activity
20152023
most citedPointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space

2.1k citations · 2.9k across the 82 of their papers we have counts for

collaborators
Showing 2016 · cs.CVShow all

7 papers · 2 filters

cs.CV2016★ 7 cited

Beyond Holistic Object Recognition: Enriching Image Understanding with Part States

Cewu Lu, Hao Su, Yongyi Lu +3

Important high-level vision tasks such as human-object interaction, image captioning and robotic manipulation require rich semantic descriptions of objects at part level. Based upo…

cs.CV2016★ 54 cited

A Point Set Generation Network for 3D Object Reconstruction from a Single Image

Haoqiang Fan, Hao Su, Leonidas Guibas

Generation of 3D data by deep neural network has been attracting increasing attention in the research community. The majority of extant works resort to regular representations such…

cs.CV2016★ 41 cited

SyncSpecCNN: Synchronized Spectral CNN for 3D Shape Segmentation

Li Yi, Hao Su, Xingwen Guo +1

In this paper, we study the problem of semantic annotation on 3D models that are represented as shape graphs. A functional view is taken to represent localized information on graph…

cs.CV2016

PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation

Charles R. Qi, Hao Su, Kaichun Mo +1

Point cloud is an important type of geometric data structure. Due to its irregular format, most researchers transform such data to regular 3D voxel grids or collections of images.…

cs.CV2016

Learning Shape Abstractions by Assembling Volumetric Primitives

Shubham Tulsiani, Hao Su, Leonidas J. Guibas +2

We present a learning framework for abstracting complex shapes by learning to assemble objects using 3D volumetric primitives. In addition to generating simple and geometrically in…

cs.CV2016

FPNN: Field Probing Neural Networks for 3D Data

Yangyan Li, Soeren Pirk, Hao Su +2

Building discriminative representations for 3D data has been an important task in computer graphics and computer vision research. Convolutional Neural Networks (CNNs) have shown to…