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 Article
Crowdsourcing annotations for visual object detection
Hao Su,Jia Deng,Li Fei-Fei +2 more
TL;DR: The key observation is that drawing a bounding box is significantly more difficult and time consuming than giving answers to multiple choice questions, so quality control through additional verification tasks is more cost effective than consensus based algorithms.
Proceedings ArticleDOI
Point-Based Multi-View Stereo Network
TL;DR: Point-MVSNet as discussed by the authors predicts the depth in a coarse-to-fine manner by generating a coarse depth map, converting it into a point cloud and refining the point cloud iteratively by estimating the residual between the depth of the current iteration and the ground truth.
Proceedings ArticleDOI
TensoRF: Tensorial Radiance Fields
TL;DR: TensoRF is presented, a novel approach to model and reconstruct radiance fields as a 4D tensor, which represents a 3D voxel grid with per-voxel multi-channel features, and a novel vector-matrix (VM) decomposition that relaxes the low-rank constraints for two modes of a tensor and factorizes tensors into compact vector and matrix factors.
Proceedings ArticleDOI
Synthesizing Training Images for Boosting Human 3D Pose Estimation
Wenzheng Chen,Huan Wang,Yangyan Li,Hao Su,Zhenhua Wang,Changhe Tu,Dani Lischinski,Daniel Cohen-Or,Baoquan Chen +8 more
TL;DR: In this paper, a fully automatic, scalable approach that samples the human pose space for guiding the synthesis procedure and extracts clothing textures from real images is presented. But this approach is not suitable for 3D pose estimation, since 3D poses are much harder to annotate.
Posted Content
FPNN: Field Probing Neural Networks for 3D Data
TL;DR: This work represents 3D spaces as volumetric fields, and proposes a novel design that employs field probing filters to efficiently extract features from them, showing that field probing is significantly more efficient than 3DCNNs, while providing state-of-the-art performance, on classification tasks for 3D object recognition benchmark datasets.