Recent progress in deep learning has led to accurate and efficient generic object detection
networks. Training of highly reliable models depends on large datasets with highly textured …

The construction of a twin model with high fidelity, real-time map** and scalability is the
foundation for realizing digital twin in underground space. Given the large size and …

In this paper, we present a systematic review and evaluation of existing single-image low-
light enhancement algorithms. Besides the commonly used low-level vision oriented …

Challenging illumination conditions (low-light, under-exposure and over-exposure) in the
real world not only cast an unpleasant visual appearance but also taint the computer vision …

Previous advances in object tracking mostly reported on favorable illumination
circumstances while neglecting performance at nighttime, which significantly impeded the …

Dark environment becomes a challenge for computer vision algorithms owing to insufficient
photons and undesirable noises. Most of the existing studies tackle this by either targeting …

Existing instance segmentation techniques are primarily tailored for high-visibility inputs, but
their performance significantly deteriorates in extremely low-light environments. In this work …

Universal domain adaptation (UniDA) aims to transfer the knowledge learned from a label-
rich source domain to a label-scarce target domain without any constraints on the label …

Sports involve commonly players and equipment of high dynamics. Their location and
motion data are essential for sports digitalization-related applications, such as from …

A practical low-light enhancement solution must be computationally fast, memory-efficient,
and achieve a visually appealing restoration. Most of the existing methods target restoration …