ABSTRACT 3D reconstruction plays an increasingly important role in modern
photogrammetric systems. Conventional satellite or aerial-based remote sensing (RS) …

Omnidirectional images and videos are widespread due to the popularization of devices for
capturing and visualization. Unlike pinhole-based imagery, omnidirectional media lie on the …

In this paper, we formulate a potentially valuable panoramic depth completion (PDC) task as
panoramic 3D cameras often produce 360∘ depth with missing data in complex scenes. Its …

Estimating the depths of equirectangular (ie, 360) images (EIs) is challenging given the
distorted 180 x 360 field-of-view, which is hard to be addressed via convolutional neural …

RGB-D data is essential for solving many problems in computer vision. Hundreds of public
RGB-D datasets containing various scenes, such as indoor, outdoor, aerial, driving, and …

Standard MSE or MAE loss function is commonly used in limited field-of-vision depth
completion, treating each pixel equally under a basic assumption that all pixels have same …

In this article, we investigate the problem of panoramic image reflection removal to relieve
the content ambiguity between the reflection layer and the transmission scene. Although a …

Monocular depth estimation is an ambiguous problem, thus global structural cues play an
important role in current data-driven single-view depth estimation methods. Panorama …

The absolute depth values of surrounding environments provide crucial cues for various
assistive technologies, such as localization, navigation, and 3D structure estimation. We …

Recent research in robotic proxies has demonstrated that one can automatically reproduce
many non-verbal cues important in co-located collaboration. However, they often require a …