H
Hao Su
Researcher at University of California, San Diego
Publications - 364
Citations - 82843
Hao Su is an academic researcher from University of California, San Diego. The author has contributed to research in topics: Computer science & Point cloud. The author has an hindex of 57, co-authored 302 publications receiving 55902 citations. Previous affiliations of Hao Su include Philips & Jiangxi University of Science and Technology.
Papers
More filters
Proceedings ArticleDOI
Improving Policy Optimization with Generalist-Specialist Learning
TL;DR: This work investigates the timing to start specialist training and compares strategies to learn generalists with assistance from specialists and shows that this framework pushes the envelope of policy learning on several challenging and popular benchmarks including Procgen, Meta-World and ManiSkill.
Book ChapterDOI
Adversarial Shape Perturbations on 3D Point Clouds
Daniel F. Liu,Ronald Yu,Hao Su +2 more
TL;DR: Liu et al. as mentioned in this paper explored three possible shape attacks for attacking 3D point cloud classification and showed that some of them are able to be effective even against preprocessing steps, like the previously proposed point-removal defenses.
Journal ArticleDOI
Propagation-Instigated Self-Limiting Polymerization of Multiarmed Amphiphiles into Finite Supramolecular Polymers.
TL;DR: In this article, a self-limiting supramolecular polymerization (SPZ) of a series of multiarmed amphiphiles with propagationattenuated reactivities that can automatically terminate the polymerization process is described.
Posted Content
Lipschitz Regularized CycleGAN for Improving Semantic Robustness in Unpaired Image-to-image Translation.
TL;DR: This paper proposes a novel approach, Lipschitz regularized CycleGAN, for improving semantic robustness and thus alleviating the semantic flipping issue, and adds a gradient penalty loss to the generators, which encourages semantically consistent transformations.
Posted Content
MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereo
TL;DR: MVSNeRF as discussed by the authors proposes a generic deep neural network that can reconstruct radiance fields from only three nearby input views via fast network inference, leveraging plane-swept cost volumes (widely used in multi-view stereo) for geometry-aware scene reasoning.