赵皓｜西南科技大学｜学者主页

2026

PredActor: Predictive Action Diffusion for Steerable Onboard Humanoid Control

Lei Ye, Hai-Bo Gao, Yi-Tang Li, Peng Xu, Zeng-Rui Jing, Jun Sun, Fan-Rong Dong, Zi-Qi Han, Xue Wang, Jian-Hua Sun, Ce-Wu Lu, Hao Zhao, Liang Ding

2026

From Hitter to Player: Separating Motor Execution and Strategy in Competitive Humanoid Table Tennis

Fan-Rong Dong, Zi-Yi Sun, Zi-Qi Han, Jun Sun, Lei Ye, Zeng-Rui Jing, Hao Zhao, Shao-Xun Liu, Rong-Rong Wang

2026

GaussianWAM: Distilling Geometry and Semantics from 3D Gaussian Fields into World-Action Models

Zi-Jian Zhang, Yu-Qing Jiang, Wei-Tao Zhou, Ming-Lei Li, Jin-Hao Zhang, Yao Mu, Xiao-Fan Li, Hao Zhao, Hai-Bao Yu

2026

P-BFM: Perceptive Behavioral Foundation Models for Humanoid Control via Unsupervised Reinforcement Learning

Xue Wang, Yi-Tang Li, Yi-Ming Zhang, Si-Qin Wang, Jun Sun, Zhi-Hao Liu, Yao-Jie Shen, Jing-Bo Yuan, Hao Zhao, Qing-Du Li

2026

I-BFM: Reward-Conditioned Robust Humanoid Interaction via Unsupervised Reinforcement Learning

Zi-Qi Han, Yi-Tang Li, Jun Sun, Fan-Rong Dong, Yao-Jie Shen, Lei Ye, Zeng-Rui Jing, Yong-Qi Zhang, Yi-Ming Zhang, Xue Wang, Hao Zhao

2026

SimVTA: Simulation-Grounded Video-Trajectory Alignment for Driving World Action Models

Chang-Hui Jing, Hao-Chen Tian, Hong-Chen Li, Tianyu Li, Cao-Jun Wang, Zi-Hao Zhang, Yan-Hao Liu, Chen-Gen Xie, Bai-Lin Li, Hao Zhao, Zhen-Jie Yang

2026

ICG-VIMOD: infrared-characteristic-guided visible-infrared multi-modal object detection network

Chao Zeng, Hao Zhao, Ju Zhou

Measurement Science and Technology

DOI

2025

FB-4D: Spatial-Temporal Coherent Dynamic 3D Content Generation with Feature Banks

Jinwei Li, Huan-Ang Gao, Wen-Yi Li, Haohan Chi, Chen-Yu Liu, Chenxi Du, Yi-Qian Liu, Ming-Ju Gao, Guiyu Zhang, Zongzheng Zhang, Li Yi, Yao Yao, Jing-Wei Zhao, Hongyang Li, Yi-Kai Wang, Hao Zhao

IEEE Workshop/Winter Conference on Applications of Computer Vision

DOI

2025

PartRM: Modeling Part-Level Dynamics with Large Cross-State Reconstruction Model

Ming-Ju Gao, Yike Pan, Huan-Ang Gao, Zongzheng Zhang, Wen-Yi Li, Hao Dong, Hao Tang, Li Yi, Hao Zhao

Computer Vision and Pattern Recognition

DOI

2025

Impromptu VLA: Open Weights and Open Data for Driving Vision-Language-Action Models

Haohan Chi, Huan-ang Gao, Ziming Liu, Jia-Ning Liu, Chen-Yu Liu, Jinwei Li, Kaisen Yang, Yangcheng Yu, Ze Wang, Wen-Yi Li, Lei-Chen Wang, Xingtao Hu, Hao Sun, Hang Zhao, Hao Zhao

Neural Information Processing Systems

DOI

2025

StereoCarla: A High-Fidelity Driving Dataset for Generalizable Stereo

Xian-Da Guo, Chen-Ming Zhang, Rui-Lin Wang, Youmin Zhang, Wen-Zhao Zheng, Matteo Poggi, Hao Zhao, Qin Zou, Long Chen

arXiv.org

DOI

2025

DiffVLA: Vision-Language Guided Diffusion Planning for Autonomous Driving

An-Qing Jiang, Yu Gao, Zhigang Sun, Yi-Ru Wang, Ji-Jun Wang, Jinhao Chai, Qian Cao, Yuwen Heng, Hao Jiang, Yun-Da Dong, Zongzheng Zhang, Xian-Da Guo, Hao Sun, Hao Zhao

arXiv.org

DOI

2025

ROVR-Open-Dataset: A Large-Scale Depth Dataset for Autonomous Driving

Xian-Da Guo, Rui-Jun Zhang, Yiqun Duan, Rui-Lin Wang, Keyuan Zhou, Wen-Zhao Zheng, Wen-Ke Huang, Gang-Wei Xu, M. Horton, Yuan Si, Hao Zhao, Long Chen

arXiv.org

DOI

2024

基于多粒度注意力改进的喷码字符识别算法

蔡文涛，赵皓，王姮，张华

《制造业自动化》

2024

PreAfford: Universal Affordance-Based Pre-Grasping for Diverse Objects and Environments

Kairui Ding, Boyuan Chen, Rui-Hai Wu, Yu-Yang Li, Zongzheng Zhang, Huan-Ang Gao, Siqi Li, Gu-Yue Zhou, Yi-Xin Zhu, Hao Dong, Hao Zhao

IEEE/RJS International Conference on Intelligent RObots and Systems

DOI

2024

SCP-Diff: Spatial-Categorical Joint Prior for Diffusion Based Semantic Image Synthesis

Huan-Ang Gao, Ming-Ju Gao, Jiaju Li, Wen-Yi Li, Rong Zhi, Hao Tang, Hao Zhao

European Conference on Computer Vision

DOI

2024

FairDiff: Fair Segmentation with Point-Image Diffusion

Wen-Yi Li, Haoran Xu, Guiyu Zhang, Huan-Ang Gao, Ming-Ju Gao, Mengyu Wang, Hao Zhao

International Conference on Medical Image Computing and Computer-Assisted Intervention

DOI

2024

SA-GS: Scale-Adaptive Gaussian Splatting for Training-Free Anti-Aliasing

Xiaowei Song, Jv Zheng, Shiran Yuan, Huan-Ang Gao, Jing-Wei Zhao, Xiang He, Weihao Gu, Hao Zhao

arXiv.org

DOI

2024

Hint-AD: Holistically Aligned Interpretability in End-to-End Autonomous Driving

Kairui Ding, Boyuan Chen, Yuchen Su, Huan-Ang Gao, Bu Jin, Chong-Hao Sima, Wuqiang Zhang, Xiao-Hui Li, Paul Barsch, Hongyang Li, Hao Zhao

Conference on Robot Learning

DOI

2024

Stereo Anything: Unifying Zero-shot Stereo Matching with Large-Scale Mixed Data

Xian-Da Guo, Chen-Ming Zhang, Youmin Zhang, Rui-Lin Wang, Dujun Nie, Wen-Zhao Zheng, Matteo Poggi, Hao Zhao, Mang Ye, Qin Zou, Long Chen

2024

SURDS: Benchmarking Spatial Understanding and Reasoning in Driving Scenarios with Vision Language Models

Xian-Da Guo, Rui-Jun Zhang, Yiqun Duan, Yuhang He, Dujun Nie, Wen-Ke Huang, Chen-Ming Zhang, Shuai Liu, Hao Zhao, Long Chen

Neural Information Processing Systems

DOI

2024

CiC-NET: a real-time semantic segmentation network for dam surface crack detection

Linjing Li, Hao Zhao, Ran Liu, Anand Nayyar, Rashid Ali, Yonglong Li, Hua Zhang

Multimedia Tools and Applications

DOI

2024

SSMask: Salient Super-Pixel Mask Data Augmentation for Object Detection

Hao Zhao, Jian‐An Huang, Hao Deng, Xue Feng Deng

International Conference on Pattern Recognition and Artificial Intelligence (PRAI)

DOI

2024

FIoU loss: Towards Accurate One-stage Object Detector with Better Bounding Box Regression

Hao Zhao, Hao Deng, Jixiang Huang, Ju Zhou

International Conference on Advanced Robotics and Mechatronics (ICARM)

DOI

2023

融合视觉先验知识的目标检测优化方法研究

赵皓

《中国科学技术大学》

2023

基于结构特征对齐的γ辐射环境场景图像配准方法

邓豪，赵皓，张华，赵俊琴，方琳琳

《原子能科学技术》

2023

Interpretability-Mask: a label-preserving data augmentation scheme for better classification

Hao Zhao, Jikai Wang, Zonghai Chen, Shiqi Lin, Peng Bao, Meng Xu

Signal Image and Video Processing

DOI

2022

基于物体关系描述的单目语义SLAM方法

林士琪，王纪凯，裴浩渊，赵皓，陈宗海

《系统仿真学报》

DOI

2022

改进RetinaNet的遮挡目标检测算法研究

阳珊，王建，胡莉，刘波，赵皓

《计算机工程与应用》

2022

SRK-Augment: A self-replacement and discriminative region keeping augmentation scheme for better classification

Hao Zhao, Jikai Wang, Zonghai Chen, Shiqi Lin, Peng Bao

Neural Processing Letters

DOI

2022

Arbitrary Direction Inkjet Character Recognition Based on Spatial Transformation

Wentao Cai, Hao Zhao, Heng Wang, Xue Feng Deng

International Conference on Communication, Image and Signal Processing (CCISP)

DOI

2022

D-NMS: A dynamic NMS network for general object detection

Hao Zhao, Jikai Wang, Deyun Dai, Shiqi Lin, Zonghai Chen

Neurocomputing

DOI

2022

Grid self-occlusion: a grid self-occlusion data augmentation for better classification

Xue Feng Deng, Hao Zhao, Hua Zhang, Jing Zhang, Boping Mei

Signal Image and Video Processing

DOI

2022

In-and-Out: a data augmentation technique for computer vision tasks

Chenghao Li, Jing Zhang, Li Hu, Hao Zhao, Huilong Zhu, Maomao Shan

Journal of Electronic Imaging

DOI

2022

DcsNet: a real-time deep network for crack segmentation

Jie Pang, Hua Zhang, Hao Zhao, Linjing Li

Signal Image and Video Processing

DOI

2021

Data Augmentation Based on Cannikin Law for Object Detection

Xue Feng Deng, Hongwei Luo, Hao Zhao, Jing Zhang, Shan Yang, Boping Mei, Hua Zhang

DOI

2021

A Refined NMS Scheme Based on Center Distance and Corner Distribution

Shan Yang, Xie Liu, Li Hu, Hao Zhao, Hua Zhang, Linjing Li, Boping Mei

DOI

2018

危险环境消防侦察机器人视轴规划算法研究

刘满禄，李铭浩，敖天翔，赵皓

《计算机工程与应用》

精选作品

期刊论文

PredActor: Predictive Action Diffusion for Steerable Onboard Humanoid Control

From Hitter to Player: Separating Motor Execution and Strategy in Competitive Humanoid Table Tennis

GaussianWAM: Distilling Geometry and Semantics from 3D Gaussian Fields into World-Action Models

P-BFM: Perceptive Behavioral Foundation Models for Humanoid Control via Unsupervised Reinforcement Learning

I-BFM: Reward-Conditioned Robust Humanoid Interaction via Unsupervised Reinforcement Learning

SimVTA: Simulation-Grounded Video-Trajectory Alignment for Driving World Action Models

ICG-VIMOD: infrared-characteristic-guided visible-infrared multi-modal object detection network

FB-4D: Spatial-Temporal Coherent Dynamic 3D Content Generation with Feature Banks

PartRM: Modeling Part-Level Dynamics with Large Cross-State Reconstruction Model

Impromptu VLA: Open Weights and Open Data for Driving Vision-Language-Action Models

StereoCarla: A High-Fidelity Driving Dataset for Generalizable Stereo

DiffVLA: Vision-Language Guided Diffusion Planning for Autonomous Driving

ROVR-Open-Dataset: A Large-Scale Depth Dataset for Autonomous Driving

基于多粒度注意力改进的喷码字符识别算法

PreAfford: Universal Affordance-Based Pre-Grasping for Diverse Objects and Environments

SCP-Diff: Spatial-Categorical Joint Prior for Diffusion Based Semantic Image Synthesis

FairDiff: Fair Segmentation with Point-Image Diffusion

SA-GS: Scale-Adaptive Gaussian Splatting for Training-Free Anti-Aliasing

Hint-AD: Holistically Aligned Interpretability in End-to-End Autonomous Driving

Stereo Anything: Unifying Zero-shot Stereo Matching with Large-Scale Mixed Data

SURDS: Benchmarking Spatial Understanding and Reasoning in Driving Scenarios with Vision Language Models

CiC-NET: a real-time semantic segmentation network for dam surface crack detection

SSMask: Salient Super-Pixel Mask Data Augmentation for Object Detection

FIoU loss: Towards Accurate One-stage Object Detector with Better Bounding Box Regression

融合视觉先验知识的目标检测优化方法研究

基于结构特征对齐的γ辐射环境场景图像配准方法

Interpretability-Mask: a label-preserving data augmentation scheme for better classification

基于物体关系描述的单目语义SLAM方法

改进RetinaNet的遮挡目标检测算法研究

SRK-Augment: A self-replacement and discriminative region keeping augmentation scheme for better classification

Arbitrary Direction Inkjet Character Recognition Based on Spatial Transformation

D-NMS: A dynamic NMS network for general object detection

Grid self-occlusion: a grid self-occlusion data augmentation for better classification

In-and-Out: a data augmentation technique for computer vision tasks

DcsNet: a real-time deep network for crack segmentation

Data Augmentation Based on Cannikin Law for Object Detection

A Refined NMS Scheme Based on Center Distance and Corner Distribution

危险环境消防侦察机器人视轴规划算法研究

会议论文

基于多元环境特征的视觉定位方法综述

基于物体关系描述的单目语义SLAM方法

交通场景下基于LiDAR点云的3D目标检测

Contour-box for object proposal based on modified Depth First Search

基于Lidar点云的道路目标分割

研究方向