While state-of-the-art monocular depth estimation approaches achieve impressive results in
ideal settings, they are highly unreliable under challenging illumination and weather …

For robots to navigate and interact more richly with the world around them, they will likely
require a deeper understanding of the world in which they operate. In robotics and related …

Autonomous systems possess the features of inferring their own state, understanding their
surroundings, and performing autonomous navigation. With the applications of learning …

Monocular depth estimation aims at predicting depth from a single image or video. Recently,
self-supervised methods draw much attention since they are free of depth annotations and …

Remarkable results have been achieved by DCNN based self-supervised depth estimation
approaches. However, most of these approaches can only handle either day-time or night …

Self-supervised depth estimation draws a lot of attention recently as it can promote the 3D
sensing capa-bilities of self-driving vehicles. However, it intrinsically relies upon the …

With the development of computational intelligence algorithms, unsupervised monocular
depth and pose estimation framework, which is driven by warped photometric consistency …

Recently, IMUTube introduced a paradigm change for bootstrapping human activity
recognition (HAR) systems for wearables. The key idea is to utilize videos of activities to …

Self-supervised monocular depth estimation (MDE) models universally suffer from the
notorious edge-fattening issue. Triplet loss, popular for metric learning, has made a great …

This paper discusses the results of the third edition of the Monocular Depth Estimation
Challenge (MDEC). The challenge focuses on zero-shot generalization to the challenging …