Depth information is important for autonomous systems to perceive environments and
estimate their own state. Traditional depth estimation methods, like structure from motion …

Stereo matching is one of the longest-standing problems in computer vision with close to 40
years of studies and research. Throughout the years the paradigm has shifted from local …

Self-supervised monocular depth estimation is an attractive solution that does not require
hard-to-source depth la-bels for training. Convolutional neural networks (CNNs) have …

Per-pixel ground-truth depth data is challenging to acquire at scale. To overcome this
limitation, self-supervised learning has emerged as a promising alternative for training …

Self-supervised paradigms for monocular depth estimation are very appealing since they do
not require ground truth annotations at all. Despite the astonishing results yielded by such …

Monocular depth estimation has become one of the most studied applications in computer
vision, where the most accurate approaches are based on fully supervised learning models …

Monocular depth estimators can be trained with various forms of self-supervision from
binocular-stereo data to circumvent the need for high-quality laser-scans or other ground …

Deep convolutional neural networks trained end-to-end are the state-of-the-art methods to
regress dense disparity maps from stereo pairs. These models, however, suffer from a …

Depth estimation from a single image represents a fascinating, yet challenging problem with
countless applications. Recent works proved that this task could be learned without direct …

Existing self-supervised monocular depth estimation methods can get rid of expensive
annotations and achieve promising results. However, these methods suffer from severe …