Article
Computer Science, Theory & Methods
Shuchao Duan, Zhenxue Chen, Q. M. Jonathan Wu, Lei Cai, Dan Lu
Summary: This paper proposes a novel method for face photo-sketch transformation, which addresses the traditional problems using a multi-scale gradients self-attention residual learning framework, and achieves both face photo-to-sketch synthesis and face sketch-to-photo synthesis simultaneously through a cycle framework.
IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY
(2021)
Article
Computer Science, Artificial Intelligence
Yonggang Qi, Guoyao Su, Qiang Wang, Jie Yang, Kaiyue Pang, Yi-Zhe Song
Summary: In this paper, the problem of sketch healing is studied and a method based on graph model and trade-off between global semantic preservation and local structure reconstruction is proposed. Experimental results show that the proposed method significantly outperforms other methods in sketch healing. Furthermore, the method can also be applied to the field of creative assistant, showing promising applications.
INTERNATIONAL JOURNAL OF COMPUTER VISION
(2022)
Article
Computer Science, Information Systems
Nannan Tian, Yuan Liu, Bo Wu, Xiaofeng Li
Summary: Logo design is a complex process where color plays a crucial role. The automatic colorization of logo sketches is valuable yet challenging. A new logo design method based on Conditional Generative Adversarial Networks is proposed in this paper, which can output multiple colorful logos by providing one logo sketch. By introducing attention mechanisms and improving traditional U-Net structure, this method can generate diverse and realistic logo images based on simple sketches.
Article
Computer Science, Information Systems
Zeyu Li, Cheng Deng, Erkun Yang, Dacheng Tao
Summary: This study introduces a semi-supervised generative adversarial networks-based method for sketch-to-image synthesis, which can directly generate realistic images from novice sketches by incorporating class-wise representations. Compared with state-of-the-art image translation methods, our approach achieves more promising results in terms of Inception Scores and Frechet Inception Distance.
IEEE TRANSACTIONS ON MULTIMEDIA
(2021)
Article
Engineering, Electrical & Electronic
Zhantao Yang, Xiaoguang Zhu, Jiuchao Qian, Peilin Liu
Summary: This research introduces the dark-aware sketch-based image retrieval (DA-SBIR) method to incorporate dark region information into fine-grained sketch-based image retrieval, achieving consistent improvements over existing technologies through the application of Split GAN for automatic sketch segmentation.
IEEE SIGNAL PROCESSING LETTERS
(2021)
Article
Computer Science, Artificial Intelligence
Lan Yan, Wenbo Zheng, Chao Gou, Fei-Yue Wang
Summary: This paper proposes a novel Identity-sensitive Generative Adversarial Network (IsGAN) to address the problem of face photo-sketch synthesis by embedding identity information through adversarial learning. The model introduces identity recognition loss and cyclic-synthesized loss to preserve identifiable information and enforce structural consistency, achieving state-of-the-art performance on the CUFS and CUFSF datasets.
PATTERN RECOGNITION
(2021)
Article
Computer Science, Software Engineering
Yuefan Shen, Changgeng Zhang, Hongbo Fu, Kun Zhou, Youyi Zheng
Summary: DeepSketchHair is a deep learning-based tool for modeling 3D hair from 2D sketches. The system utilizes three carefully designed neural networks to convert, map, and update input sketches, generating 3D hair models that match the input sketches.
IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS
(2021)
Article
Computer Science, Software Engineering
Paul Merrell
Summary: We propose a method to automatically generate polygonal shapes from an example using a graph grammar. Unlike traditional procedural modeling techniques, our method can create grammar rules automatically from the given example. By disassembling the input into small primitives and reassembling them into new graphs, our method can generate locally similar graphs that match the given example. These graphs are converted into planar graph drawings to produce the final shape.
ACM TRANSACTIONS ON GRAPHICS
(2023)
Article
Computer Science, Artificial Intelligence
Zhi Dou, Ning Wang, Baopu Li, Zhihui Wang, Haojie Li, Bin Liu
Summary: Automatic sketch colorization is a challenging task that requires consideration of color, texture, and shading generation in both the RGB and HSV color spaces, as well as the subjective understanding of illustrators. The proposed dual color space guided generative adversarial network method achieves more vivid coloring effects by incorporating the HSV color space and DP loss.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2021)
Article
Computer Science, Theory & Methods
Congyu Zhang, Decheng Liu, Chunlei Peng, Nannan Wang, Xinbo Gao
Summary: With the development of generative adversarial networks, face sketch synthesis is gaining attention for its promising prospects in entertainment and law enforcement. A novel generative adversarial network is proposed to synthesize sketches with similar shapes and rich details to photos. The method incorporates a cross-domain framework and a spatially adaptive denormalization module to improve the synthesis quality and details of the face images.
IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY
(2022)
Article
Computer Science, Information Systems
Han Yan, Haijun Zhang, Linlin Liu, Dongliang Zhou, Xiaofei Xu, Zhao Zhang, Shuicheng Yan
Summary: The article introduces an AI-based framework for fashion design using generative adversarial networks to enhance designers' efficiency. The framework includes a sketch-generation module based on latent space and a rendering-generation module to learn the mapping between textures and sketches. Experimental results demonstrate the effectiveness of the proposed method in synthesizing semantic-aware textures on sketches.
IEEE TRANSACTIONS ON MULTIMEDIA
(2023)
Article
Computer Science, Information Systems
Samah S. Baraheem, Tam V. Nguyen
Summary: Generating a natural and reasonable image by decomposing the problem into subproblems, creating a semantic mask map from the input sketch through instance and semantic segmentation, and then translating the mask map into an image using an image-to-image translation model.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Computer Science, Information Systems
Uche Osahor, Nasser M. Nasrabadi
Summary: This paper proposes a text-guided sketch-to-image synthesis model that can generate realistic images from human facial sketches and their corresponding text descriptions. By utilizing pre-trained visual-linguistic semantic features and an intermediate mapping network, as well as a linear-based attention scheme, the model achieves better feature matching and computational performance.
Article
Engineering, Electrical & Electronic
Haitao Yin, Jinghu Xiao, Hao Chen
Summary: This article proposes a novel cross-scale pyramid attention GAN-based IVIF method (CSPA-GAN) for fusing infrared and visible images. It adopts one generator and dual discriminators to approximate the distribution of fused image, and utilizes multi-scale feature fusion, bidirectional interaction decoding, and reconstruction module to achieve high-performance results qualitatively and quantitatively.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2023)
Article
Computer Science, Artificial Intelligence
Jiamin Liang, Xin Yang, Yuhao Huang, Haoming Li, Shuangchi He, Xindi Hu, Zejian Chen, Wufeng Xue, Jun Cheng, Dong Ni
Summary: This paper proposes a generative adversarial network (GAN) based image synthesis framework for generating realistic and high-resolution B-mode ultrasound (US) images. The framework incorporates auxiliary sketch guidance and a progressive training strategy to enhance structural details and resolution of the generated images. The method is versatile and has been validated on multiple US image datasets of different anatomical structures.
MEDICAL IMAGE ANALYSIS
(2022)