S
Shi-Min Hu
Researcher at Tsinghua University
Publications - 330
Citations - 16809
Shi-Min Hu is an academic researcher from Tsinghua University. The author has contributed to research in topics: Computer science & Image segmentation. The author has an hindex of 54, co-authored 321 publications receiving 13301 citations. Previous affiliations of Shi-Min Hu include Microsoft & Beihang University.
Papers
More filters
Proceedings ArticleDOI
Lidar-Monocular Visual Odometry using Point and Line Features
TL;DR: This work introduces a novel lidar-monocular visual odometry approach using point and line features that achieves more accurate pose estimation than the state-of-the-art approaches, and is sometimes even better than those leveraging semantic information.
Proceedings ArticleDOI
MultiBodySync: Multi-Body Segmentation and Motion Estimation via 3D Scan Synchronization
Jiahui Huang,He Wang,Tolga Birdal,Minhyuk Sung,Federica Arrigoni,Shi-Min Hu,Leonidas J. Guibas +6 more
TL;DR: MultiBodySync as discussed by the authors proposes an end-to-end trainable multi-body motion segmentation and rigid registration framework for multiple input 3D point clouds, which incorporates spectral synchronization into an iterative deep declarative network.
Journal ArticleDOI
An extension algorithm for B-splines by curve unclamping
TL;DR: A new algorithm for extending B-spline curves that extrapolates using the recurrence property of the de Boor algorithm is proposed that provides a nice extension, with maximum continuity, to the original curve segment.
Journal ArticleDOI
A unified particle system framework for multi-phase, multi-material visual simulations
TL;DR: A unified particle framework which integrates the phase-field method with multi-material simulation to allow modeling of both liquids and solids, as well as phase transitions between them, and provides the first method in computer graphics capable of modeling a continuous interface between phases.
Journal ArticleDOI
Faithful Completion of Images of Scenic Landmarks Using Internet Images
TL;DR: This paper proposes an approach to faithfully complete the missing regions of an image that assumes that the input image is taken at a well-known landmark, so similar images taken at the same location can be easily found on the Internet.