11 datasets found

The dataset used for monocular depth estimation task

The dataset used for monocular depth estimation task

Hand segmentation for hand-object interaction using only a depth map

The dataset used for testing the HandVoxNet approach for 3D hand shape and pose estimation from a single depth map.

The NYU dataset contains 1449 depth maps captured by Kinect.

The SUNCG dataset is a manually created large-scale synthetic scene dataset. It contains 139368 valid pairs of depth map and complete labels for training, and 470 pairs for...

Guided depth super-resolution (GDSR) involves restor- ing missing depth details using the high-resolution RGB image of the same scene.

The NYUv2 dataset is a large-scale dataset for 3D object recognition and semantic segmentation. It contains 206 test set video sequences with 135 classes.

Guided depth super-resolution (GDSR) involves restor- ing missing depth details using the high-resolution RGB image of the same scene.

Guided depth super-resolution (GDSR) involves restor- ing missing depth details using the high-resolution RGB image of the same scene.

Feature matching is a fundamental problem for many computer vision tasks, such as object recognition, structure from motion, and simultaneous localization and mapping.