++, we replace the model quality and polishing functions of the original method by …