Search

Artistic style transfer involves the adaption of an input image to reflect the style of a reference image while maintaining its original content. This technique, now a prominent focus due to its prospective use in creative fields like digital art and graphic design, typically applies normalization techniques and attention mechanisms. While these methods yield decent results, they often fall short due to distortion of content image details and non‐artefact styles. In this paper, we introduce a novel approach that synergizes adaptive instance normalization (AdaIN), attention mechanisms, knowledge distillation (KD) and strategically placed internal layers, and new enhancements designed to preserve content details and provide a nuanced control over the style transfer process. We introduce a Detail Enhancement Module to amplify high‐frequency details in the content image, enhancing edge and texture preservation. A Multi‐scale Strategy is implemented to ensure uniform style application across various detail levels, leading to more coherent stylization. The Content Feature Refinement process refines content features, sharpening and emphasizing details to preserve structural and textural integrity. AdaIN's distinctive feature of efficiently collecting style data is exploited in our approach, coupled with attention mechanisms' inherent ability to conserve content information. We supplement this blend with KD for the enhancement of model accuracy and efficiency. Additionally, the introduction of internal layers acts as a conduit to further improve the style transfer process, increasing the transfer level of features and fostering better stylized results. The cornerstone of our technique lies in preserving the content structure amidst complex style transfers. Experimental results affirm the superior performance of our method over existing techniques in both quantitative and qualitative evaluations. [ABSTRACT FROM AUTHOR]

Due to the disadvantages of traditional imaging methods, an imaging method based on object imaging has been proposed in this paper. This imaging method only images objects that are of interest and filters other objects. This paper mainly applies this imaging method to detect the quality of tiles by detection of special shapes. If the printing graphics of the tiles meet our requirements, a quality detection system will display the graphics needing quality detection on a monitor. Otherwise, no graphics are displayed on the monitor if the printing graphics do not meet requirements. The system includes: the use of communication between ARM and DSP under the DM6446 platform, the call to a multiple-algorithm, and design of a specific graphic imaging algorithm. The system removes the artificial testing steps in the process of quality detection, improves the speed and accuracy of quality detection and reduces the labor intensity required from inspectors. The preliminary studies show the feasibility and practicability of this system, and the preliminary experimental results show that an imaging method based on object imaging can be applied to quality detection of tiles and can solve existing problems for quality detection. [ABSTRACT FROM AUTHOR]

This paper presents how to synthesize a texture in a procedural way that preserves the features of the input exemplar. The exemplar is analyzed in both spatial and frequency domains to be decomposed into feature and non-feature parts. Then, the non-feature parts are reproduced as a procedural noise, whereas the features are independently synthesized. They are combined to output a non-repetitive texture that also preserves the exemplar's features. The proposed method allows the user to control the extent of extracted features and also enables a texture to edited quite effectively. [ABSTRACT FROM AUTHOR]

Although a large number of methods for video text detection and recognition have been proposed over the past years, it is hard to find the best state-of-the-art method because of nonavailability of standard datasets, ground truth, and common evaluation measures. Therefore, in this paper, we propose a semiautomatic system for ground truth generation for video text detection and recognition, which includes English and Chinese text of different orientation. The system has a facility to allow the user to manually correct the ground truth if the automatic method produces incorrect results. We propose eleven attributes at the word level, namely: line index, word index, coordinate values of bounding box, area, content, script type, orientation information, type of text (caption/scene), condition of text (distortion/distortion free), start frame, and end frame to evaluate the performance of the method. We also introduce a new dataset that consists of 466 video frames collected from TRECVID 2005 and 2006 databases. The video frames in our dataset contain both horizontal texts (278 frames: 181 with English texts and 97 with Chinese texts) and nonhorizontal texts (188 frames: 140 English and 48 Chinese). Furthermore, the performance of the proposed system is compared with existing text detection methods by calculating measures manually and automatically to show usefulness of our semiautomatic system. The ground truth and the semiautomatic system will be released to the public. [ABSTRACT FROM AUTHOR]

To render 3-D graphics efficiently, rasterization techniques have been developed. Traditional triangle traversal techniques using scan-line-based or edge-equation-based methods may cause potential instability from the division operations. This paper develops an efficient rasterization algorithm—a barycentric-based ladder start tile traversal that is division free. Throughout the process, no extra traversal position and context is produced to reduce the number of pixel tests and improve the efficiency and stability of the graphic rendering. It also presents the architecture of a 300 MHz 3-D graphics rasterizer in a 65 nm 1P9M process with a core size of 0.537 mm \(^{2}\) and internal buffer 3 K. The proposed ladder start tile traversal architecture can perform each tile intersect test in six cycles and tile interior traversal with barycentric tests in 2 pixels per cycle. In addition, the rasterizer throughput can achieve up to 50M triangles per second and 600M pixels per second. [ABSTRACT FROM PUBLISHER]