Search

Image editing refers to the process of retaining the content of non-editable areas of an image while modifying the content of editable regions based on input conditions. Guided by editing conditions, generative image editing utilizes a deep learning model to modify the content of an image by generating it, including but not limited to modifying features such as objects, styles, colors, and textures in the image. Generative image editing is an essential component of computer vision research, holding significant theoretical and practical application value. It has garnered widespread attention in both academia and industry, however, there is a relative scarcity of comprehensive surveys on related research. The paper provides a review of representative generative image editing methods. Firstly, based on different editing methods, editing tasks are divided into attribute based, text based, line based, and physical example-guided image editing. Different methods are analyzed and summarized by combining loss functions, types, and characteristics. At the same time, the impact of various methods on generation quality is further explored, and the dataset and evaluation indicators are elaborated in detail. Finally, future challenges and potential research directions in this field are highlighted. [ABSTRACT FROM AUTHOR]

In order to achieve a better balance between speed and accuracy in the process of clothing landmark detection, based on the human pose estimation network YOLOv8s-Pose, a T-shirt landmark detection method named YOLO-T-Shirt is proposed, which utilizes a cascade architecture and fused geometric information. Firstly, inspired by the CFNet architecture, the cascade fusion network design architecture is introduced into YOLOv8s-Pose, with a redesign of the original feature extraction and feature fusion architecture to better integrate multi-scale features, so as to have good robustness to changes in clothing size and shape. Secondly, the native OKS loss function is optimized, and an efficient landmark similarity loss function EOKS (Efficient Object Keypoint Similarity) that integrates integrating geometric information of area, width, height and distance of the center point of the frame is proposed to improve the accuracy of landmark detection. The proposed method achieves a prediction accuracy of 0.760 in the landmark detection task of the T-shirt category in the DeepFashion2 dataset, which is close to the accuracy of 0.765 of the current clothing landmark detection algorithm with the highest accuracy, while the inference speed is more than 9 times faster. [ABSTRACT FROM AUTHOR]

In order to explore the effect of competitive adsorbents on the distribution of mercury removal active components of activated carbon and its mercury adsorption performances, a kind of commercial activated carbon was pretreatmented by acetic acid and ammonia, then activated carbon was modified by KBr solution.These modified activated carbon samples were characterized by means of measuring iodine and methylene blue adsorption to analyze the changes of pore structure of activated carbon after pretreatment and loading of active components.The distribution of active components on activated carbon were investigated with the of SEM and EDS.Experimental studies on removal of Hg were performed in a fixed bed reactor system.The effects of different competitive adsorbents on the distribution of active components and mercury adsorption performances of brominated activated carbon were investigated.The results showed activated component Br was mainly distributed on the surface of activated carbon when the competitive adsorbent was ammonia.When acetic acid was the competitive adsorbent, activated component Br was mainly distributed inside the pores of activated carbon.Activated component Br was mainly distributed both on the surface and inside the pores when it was pretreatmented by water.The adsorption amount of mercury increased significantly when the activated carbon was loaded by Br.The location of Br on activated carbon had negligible effect on the total amount of adsorption, but it affected the rate of mercury removal at different time periods during the mercury removal process.

Objective: To investigate the genotoxic effect of indium chloride using the in vivo bone marrow micronucleus test, and to provide scientific basis for the evaluation of the toxicity of indium compounds., Methods: Thirty two healthy male adult SPF Wistar rats were selected and randomly divided into four groups( control group, 0. 065, 0. 65, 1. 3 mg/kg group). Rats were treated with indium chloride using non exposed endotracheal injection method. Hematoxylin and eosin( H&E) staining was used to detect histological changes. Oxidative stress status relative to lung damage in rats was evaluated by detecting superoxide dismutase( SOD) and maleic dialdehyde( MDA) activities. The frequency of micronuclei was determined at the end of each culture period. Inductively coupled plasma mass spectrometry( ICP-MS) method was used to detect the content of indium in whole blood and lung tissue of rats., Results: The content of indium in whole blood and lung tissue of rats and the micronucleus rate in rats exposed to indium chloridewere significantly higher than those in the control group( P < 0. 01). The MDA content in the lung tissue of rats in middle and high dose group was significantly increased( P <0. 05), while SOD level was significantly lower than that in control group( P < 0. 05);Pathological changes of lung tissue showed that after exposure to indium chloride, inflammatory cell exudation was present in the alveolar cavity and surrounding areas of the trachea were apparent. Alveolar lumen was filled with intraalveolar proteinaceous material., Conclusion: Indium chloride exposure will cause the accumulation of indium in blood and lung, bone marrow micronucleus rate increased, occurrence of oxidative damage and pathological changes.