Search

This work presents Unified Contrastive Arbitrary Style Transfer (UCAST), a novel style representation learning and transfer framework, that can fit in most existing arbitrary image style transfer models, such as CNN-based, ViT-based, and flow-based methods. As the key component in image style transfer tasks, a suitable style representation is essential to achieve satisfactory results. Existing approaches based on deep neural networks typically use second-order statistics to generate the output. However, these hand-crafted features computed from a single image cannot leverage style information sufficiently, which leads to artifacts such as local distortions and style inconsistency. To address these issues, we learn style representation directly from a large number of images based on contrastive learning by considering the relationships between specific styles and the holistic style distribution. Specifically, we present an adaptive contrastive learning scheme for style transfer by introducing an input-dependent temperature. Our framework consists of three key components: a parallel contrastive learning scheme for style representation and transfer, a domain enhancement (DE) module for effective learning of style distribution, and a generative network for style transfer. Qualitative and quantitative evaluations show the results of our approach are superior to those obtained via state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Great progress has been achieved in domain adaptation in decades. Existing works are always based on an ideal assumption that testing target domains are independent and identically distributed with training target domains. However, due to unpredictable corruptions (e.g., noise and blur) in real data, such as web images and real-world object detection, domain adaptation methods are increasingly required to be corruption robust on target domains. We investigate a new task, corruption-agnostic robust domain adaptation (CRDA), to be accurate on original data and robust against unavailable-for-training corruptions on target domains. This task is non-trivial due to the large domain discrepancy and unsupervised target domains. We observe that simple combinations of popular methods of domain adaptation and corruption robustness have suboptimal CRDA results. We propose a newapproach based on two technical insights into CRDA, as follows: (1) an easy-to-plug module called domain discrepancy generator (DDG) that generates samples that enlarge domain discrepancy to mimic unpredictable corruptions; (2) a simple but effective teacher-student scheme with contrastive loss to enhance the constraints on target domains. Experiments verify that DDG maintains or even improves its performance on original data and achieves better corruption robustness than baselines. [ABSTRACT FROM AUTHOR]

Multimodal and multi-domain stylization are two important problems in the field of image style transfer. Currently, there are few methods that can perform multimodal and multi-domain stylization simultaneously. In this study, we propose a unified framework for multimodal and multi-domain style transfer with the support of both exemplar-based reference and randomly sampled guidance. The key component of our method is a novel style distribution alignment module that eliminates the explicit distribution gaps between various style domains and reduces the risk of mode collapse. The multimodal diversity is ensured by either guidance from multiple images or random style codes, while the multi-domain controllability is directly achieved by using a domain label. We validate our proposed framework on painting style transfer with various artistic styles and genres. Qualitative and quantitative comparisons with state-of-the-art methods demonstrate that our method can generate high-quality results of multi-domain styles and multimodal instances from reference style guidance or a random sampled style. [ABSTRACT FROM AUTHOR]

The recently published joint demosaicking and zooming algorithms for single-sensor digital cameras all overfit the popular Kodak test images, which have been found to have higher spectral correlation than typical color images. Their performance perhaps significantly degrades on other datasets, such as the McMaster test images, which have weak spectral correlation. A new joint demosaicking and zooming algorithm is proposed for the Bayer color filter array (CFA) pattern, in which the edge direction information (edge map) extracted from the raw CFA data is consistently used in demosaicking and zooming. It also moderately utilizes the spectral correlation between color planes. The experimental results confirm that the proposed algorithm produces an excellent performance on both the Kodak and McMaster datasets in terms of both subjective and objective measures. Our algorithm also has high computational efficiency. It provides a better tradeoff among adaptability, performance, and computational cost compared to the existing algorithms. [ABSTRACT FROM AUTHOR]

In this paper, we address the following research problem: How can we generate a meaningful split grammar that explains a given facade layout? To evaluate if a grammar is meaningful, we propose a cost function based on the description length and minimize this cost using an approximate dynamic programming framework. Our evaluation indicates that our framework extracts meaningful split grammars that are competitive with those of expert users, while some users and all competing automatic solutions are less successful. [ABSTRACT FROM AUTHOR]

We present a novel method for content-aware image resizing based on optimization of a well-defined image distance function, which preserves both the important regions and the global visual effect (the background or other decorative objects) of an image. The method operates by joint use of seam carving and image scaling. The principle behind our method is the use of a bidirectional similarity function of image Euclidean distance (IMED), while cooperating with a dominant color descriptor (DCD) similarity and seam energy variation. The function is suitable for the quantitative evaluation of the resizing result and the determination of the best seam carving number. Different from the previous simplex-mode approaches, our method takes the advantages of both discrete and continuous methods. The technique is useful in image resizing for both reduction/retargeting and enlarging. We also show that this approach can be extended to indirect image resizing. [ABSTRACT FROM AUTHOR]

One significant problem in tile-based texture synthesis is the presence of conspicuous seams in the tiles. The reason is that sample patches employed as primary patterns of the tile set may not be well stitched if carelessly picked. In this paper, we introduce a robust approach that can stably generate an ω-tile set of high quality and pattern diversity. First, an extendable rule is introduced to increase the number of sample patches to vary the patterns in an ω-tile set. Second, in contrast to other concurrent techniques that randomly choose sample patches for tile construction, ours uses artificial immune system (AIS) to select the feasible patches from the input example. This operation ensures the quality of the whole tile set. Experimental results verify the high quality and efficiency of the proposed algorithm. [ABSTRACT FROM AUTHOR]

Abstract  This paper presents a novel texture synthesis scheme for anisotropic 2D textures based on perspective feature analysis and energy optimization. Given an example texture, the synthesis process starts with analyzing the texel (TEXture ELement) scale variations to obtain the perspective map (scale map). Feature mask and simple user-assisted scale extraction operations including slant and tilt angles assignment and scale value editing are applied. The scale map represents the global variations of the texel scales in the sample texture. Then, we extend 2D texture optimization techniques to synthesize these kinds of perspectively featured textures. The non-parametric texture optimization approach is integrated with histogram matching, which forces the global statics of the texel scale variations of the synthesized texture to match those of the example. We also demonstrate that our method is well-suited for image completion of a perspectively featured texture region in a digital photo. [ABSTRACT FROM AUTHOR]

This paper proposes a new codebook generation algorithm for image data compression using a combined scheme of principal component analysis (PCA) and genetic algorithm (GA). The combined scheme makes full use of the near global optimal searching ability of GA and the computation complexity reduction of PCA to compute the codebook. The experimental results show that our algorithm outperforms the popular LBG algorithm in terms of computational efficiency and image compression performance. [ABSTRACT FROM AUTHOR]