4.5 Review

Image Generation: A Review

Related references

Note: Only part of the references are listed.
Article Computer Science, Information Systems

Fast Adaptive Meta-Learning for Few-Shot Image Generation

Aniwat Phaphuangwittayakul et al.

Summary: Generative Adversarial Networks (GANs) are able to synthesize new realistic images and estimate sample distributions using adversarial learning. However, traditional GANs require a large amount of training data to produce reasonable results. In this study, a model called Fast Adaptive Meta-Learning (FAML) is proposed, which can generate new realistic images with fewer samples. Compared to baseline models, FAML has faster convergence and a simpler network structure.

IEEE TRANSACTIONS ON MULTIMEDIA (2022)

Article Computer Science, Artificial Intelligence

Applications, databases and open computer vision research from drone videos and images: a survey

Younes Akbari et al.

Summary: Analyzing videos and images captured by drones in computer vision falls into three main categories: remote sensing applications, drone-autonomous navigation, and various other applications like agriculture and animal detection. The research methods are primarily designed for real-world conditions but cannot provide entirely drone-based actual conditions. There are open problems and directions for future research that need to be explored in the field.

ARTIFICIAL INTELLIGENCE REVIEW (2021)

Article Computer Science, Artificial Intelligence

Evaluation Metrics for Conditional Image Generation

Yaniv Benny et al.

Summary: Two new metrics for evaluating generative models in the class-conditional image generation setting are proposed by generalizing the two most popular unconditional metrics. Theoretical analysis and extensive empirical evaluation compare these new metrics with their unconditional counterparts and provide additional insights into existing generative models.

INTERNATIONAL JOURNAL OF COMPUTER VISION (2021)

Article Computer Science, Artificial Intelligence

Cali-sketch: Stroke calibration and completion for high-quality face image generation from human-like sketches

Weihao Xia et al.

Summary: This paper introduces a method called Cali-Sketch for generating photo-realistic images from human-like sketches, which successfully addresses the generation problem of realistic face images from sketches through a combination of stroke calibration network and image synthesis network.

NEUROCOMPUTING (2021)

Review Computer Science, Information Systems

A review of video surveillance systems

Omar Elharrouss et al.

Summary: This paper provides a comprehensive review of automated surveillance systems, analyzing the observed scenarios using cameras and motion detection to achieve multiple tasks. It compares existing surveillance systems in terms of characteristics, advantages, and difficulties, and discusses future trends in research directions.

JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION (2021)

Article Ophthalmology

Pix2pix Conditional Generative Adversarial Networks for Scheimpflug Camera Color-Coded Corneal Tomography Image Generation

Hazem Abdelmotaal et al.

Summary: The study evaluated the ability of pix2pix cGAN to synthesize realistic Scheimpflug camera color-coded corneal tomography images, and used them for training deep convolutional neural networks for keratoconus and normal corneal image classification. The results showed that the synthesized images had good quality and improved classification performance.

TRANSLATIONAL VISION SCIENCE & TECHNOLOGY (2021)

Proceedings Paper Computer Science, Artificial Intelligence

LayoutTransformer: Scene Layout Generation with Conceptual and Spatial Diversity

Cheng-Fu Yang et al.

Summary: In this paper, we propose a LayoutTransformer Network (LT-Net) that encodes semantic features and translates them into bounding boxes to properly infer implicit objects or relationships during layout generation. By fitting distributions to Gaussian mixture models, spatially-diverse layouts can be produced by LT-Net. Our experiments on MS-COCO and Visual Genome datasets confirm the effectiveness and plausibility of our LT-Net over recent layout generation models.

2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021 (2021)

Proceedings Paper Computer Science, Artificial Intelligence

Energy-Based Learning for Scene Graph Generation

Mohammed Suhail et al.

Summary: A novel energy-based learning framework is proposed for generating scene graphs, leading to significant performance improvements on the Visual Genome and GQA benchmark datasets. The framework efficiently incorporates the structure of scene graphs and allows models to learn efficiently with a small number of labels.

2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021 (2021)

Proceedings Paper Computer Science, Artificial Intelligence

Context-Aware Layout to Image Generation with Enhanced Object Appearance

Sen He et al.

Summary: This paper introduces two new modules, a context-aware feature transformation module and the use of Gram matrix to preserve location-sensitive information. Experimental results demonstrate that these methods achieve state-of-the-art performance on relevant benchmarks.

2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021 (2021)

Article Computer Science, Information Systems

DeepWTPCA-L1: A New Deep Face Recognition Model Based on WTPCA-L1 Norm Features

Ayyad Maafiri et al.

Summary: This paper proposes a robust face recognition model called DeepWTPCA-L-1 using WTPCA-L-1 features and a CNN-LSTM architecture. The model achieves high recognition performance on multiple datasets and demonstrates better face recognition rate compared to state-of-the-art methods.

IEEE ACCESS (2021)

Article Computer Science, Information Systems

Pose-Normalized and Appearance-Preserved Street-to-Shop Clothing Image Generation and Feature Learning

Huijing Zhan et al.

Summary: The paper proposes a Pose-Normalized and Appearance-Preserved Generative Adversarial Network (PNAP-GAN) to tackle street-to-shop clothing image synthesis, addressing challenges such as visual discrepancy between scenarios and shape deformation. By disentangling shape and appearance synthesis and introducing semantic embedding loss for domain transfer, the PNAP-GAN is effective in generating high quality frontal-view images and pose-normalized features for clothing retrieval. Experiments show its superiority over existing methods and its benefits for cross-scenario clothing image generation.

IEEE TRANSACTIONS ON MULTIMEDIA (2021)

Article Computer Science, Artificial Intelligence

Use of Neural Signals to Evaluate the Quality of Generative Adversarial Network Performance in Facial Image Generation

Zhengwei Wang et al.

COGNITIVE COMPUTATION (2020)

Article Computer Science, Information Systems

High-quality face image generation based on generative adversarial networks

Zhixin Zhang et al.

JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION (2020)

Article Computer Science, Interdisciplinary Applications

Image generation by GAN and style transfer for agar plate image segmentation

Paolo Andreini et al.

COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE (2020)

Article Engineering, Electrical & Electronic

Panoramic Image Generation: From 2-D Sketch to Spherical Image

Yiping Duan et al.

IEEE JOURNAL OF SELECTED TOPICS IN SIGNAL PROCESSING (2020)

Article Computer Science, Artificial Intelligence

Generative adversarial networks with mixture of t-distributions noise for diverse image generation

Jinxuan Sun et al.

NEURAL NETWORKS (2020)

Proceedings Paper Computer Science, Artificial Intelligence

Enforcing Linearity in DNN Succours Robustness and Adversarial Image Generation

Anindya Sarkar et al.

ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING, ICANN 2020, PT I (2020)

Proceedings Paper Computer Science, Artificial Intelligence

SketchyCOCO: Image Generation from Freehand Scene Sketches

Chengying Gao et al.

2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) (2020)

Proceedings Paper Automation & Control Systems

Pixel-Level Bird View Image Generation from Front View by Using a Generative Adversarial Network

Tianru Zhou et al.

2020 6TH INTERNATIONAL CONFERENCE ON CONTROL, AUTOMATION AND ROBOTICS (ICCAR) (2020)

Article Computer Science, Information Systems

Dairy Goat Image Generation Based on Improved-Self-Attention Generative Adversarial Networks

Huan Li et al.

IEEE ACCESS (2020)

Article Computer Science, Artificial Intelligence

Panoramic Background Image Generation for PTZ Cameras

Hongwei Yong et al.

IEEE TRANSACTIONS ON IMAGE PROCESSING (2019)

Article Computer Science, Artificial Intelligence

A kernel-based image denoising method for improving parametric image generation

Hsuan-Ming Huang et al.

MEDICAL IMAGE ANALYSIS (2019)

Article Computer Science, Information Systems

An improved vehicle panoramic image generation algorithm

Jindong Zhang et al.

MULTIMEDIA TOOLS AND APPLICATIONS (2019)

Article Computer Science, Information Systems

Adversarially Approximated Autoencoder for Image Generation and Manipulation

Wenju Xu et al.

IEEE TRANSACTIONS ON MULTIMEDIA (2019)

Proceedings Paper Computer Science, Artificial Intelligence

ClothFlow: A Flow-Based Model for Clothed Person Generation

Xintong Han et al.

2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019) (2019)

Proceedings Paper Computer Science, Artificial Intelligence

Lifelong GAN: Continual Learning for Conditional Image Generation

Mengyao Zhai et al.

2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019) (2019)

Proceedings Paper Computer Science, Artificial Intelligence

Constrained Generative Adversarial Networks for Interactive Image Generation

Eric Heim

2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019) (2019)

Proceedings Paper Computer Science, Artificial Intelligence

Progressive Pose Attention Transfer for Person Image Generation

Zhen Zhu et al.

2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019) (2019)

Proceedings Paper Computer Science, Artificial Intelligence

Scene Graph Generation with External Knowledge and Image Reconstruction

Jiuxiang Gu et al.

2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019) (2019)

Proceedings Paper Computer Science, Interdisciplinary Applications

Cycle In Cycle Generative Adversarial Networks for Keypoint-Guided Image Generation

Hao Tang et al.

PROCEEDINGS OF THE 27TH ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA (MM'19) (2019)

Article Computer Science, Information Systems

Dense Convolutional Networks With Focal Loss and Image Generation for Electrocardiogram Classification

Mohamad Mahmoud Al Rahhal et al.

IEEE ACCESS (2019)

Article Computer Science, Information Systems

Synthetic Gastritis Image Generation via Loss Function-Based Conditional PGGAN

Ren Togo et al.

IEEE ACCESS (2019)

Article Computer Science, Artificial Intelligence

Semantic invariant cross-domain image generation with generative adversarial networks

Xiaofeng Mao et al.

NEUROCOMPUTING (2018)

Article Computer Science, Artificial Intelligence

Auto-painter: Cartoon image generation from sketch by using conditional Wasserstein generative adversarial networks

Yifan Liu et al.

NEUROCOMPUTING (2018)

Article Computer Science, Information Systems

A Survey of Image Synthesis and Editing with Generative Adversarial Networks

Xian Wu et al.

TSINGHUA SCIENCE AND TECHNOLOGY (2017)

Article Engineering, Electrical & Electronic

Moving object detection using a background modeling based on entropy theory and quad-tree decomposition

Omar Elharrouss et al.

JOURNAL OF ELECTRONIC IMAGING (2016)

Article Computer Science, Artificial Intelligence

Image quality assessment: From error visibility to structural similarity

Z Wang et al.

IEEE TRANSACTIONS ON IMAGE PROCESSING (2004)