R
Ronald Yu
Researcher at University of California, San Diego
Publications - 20
Citations - 1239
Ronald Yu is an academic researcher from University of California, San Diego. The author has contributed to research in topics: Deep learning & Artificial neural network. The author has an hindex of 13, co-authored 20 publications receiving 824 citations. Previous affiliations of Ronald Yu include University of Southern California.
Papers
More filters
Proceedings ArticleDOI
SGPN: Similarity Group Proposal Network for 3D Point Cloud Instance Segmentation
TL;DR: This work introduces Similarity Group Proposal Network (SGPN), a simple and intuitive deep learning framework for 3D object instance segmentation on point clouds that uses a single network to predict point grouping proposals and a corresponding semantic class for each proposal.
Proceedings ArticleDOI
Production-level facial performance capture using deep convolutional neural networks
Samuli Laine,Tero Karras,Timo Aila,Antti Herva,Shunsuke Saito,Ronald Yu,Hao Li,Jaakko Lehtinen +7 more
TL;DR: A real-time deep learning framework for video-based facial performance capture---the dense 3D tracking of an actor's face given a monocular video, which can drastically reduce the amount of labor involved in the development of modern narrative-driven video games or films involving realistic digital doubles of actors and potentially hours of animated dialogue per character.
Proceedings ArticleDOI
Realistic Dynamic Facial Textures from a Single Image Using GANs
Kyle Olszewski,Zimo Li,Chao Yang,Yi Zhou,Ronald Yu,Zeng Huang,Sitao Xiang,Shunsuke Saito,Pushmeet Kohli,Hao Li +9 more
TL;DR: A Deep Generative Network is trained that can infer realistic per-frame texture deformations of the target identity using the per-frames source textures and the single target texture, and can both animate the face and perform video face replacement on the source video using the target appearance.
Posted Content
Extending Adversarial Attacks and Defenses to Deep 3D Point Cloud Classifiers
Daniel F. Liu,Ronald Yu,Hao Su +2 more
TL;DR: Overall, it is found that 3D point cloud classifiers are weak to adversarial attacks, but they are also more easily defensible compared to 2D image classifiers.
Proceedings ArticleDOI
Extending Adversarial Attacks and Defenses to Deep 3D Point Cloud Classifiers
Daniel F. Liu,Ronald Yu,Hao Su +2 more
TL;DR: In this article, a preliminary evaluation of adversarial attacks on 3D point cloud classifiers was conducted by evaluating 2D images, and extending those attacks to reduce the perceptibility of the perturbations in 3D space.