In this work, we explore the problem of generating fantastic special-effects for the typography. It is quite challenging due to the model diversities to illustrate varied text effects for different characters. To address this issue, our key idea is to exploit the analytics on the high regularity of the spatial distribution for text effects to guide the synthesis process. Specifically, we characterize the stylized patches by their normalized positions and the optimal scales to depict their style elements. Our method first estimates these two features and derives their correlation statistically. They are then converted into soft constraints for texture transfer to accomplish adaptive multi-scale texture synthesis and to make style element distribution uniform. It allows our algorithm to produce artistic typography that fits for both local texture patterns and the global spatial distribution in the example. Experimental results demonstrate the superiority of our method for various text effects over conventional style transfer methods. In addition, we validate the effectiveness of our algorithm with extensive artistic typography library generation.

b) adjustable stylistic degree of glyph (c) stylized text (d) application (e) liquid artistic text rendering (f) smoke artistic text rendering Figure 1: We propose a novel style transfer framework for rendering artistic text from a source style image in a scale-controllable manner.Our framework allows users to (b) adjust the stylistic degree of the glyph (i.e. deformation degree) in a continuous and real-time way, and therefore to (c) select the artistic text that is most ideal for both legibility and style consistency. The generated diverse artistic text will facilitate users to design (d) exquisite posters and (e)(f) dynamic typography. Embedded animation best viewed in Acrobat Reader. AbstractArtistic text style transfer is the task of migrating the style from a source image to the target text to create artistic typography. Recent style transfer methods have considered texture control to enhance usability. However, controlling the stylistic degree in terms of shape deformation remains an important open challenge. In this paper, we present the first text style transfer network that allows for real-time control of the crucial stylistic degree of the glyph through an adjustable parameter. Our key contribution is a novel bidirectional shape matching framework to establish an effective glyph-style mapping at various deformation levels without paired ground truth. Based on this idea, we propose a scale-controllable module to empower a single network to continuously characterize the multi-scale shape features of the style image and transfer these features to the target text. The proposed method demonstrates its superiority over previous state-of-the-arts in generating diverse, controllable and high-quality stylized text.

No abstract

No abstract

Background: Autologous osteoperiosteal transplantation (AOPT) using graft harvested from the iliac crest is used to treat large cystic osteochondral lesions of the talus (OLTs). However, no studies have compared clinical and radiologic outcomes between AOPT and autologous osteochondral transplantation (AOCT) using graft harvested from the nonweightbearing zone of the femoral condyle of the ipsilateral knee in patients with large cystic OLTs. Purpose: To compare clinical and radiologic outcomes between patients undergoing AOPT and those undergoing AOCT for large cystic OLTs. Study Design: Cohort study; Level of evidence, 3. Methods: Between March 2015 and March 2018, patients who underwent AOCT and AOPT to treat medial large cystic OLTs (>10 mm) were retrospectively evaluated. For comparability, the 2 groups were matched 1:1 based on their characteristics, including sex, age, body mass index, side of injury, follow-up period, and the preoperative cyst volume. After propensity score matching, 23 patients were enrolled in each group for the analysis. Clinical outcomes were assessed using the visual analog scale (VAS), the American Orthopaedic Foot & Ankle Society (AOFAS) score, and the Tegner score. Donor-site morbidity was recorded according to the symptoms, including pain, stiffness, swelling, and discomfort. In addition, the Lysholm score was used to assess the most common knee donor-site morbidity. Radiologic outcomes were evaluated using the magnetic resonance observation of cartilage repair tissue (MOCART) score, and the International Cartilage Regeneration & Joint Preservation Society (ICRS) score was obtained during second-look surgery. Results: The mean follow-up period was about 48 months. There were no significant differences in patient characteristics and lesion volumes between groups. Postoperative ankle pain VAS score, AOFAS score, and Tegner score were not significantly different between groups at final follow-up. Total donor-site morbidity ( P = .004) and discomfort morbidity ( P = .009) were significantly lower in the AOPT group than in the AOCT group. However, the Lysholm score showed no significant difference between the donor knee and the opposite knee ( P = .503) in the AOCT group. The MOCART and ICRS scores were not significantly different between groups. Conclusion: Clinical and radiologic outcomes of patients who underwent AOPT from the iliac crest were found to be comparable with those of patients who underwent AOCT from the ipsilateral knee for the treatment of medial large cystic OLTs. These results may be helpful for orthopaedic surgeons to decide appropriate treatments for patients with large cystic OLTs.

No abstract

Text effects transfer technology automatically makes the text dramatically more impressive. However, previous style transfer methods either study the model for general style, which cannot handle the highly-structured text effects along the glyph, or require manual design of subtle matching criteria for text effects. In this paper, we focus on the use of the powerful representation abilities of deep neural features for text effects transfer. For this purpose, we propose a novel Texture Effects Transfer GAN (TET-GAN), which consists of a stylization subnetwork and a destylization subnetwork. The key idea is to train our network to accomplish both the objective of style transfer and style removal, so that it can learn to disentangle and recombine the content and style features of text effects images. To support the training of our network, we propose a new text effects dataset with as much as 64 professionally designed styles on 837 characters. We show that the disentangled feature representations enable us to transfer or remove all these styles on arbitrary glyphs using one network. Furthermore, the flexible network design empowers TET-GAN to efficiently extend to a new text style via oneshot learning where only one example is required. We demonstrate the superiority of the proposed method in generating high-quality stylized text over the state-of-the-art methods.

No abstract