We propose a method that augments a simulated dataset using diffusion models to improve the performance of pedestrian detection in real-world data. The high cost of collecting and annotating data in the real-world has motivated the use of simulation platforms to create training datasets. While simulated data is inexpensive to collect and annotate, it unfortunately does not always closely match the distribution of real-world data, which is known as the sim2real gap. In this paper we propose a novel method of synthetic data creation meant to close the sim2real gap for the challenging pedestrian detection task. Our method uses a diffusion-based architecture to learn a real-world distribution which, once trained, is used to generate datasets. We mix this generated data with simulated data as a form of augmentation and show that training on a combination of generated and simulated data increases average precision by as much as 27.3% for pedestrian detection models in real-world data, compared against training on purely simulated data.
Intention Enhanced Diffusion Model for Multimodal Pedestrian Trajectory Prediction
Guangdong Provincial Key Laboratory of Fully Actuated System Control Theory and Technology, the Southern University of Science and Technology, Shenzhen 518055, China(广东省全自动化系统控制理论与技术重点实验室,南方科技大学,深圳518055,中国);Department of Mechanical Engineering, City University of Hong Kong, Hong Kong SAR, China(香港城市大学机械工程系,香港特别行政区,中国)
Mitigating Illumination-Induced Domain Shift in Night-Time Pedestrian Detection for Intelligent Vehicles using Annotation-Preserving Diffusion Augmentation
Diffusion^2: Dual Diffusion Model with Uncertainty-Aware Adaptive Noise for Momentary Trajectory Prediction
Civil and Environmental Engineering Department, University of Wisconsin-Madison(威斯康星大学麦迪逊分校土木与环境工程系);Civil and Environmental Engineering Department, University of Washington(华盛顿大学土木与环境工程系);College of Transportation, Tongji University(同济大学交通运输学院)
PSDiff: Diffusion Model for Person Search with Iterative and Collaborative Refinement
SGIT AI Lab(SGIT人工智能实验室);State Grid Shaanxi Electric Power Company Limited, State Grid Corporation of China(中国国家电网有限公司 国网陕西省电力公司);School of Information Science and Technology, University of Science and Technology of China(中国科学技术大学信息科学技术学院)
GenFusion: Closing the Loop between Reconstruction and Generation via Videos
Westlake University(西湖大学);Technical University of Munich(慕尼黑工业大学);ShanghaiTech University(上海科技大学);The University of Hong Kong(香港大学);University of Tübingen(蒂宾根大学)
Closing the Safety Gap: Surgical Concept Erasure in Visual Autoregressive Models
Harbin Institute of Technology, Shenzhen(哈尔滨工业大学(深圳));Tsinghua Shenzhen International Graduate School, Tsinghua University(清华大学深圳国际研究生院);Jilin University(吉林大学);Peng Cheng Laboratory(鹏城实验室);Department of Computer Science and Technology, Tsinghua University(清华大学计算机科学与技术系)
DeCo: Frequency-Decoupled Pixel Diffusion for End-to-End Image Generation
State Key Laboratory of Multimedia Information Processing, School of Computer Science, Peking University(北京大学计算机学院多媒体信息处理国家重点实验室);Nanjing University(南京大学);Huawei Inc.(华为公司)
Stochastic Trajectory Prediction via Motion Indeterminacy Diffusion
University of California, Los Angeles(加州大学洛杉矶分校);MBZUAI(穆罕默德·本·扎耶德人工智能大学);Carnegie Mellon University(卡内基梅隆大学);Tsinghua University(清华大学);SenseTime Research(商汤科技研究院)
Feature Erasing and Diffusion Network for Occluded Person Re-Identification
Monash University(莫纳什大学);SenseTime Research(商汤科技研究院);The University of Sydney(悉尼大学);Qing Yuan Research Institute, Shanghai Jiao Tong University(上海交通大学清源研究院);Xidian University(西安电子科技大学)
VI-Diff: Unpaired Visible-Infrared Translation Diffusion Model for Single Modality Labeled Visible-Infrared Person Re-identification
University of Chinese Academy of Sciences (UCAS)(中国科学院大学);The Center for Research on Intelligent Perception and Computing (CRIPAC)(智能感知与计算研究中心);Institute of Automation, Chinese Academy of Sciences (CASIA)(中国科学院自动化研究所)
InstancePin: Instance-Addressable Layout-to-Image Diffusion via Coordinate Pinning
School of Computer Science and Engineering, South China University of Technology(华南理工大学计算机科学与工程学院);School of Future Technology, South China University of Technology(华南理工大学未来技术学院)
MoVerse: Real-Time Video World Modeling with Panoramic Gaussian Scaffold
South China University of Technology;Columbia University;Orange Team, Youku Moku-Lab, HUJING Digital Media \& Entertainment Group;Singapore Management University
Do Generative Metrics Predict YOLO Performance? An Evaluation Across Models, Augmentation Ratios, and Dataset Complexity
School of Mechanical and Mining Engineering, The University of Queensland,Level 4, Mansergh Shaw Building (45), St Lucia, QLD 4072, Australia(昆士兰大学机械与采矿工程学院);Swinburne University of Technology, John Street, Hawthorn, VIC 3122, Australia(斯威本科技大学)
A Dual-stage Prompt-driven Privacy-preserving Paradigm for Person Re-Identification
School of Artificial Intelligence and Robotics at Hunan University(湖南大学人工智能与机器人学院);National Engineering Research Center of Robot Visual Perception and Control Technology(机器人视觉感知与控制技术国家工程研究中心);College of Information Science and Engineering at Hunan Normal University(湖南师范大学信息科学与工程学院)