1 citations · 1 across the 3 of their papers we have counts for
4 papers
Learning to Register Unbalanced Point Pairs
Kanghee Lee, Junha Lee, Jaesik Park
Point cloud registration methods can effectively handle large-scale, partially overlapping point cloud pairs. Despite its practicality, matching the unbalanced pairs in terms of sp…
Putting 3D Spatially Sparse Networks on a Diet
Junha Lee, Christopher Choy, Jaesik Park
3D neural networks have become prevalent for many 3D vision tasks including object detection, segmentation, registration, and various perception tasks for 3D inputs. However, due t…
Deep Hough Voting for Robust Global Registration
Junha Lee, Seungwook Kim, Minsu Cho +1
Point cloud registration is the task of estimating the rigid transformation that aligns a pair of point cloud fragments. We present an efficient and robust framework for pairwise r…
High-dimensional Convolutional Networks for Geometric Pattern Recognition
Christopher Choy, Junha Lee, Rene Ranftl +2
Many problems in science and engineering can be formulated in terms of geometric patterns in high-dimensional spaces. We present high-dimensional convolutional networks (ConvNets)…