Hao Su

is this you? claim profile

∙ 0 followers
University of California, San Diego ∙ Stanford University

Assistant Professor at University of California San Diego

O2O-Afford: Annotation-Free Large-Scale Object-Object Affordance Learning

Contrary to the vast literature in modeling, perceiving, and understandi...
06/29/2021 ∙ by Kaichun Mo, et al. ∙ 2 ∙ share

read it
Particle Cloud Generation with Message Passing Generative Adversarial Networks

In high energy physics (HEP), jets are collections of correlated particl...
06/22/2021 ∙ by Raghav Kansal, et al. ∙ 0 ∙ share

read it
One-shot Learning with Absolute Generalization

One-shot learning is proposed to make a pretrained classifier workable o...
05/28/2021 ∙ by Hao Su, et al. ∙ 0 ∙ share

read it
OCRTOC: A Cloud-Based Competition and Benchmark for Robotic Grasping and Manipulation

In this paper, we propose a cloud-based benchmark for robotic grasping a...
04/23/2021 ∙ by Ziyuan Liu, et al. ∙ 0 ∙ share

read it
CAPTRA: CAtegory-level Pose Tracking for Rigid and Articulated Objects from Point Clouds

In this work, we tackle the problem of category-level online pose tracki...
04/08/2021 ∙ by Yijia Weng, et al. ∙ 5 ∙ share

read it
PlasticineLab: A Soft-Body Manipulation Benchmark with Differentiable Physics

Simulated virtual environments serve as one of the main driving forces b...
04/07/2021 ∙ by Zhiao Huang, et al. ∙ 7 ∙ share

read it
GNeRF: GAN-based Neural Radiance Field without Posed Camera

We introduce GNeRF, a framework to marry Generative Adversarial Networks...
03/29/2021 ∙ by Quan Meng, et al. ∙ 21 ∙ share

read it
MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereo

We present MVSNeRF, a novel neural rendering approach that can efficient...
03/29/2021 ∙ by Anpei Chen, et al. ∙ 0 ∙ share

read it
NeuTex: Neural Texture Mapping for Volumetric Neural Rendering

Recent work has demonstrated that volumetric scene representations combi...
03/01/2021 ∙ by Fanbo Xiang, et al. ∙ 0 ∙ share

read it
DeepMetaHandles: Learning Deformation Meta-Handles of 3D Meshes with Biharmonic Coordinates

We propose DeepMetaHandles, a 3D conditional generative model based on m...
02/18/2021 ∙ by Minghua Liu, et al. ∙ 0 ∙ share

read it
Design and Actuator Optimization of Lightweight and Compliant Knee Exoskeleton for Mobility Assistance of Children with Crouch Gait

Pediatric exoskeletons offer great promise to increase mobility for chil...
01/01/2021 ∙ by Sainan Zhang, et al. ∙ 0 ∙ share

read it
Medical Robots for Infectious Diseases: Lessons and Challenges from the COVID-19 Pandemic

Medical robots can play an important role in mitigating the spread of in...
12/14/2020 ∙ by Antonio Di Lallo, et al. ∙ 0 ∙ share

read it
Lipschitz Regularized CycleGAN for Improving Semantic Robustness in Unpaired Image-to-image Translation

For unpaired image-to-image translation tasks, GAN-based approaches are ...
12/09/2020 ∙ by Zhiwei Jia, et al. ∙ 0 ∙ share

read it
Compositionally Generalizable 3D Structure Prediction

Single-image 3D shape reconstruction is an important and long-standing p...
12/04/2020 ∙ by Songfang Han, et al. ∙ 11 ∙ share

read it
An End-to-end Method for Producing Scanning-robust Stylized QR Codes

Quick Response (QR) code is one of the most worldwide used two-dimension...
11/16/2020 ∙ by Hao Su, et al. ∙ 32 ∙ share

read it
Rearrangement: A Challenge for Embodied AI

We describe a framework for research and evaluation in Embodied AI. Our ...
11/03/2020 ∙ by Dhruv Batra, et al. ∙ 2 ∙ share

read it
Refactoring Policy for Compositional Generalizability using Self-Supervised Object Proposals

We study how to learn a policy with compositional generalizability. We p...
10/26/2020 ∙ by Tongzhou Mu, et al. ∙ 0 ∙ share

read it
Towards Scale-Invariant Graph-related Problem Solving by Iterative Homogeneous Graph Neural Networks

Current graph neural networks (GNNs) lack generalizability with respect ...
10/26/2020 ∙ by Hao Tang, et al. ∙ 0 ∙ share

read it
Photon-Driven Neural Path Guiding

Although Monte Carlo path tracing is a simple and effective algorithm to...
10/05/2020 ∙ by Shilin Zhu, et al. ∙ 0 ∙ share

read it
Weakly-supervised 3D Shape Completion in the Wild

3D shape completion for real data is important but challenging, since pa...
08/20/2020 ∙ by Jiayuan Gu, et al. ∙ 11 ∙ share

read it
Deep Keypoint-Based Camera Pose Estimation with Geometric Constraints

Estimating relative camera poses from consecutive frames is a fundamenta...
07/29/2020 ∙ by You-Yi Jau, et al. ∙ 1 ∙ share

read it
Balance Scene Learning Mechanism for Offshore and Inshore Ship Detection in SAR Images

This letter proposes a novel Balance Scene Learning Mechanism (BSLM) for...
07/21/2020 ∙ by Tianwen Zhang, et al. ∙ 0 ∙ share

read it
Meshing Point Clouds with Predicted Intrinsic-Extrinsic Ratio Guidance

We are interested in reconstructing the mesh representation of object su...
07/17/2020 ∙ by Minghua Liu, et al. ∙ 0 ∙ share

read it
Rethinking Sampling in 3D Point Cloud Generative Adversarial Networks

In this paper, we examine the long-neglected yet important effects of po...
06/12/2020 ∙ by He Wang, et al. ∙ 10 ∙ share

read it
Deep Photon Mapping

Recently, deep learning-based denoising approaches have led to dramatic ...
04/25/2020 ∙ by Shilin Zhu, et al. ∙ 0 ∙ share

read it
Unpaired Photo-to-manga Translation Based on The Methodology of Manga Drawing

Manga is a world popular comic form originated in Japan, which typically...
04/22/2020 ∙ by Hao Su, et al. ∙ 0 ∙ share

read it
Quasi-Direct Drive Actuation for a Lightweight Hip Exoskeleton with High Backdrivability and High Bandwidth

High-performance actuators are crucial to enable mechanical versatility ...
04/01/2020 ∙ by Shuangyue Yu, et al. ∙ 0 ∙ share

read it
SAPIEN: A SimulAted Part-based Interactive ENvironment

Building home assistant robots has long been a pursuit for vision and ro...
03/19/2020 ∙ by Fanbo Xiang, et al. ∙ 7 ∙ share

read it
Learning to Group: A Bottom-Up Framework for 3D Part Discovery in Unseen Categories

We address the problem of discovering 3D parts for objects in unseen cat...
02/16/2020 ∙ by Tiange Luo, et al. ∙ 11 ∙ share

read it
Regret Bounds for Discounted MDPs

Recently, it has been shown that carefully designed reinforcement learni...
02/12/2020 ∙ by Shuang Liu, et al. ∙ 0 ∙ share

read it
Deep Stereo using Adaptive Thin Volume Representation with Uncertainty Awareness

We present Uncertainty-aware Cascaded Stereo Network (UCS-Net) for 3D re...
11/27/2019 ∙ by Shuo Cheng, et al. ∙ 27 ∙ share

read it
StructEdit: Learning Structural Shape Variations

Learning to encode differences in the geometry and (topological) structu...
11/25/2019 ∙ by Kaichun Mo, et al. ∙ 11 ∙ share

read it
Normal Assisted Stereo Depth Estimation

Accurate stereo depth estimation plays a critical role in various 3D tas...
11/24/2019 ∙ by Uday Kusupati, et al. ∙ 15 ∙ share

read it
State Alignment-based Imitation Learning

Consider an imitation learning problem that the imitator and the expert ...
11/21/2019 ∙ by Fangchen Liu, et al. ∙ 0 ∙ share

read it
Information-Theoretic Local Minima Characterization and Regularization

Recent advances in deep learning theory have evoked the study of general...
11/19/2019 ∙ by Zhiwei Jia, et al. ∙ 0 ∙ share

read it
S4G: Amodal Single-view Single-Shot SE(3) Grasp Detection in Cluttered Scenes

Grasping is among the most fundamental and long-lasting problems in robo...
10/31/2019 ∙ by Yuzhe Qin, et al. ∙ 0 ∙ share

read it
Multi-view PointNet for 3D Scene Understanding

Fusion of 2D images and 3D point clouds is important because information...
09/30/2019 ∙ by Maximilian Jaritz, et al. ∙ 0 ∙ share

read it
Model Imitation for Model-Based Reinforcement Learning

Model-based reinforcement learning (MBRL) aims to learn a dynamic model ...
09/25/2019 ∙ by Yueh-Hua Wu, et al. ∙ 9 ∙ share

read it
Pre-training as Batch Meta Reinforcement Learning with tiMe

Pre-training is transformative in supervised learning: a large network t...
09/25/2019 ∙ by Quan Vuong, et al. ∙ 0 ∙ share

read it
Adversarial point perturbations on 3D objects

The importance of training robust neural network grows as 3D data is inc...
08/16/2019 ∙ by Daniel Liu, et al. ∙ 0 ∙ share

read it
Mapping State Space using Landmarks for Universal Goal Reaching

An agent that has well understood the environment should be able to appl...
08/15/2019 ∙ by Zhiao Huang, et al. ∙ 2 ∙ share

read it
Point-Based Multi-View Stereo Network

We introduce Point-MVSNet, a novel point-based deep framework for multi-...
08/12/2019 ∙ by Rui Chen, et al. ∙ 0 ∙ share

read it
StructureNet: Hierarchical Graph Networks for 3D Shape Generation

The ability to generate novel, diverse, and realistic 3D shapes along wi...
08/01/2019 ∙ by Kaichun Mo, et al. ∙ 5 ∙ share

read it
Spine-Inspired Continuum Soft Exoskeleton for Stoop Lifting Assistance

Back injuries are the most prevalent work-related musculoskeletal disord...
07/04/2019 ∙ by Xiaolong Yang, et al. ∙ 0 ∙ share

read it
How to pick the domain randomization parameters for sim-to-real transfer of reinforcement learning policies?

Recently, reinforcement learning (RL) algorithms have demonstrated remar...
03/28/2019 ∙ by Quan Vuong, et al. ∙ 12 ∙ share

read it
A Soft High Force Hand Exoskeleton for Rehabilitation and Assistance of Spinal Cord Injury and Stroke Individuals

Individuals with spinal cord injury (SCI) and stroke who is lack of mani...
02/19/2019 ∙ by Shuangyue Yu, et al. ∙ 0 ∙ share

read it
Design and Control of a Quasi-Direct Drive Soft Hybrid Knee Exoskeleton for Injury Prevention during Squatting

This paper presents a new design approach of wearable robots that tackle...
02/19/2019 ∙ by Shuangyue Yu, et al. ∙ 0 ∙ share

read it
Comfort-Centered Design of a Lightweight and Backdrivable Knee Exoskeleton

This paper presents design principles for comfort-centered wearable robo...
02/11/2019 ∙ by Junlin Wang, et al. ∙ 0 ∙ share

read it
DeepSpline: Data-Driven Reconstruction of Parametric Curves and Surfaces

Reconstruction of geometry based on different input modes, such as image...
01/12/2019 ∙ by Jun Gao, et al. ∙ 12 ∙ share

read it
Extending Adversarial Attacks and Defenses to Deep 3D Point Cloud Classifiers

3D object classification and segmentation using deep neural networks has...
01/10/2019 ∙ by Daniel Liu, et al. ∙ 0 ∙ share

read it

Hao Su

Featured Co-authors