基于物理的视觉与深度学习的交叉领域是推动计算机视觉技术发展的前沿方向。通过利用物理学原理指导并优化深度学习模型,我们能够开发出更鲁棒、更精准的视觉系统。基于物理的视觉旨在反转成像过程,从图像中恢复形状、反射率、光分布及介质属性等场景特性。近年来,深度学习在各类视觉任务上展现出可观的性能提升,与基于物理的视觉结合后,这类方法可进一步增强视觉系统的鲁棒性与准确性。本技术报告总结了在CVPR 2024研讨会上举办的Physics-Based Vision Meets Deep Learning(PBDL,基于物理的视觉与深度学习)2024挑战赛的成果。本次挑战赛共设8个赛道,聚焦低光照增强与检测以及高动态范围(HDR)成像两大方向。报告详述了各赛道的目标、方法与结果,重点介绍了排名领先的解决方案及其创新思路。
英文摘要:
The intersection of physics-based vision and deep learning presents an exciting frontier for advancing computer vision technologies. By leveraging the principles of physics to inform and enhance deep learning models, we can develop more robust and accurate vision systems. Physics-based vision aims to invert the processes to recover scene properties such as shape, reflectance, light distribution, and medium properties from images. In recent years, deep learning has shown promising improvements for various vision tasks, and when combined with physics-based vision, these approaches can enhance the robustness and accuracy of vision systems. This technical report summarizes the outcomes of the Physics-Based Vision Meets Deep Learning (PBDL) 2024 challenge, held in CVPR 2024 workshop. The challenge consisted of eight tracks, focusing on Low-Light Enhancement and Detection as well as High Dynamic Range (HDR) Imaging. This report details the objectives, methodologies, and results of each track, highlighting the top-performing solutions and their innovative approaches.
Technical Report of RoboSpatial Challenge at CVPR 2026: Selective Reasoning Activation and Reference-Frame Disambiguation for Embodied Spatial Reasoning
Harbin Institute of Technology, Shenzhen(哈尔滨工业大学(深圳));Ruoyu Technology(若愚科技)
WiCV@CVPR2023: The Eleventh Women In Computer Vision Workshop at the Annual CVPR Conference
Austrian Institute of Technology(奥地利技术研究所);Technical University of Berlin(柏林工业大学);University of Leeds(利兹大学);CISPA – Helmholtz Center for Information Security(CISPA亥姆霍兹信息安全中心);Simon Fraser University(西蒙菲莎大学);Nanyang Technological University(南洋理工大学);Princeton University(普林斯顿大学);CSIR – Central Scientific Instruments Organisation(科学与工业研究理事会-中央科学仪器组织);Microsoft(微软)
WiCV@CVPR2024: The Thirteenth Women In Computer Vision Workshop at the Annual CVPR Conference
University of Leeds(利兹大学);Simon Fraser University(西蒙菲莎大学);Nanyang Technological University(南洋理工大学);University of Twente(特温特大学);University of Bath(巴斯大学);Carnegie Mellon University(卡内基梅隆大学);Austrian Institute of Technology(奥地利技术研究院);Adobe(奥多比公司)
Results of the 1st Asynchronous CASTLE Challenge at the Joint Egocentric Vision Workshop in Conjunction with CVPR 2026
Dublin City University(都柏林城市大学);JOANNEUM RESEARCH(约阿内研究机构);IT University of Copenhagen(哥本哈根信息技术大学);University of Amsterdam(阿姆斯特丹大学);Klagenfurt University(克拉根福大学)
WiCV at CVPR 2025: The Women in Computer Vision Workshop
University of Twente(特文特大学);University of Bath(巴斯大学);Carnegie Mellon University(卡内基梅隆大学);Adobe(Adobe公司);KAUST(科威特人工智能研究所以及先进技术中心);Microsoft(微软公司);KAIST(韩国科学技术院);General Robotics(通用机器人公司);Toyota Material Handling North America(丰田物流北美公司)
Multi-Modal UAV Detection, Classification and Tracking Algorithm -- Technical Report for CVPR 2024 UG2 Challenge
Shanghai Jiao Tong University(上海交通大学);JITRI(江苏集萃智能制造技术研究所有限公司);Dalian University of Technology(大连理工大学);University of Electronic Science and Technology of China(电子科技大学);The University of Tokyo(东京大学);The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州))
SuperAD: A Training-free Anomaly Classification and Segmentation Method for CVPR 2025 VAND 3.0 Workshop Challenge Track 1: Adapt & Detect
School of Computer Science and Engineering, Southeast University, China(东南大学计算机科学与工程学院);School of Computer Science and Engineering, Nanjing University of Science and Technology, China(南京理工大学计算机科学与工程学院)
针对MVTec AD 2真实工业异常检测挑战,提出基于DINOv2特征提取与记忆库最近邻匹配的完全无需训练方法SuperAD,在测试集上取得有竞争力结果。
Technical Report for Argoverse Challenges on Unified Sensor-based Detection, Tracking, and Forecasting
Lenovo Research(联想研究院);Liaoning Petrochemical University(辽宁石油化工大学);University of Science and Technology Beijing(北京科技大学);University of Science and Technology of China(中国科学技术大学);Tsinghua University(清华大学)
Technical Report on the CVPR 2026@AdvML Workshop Challenge
Beihang University(北京航空航天大学);University of Chinese Academy of Sciences(中国科学院大学);Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所);Tongji University(同济大学);iFLYTEK Co., Ltd.(科大讯飞股份有限公司);Anhui Laboratory for Safe Artificial Intelligence in the Yangtze River Delta(长三角安全人工智能安徽实验室);Wenzhou Business College(温州商学院);Jiangnan University(江南大学);Guangzhou City University of Technology(广州理工学院);Inceptio Technology(智元机器);Institute of Dataspace(数据空间研究所);Zhongguancun Laboratory(中关村实验室);Tsinghua University(清华大学);ETH Zürich(苏黎世联邦理工学院);University of Oxford(牛津大学);Shanghai AI Laboratory(上海人工智能实验室);BAAI(北京智源人工智能研究院);Meta;Johns Hopkins University(约翰·霍普金斯大学);University of California, Berkeley(加州大学伯克利分校);Nanyang Technological University(南洋理工大学)
APRIL-GAN: A Zero-/Few-Shot Anomaly Classification and Segmentation Method for CVPR 2023 VAND Workshop Challenge Tracks 1&2: 1st Place on Zero-shot AD and 4th Place on Few-shot AD
CVPR 2020 Continual Learning in Computer Vision Competition: Approaches, Results, Current Challenges and Future Directions
University of Bologna(博洛尼亚大学);ContinualAI Research(持续人工智能研究所);Element AI(元素人工智能公司);MILA(蒙特利尔学习算法研究所);ByteDance AI Labs(字节跳动人工智能实验室);University of Bristol(布里斯托大学);Tokyo Institute of Technology(东京工业大学);AIST RWBC-OIL(日本产业技术综合研究所实世界大数据与计算开放创新实验室);Chinese Academy of Sciences(中国科学院);University of Toronto(多伦多大学);University of Hamburg(汉堡大学);University of Cambridge(剑桥大学);Google AI(谷歌人工智能)