arXivDaily arXiv每日学术速递 周一至周五更新

高校专区

The University of Hong Kong(香港大学)

2025-11-25 至 2025-11-25 共收录 8
2511.19437 2025-11-25 cs.CV

LumiTex: Towards High-Fidelity PBR Texture Generation with Illumination Context

LumiTex: 向高保真PBR纹理生成迈进:基于照明上下文

Jingzhi Bao, Hongze Chen, Lingting Zhu, Chenyu Liu, Runze Zhang, Keyang Luo, Zeyu Hu, Weikai Chen, Yingda Yin, Xin Wang, Zehong Lin, Jun Zhang, Xiaoguang Han

机构 * CUHK(SZ)(香港中文大学(深圳)) HKUST(香港理工大学) HKU(香港大学) PKU(北京大学) LIGHTSPEED

AI总结 LumiTex通过结合光照上下文和几何引导的修补模块,实现了高保真的PBR纹理生成,提升了材料分解和无缝纹理完成的性能。

Comments Project page: https://lumitex.vercel.app

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.19368 2025-11-25 cs.LG cs.NI

LLM-Driven Stationarity-Aware Expert Demonstrations for Multi-Agent Reinforcement Learning in Mobile Systems

基于大语言模型的站稳意识专家示范的多智能体强化学习在移动系统中的应用

Tianyang Duan, Zongyuan Zhang, Zheng Lin, Songxiao Guo, Xiuxian Guan, Guangyu Wu, Zihan Fang, Haotian Meng, Xia Du, Ji-Zhe Zhou, Heming Cui, Jun Luo, Yue Gao

机构 * Division of Computer Science, The University of Hong Kong(计算机科学系,香港大学) Department of Electrical and Electronic Engineering, The University of Hong Kong(电气电子工程系,香港大学) Department of Computer Science and Technology, Peking University(计算机科学与技术系,北京大学) Department of Computer Science, City University of Hong Kong(计算机科学系,城市大学) China Unicom Digital Technology, China Unicom co.,Ltd(中国联合数字技术,中国联合有限公司) School of Computer and Information Engineering, Xiamen University of Technology(计算机与信息工程学院,厦门理工学院) School of Computer Science, Engineering Research Center of Machine Learning and Industry Intelligence, Sichuan University(计算机科学学院,机器学习与工业智能工程研究中心,四川大学) College of Computing and Data Science, Nanyang Technological University(计算与数据科学学院,南洋理工大学) Institute of Space Internet, Fudan University(空间互联网研究院,复旦大学) School of Computer Science, Fudan University(计算机科学学院,复旦大学)

AI总结 本文提出RELED框架,通过大语言模型驱动的专家示范与自主探索相结合,提升多智能体强化学习在移动系统中的性能和稳定性。

Comments 15 pages, 9 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.19294 2025-11-25 cs.CV

DensifyBeforehand: LiDAR-assisted Content-aware Densification for Efficient and Quality 3D Gaussian Splatting

提前密集化:基于LiDAR的内容感知密集化以实现高效且高质量的3D高斯溅射

Phurtivilai Patt, Leyang Huang, Yinqiang Zhang, Yang Lei

机构 * The University of Hong Kong(香港大学)

AI总结 本文提出基于LiDAR的内容感知密集化方法,通过结合稀疏LiDAR数据与单目深度估计,提升3D高斯溅射的初始化效率和视觉质量,降低资源消耗和训练时间。

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.18834 2025-11-25 cs.CV cs.AI

FlowSteer: Guiding Few-Step Image Synthesis with Authentic Trajectories

FlowSteer: 通过真实轨迹引导少步图像合成

Lei Ke, Hubery Yin, Gongye Liu, Zhengyao Lv, Jingcai Guo, Chen Li, Wenhan Luo, Yujiu Yang, Jing Lyu

机构 * Tsinghua University(清华大学) WeChat Vision, Tencent Inc.(腾讯公司微信视觉部门) The Hong Kong University of Science and Technology(香港科学与技术大学) The University of Hong Kong(香港大学) The Hong Kong Polytechnic University(香港理工大学)

AI总结 FlowSteer通过引导学生沿教师真实生成轨迹提升ReFlow蒸馏效果,解决分布不匹配和优化调度器问题,提升少步图像合成质量。

Comments Few-Step Image Synthesis

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.20776 2025-11-25 cs.CV

CUPID: Generative 3D Reconstruction via Joint Object and Pose Modeling

CUPID:通过联合物体和姿态建模实现生成式3D重建

Binbin Huang, Haobin Duan, Yiqun Zhao, Zibo Zhao, Yi Ma, Shenghua Gao

机构 * The University of Hong Kong(香港大学) Transcengram Tencent(腾讯)

AI总结 CUPID通过联合建模物体和姿态,实现高保真3D重建,优于现有方法,在PSNR和Chamfer距离上分别提升3 dB和10%。

Comments project page at https://cupid3d.github.io

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.00350 2025-11-25 cs.LG cs.CV

BOOD: Boundary-based Out-Of-Distribution Data Generation

基于边界的Out-Of-Distribution数据生成

Qilin Liao, Shuo Yang, Bo Zhao, Ping Luo, Hengshuang Zhao

机构 * The University of Hong Kong, Hong Kong, China(香港大学) School of AI, Shanghai Jiao Tong University, Shanghai, China(上海交通大学人工智能学院) Department of Computer Science, Harbin Institute of Technology (Shenzhen), Shenzhen, China(哈尔滨工业大学(深圳)计算机科学系)

AI总结 BOOD通过在潜在空间中识别决策边界并生成高质量OOD特征,提升OOD检测性能,实验显示在CIFAR-100数据集上显著优于现有方法。

Comments 14 pages, 8 figures, To be published in the Proceedings of the International Conference on Machine Learning (ICML) 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.23771 2025-11-25 cs.RO cs.AI

Multi-Timescale Hierarchical Reinforcement Learning for Unified Behavior and Control of Autonomous Driving

多尺度分层强化学习用于自动驾驶的统一行为与控制

Guizhe Jin, Zhuoren Li, Bo Leng, Ran Yu, Lu Xiong, Chen Sun

机构 * School of Automotive Studies, Tongji University(同济大学汽车学院) Department of Data and Systems Engineering, University of Hong Kong(香港大学数据与系统工程系)

AI总结 本文提出多尺度分层强化学习方法,通过分层策略结构统一生成运动引导和控制指令,提升自动驾驶的效率、一致性和安全性。

Comments 8 pages, accepted for publication in IEEE Robotics and Automation Letters (RAL)

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.16001 2025-11-25 cs.LG cs.AI

AutoHFormer: Efficient Hierarchical Autoregressive Transformer for Time Series Prediction

AutoHFormer:高效的层次自回归变换器用于时间序列预测

Qianru Zhang, Honggang Wen, Ming Li, Dong Huang, Siu-Ming Yiu, Christian S. Jensen, Pietro Liò

机构 * School of Computing and Data Science, The University of Hong Kong (HKU)(计算与数据科学学院,香港大学) Zhejiang Key Laboratory of Intelligent Education Technology and Application, Zhejiang Normal University (ZJNU)(智能教育技术与应用浙江省重点实验室,浙江师范大学) Department of Computer Science, National University of Singapore (NUS)(计算机科学系,新加坡国立大学) Department of Computer Science, Aalborg University (AU)(计算机科学系,奥尔堡大学) Department of Computer Science and Technology, Cambridge University (Cambridge)(计算机科学与技术系,剑桥大学)

AI总结 AutoHFormer通过层次时间建模、动态窗口注意力和自适应时间编码,实现了高效且精确的时间序列预测,训练速度提升10.76倍,内存减少6.06倍。

Comments 14 pages

Journal ref ICDE'2026

详情

展开后加载摘要…

URL PDF HTML 收藏