Generating robust and reliable correspondences across images is a fundam...
In this paper, we introduce a novel network, called discriminative featu...
Current bundle adjustment solvers such as the Levenberg-Marquardt (LM)
a...
Recent learning-based approaches, in which models are trained by single-...
Semantic segmentation and semantic edge detection can be seen as two dua...
In this paper, we present a joint multi-task learning framework for sema...
Temporal camera relocalization estimates the pose with respect to each v...
Semantic segmentation is pixel-wise classification which retains critica...
Critical to the registration of point clouds is the establishment of a s...