Search

Despite progress in the past decades, 3D shape acquisition techniques are still a threshold for various 3D face-based applications and have therefore attracted extensive research. Moreover, advanced 2D data generation models based on deep networks may not be directly applicable to 3D objects because of the different dimensionality of 2D and 3D data. In this work, we propose two novel sampling methods to represent 3D faces as matrix-like structured data that can better fit deep networks, namely (1) a geometric sampling method for the structured representation of 3D faces based on the intersection of iso-geodesic curves and radial curves, and (2) a depth-like map sampling method using the average depth of grid cells on the front surface. The above sampling methods can bridge the gap between unstructured 3D face models and powerful deep networks for an unsupervised generative 3D face model. In particular, the above approaches can obtain the structured representation of 3D faces, which enables us to adapt the 3D faces to the Deep Convolution Generative Adversarial Network (DCGAN) for 3D face generation to obtain better 3D faces with different expressions. We demonstrated the effectiveness of our generative model by producing a large variety of 3D faces with different expressions using the two novel down-sampling methods mentioned above. [ABSTRACT FROM AUTHOR]

Due to the rise of e-commerce platforms, online shopping has become a trend. However, the current mainstream retrieval methods are still limited to using text or exemplar images as input. For huge commodity databases, it remains a long-standing unsolved problem for users to find the interested products quickly. Different from the traditional text-based and exemplar-based image retrieval techniques, sketch-based image retrieval (SBIR) provides a more intuitive and natural way for users to specify their search need. Due to the large cross-domain discrepancy between the free-hand sketch and fashion images, retrieving fashion images by sketches is a significantly challenging task. In this work, we propose a new algorithm for sketch-based fashion image retrieval based on cross-domain transformation. In our approach, the sketch and photo are first transformed into the same domain. Then, the sketch domain similarity and the photo domain similarity are calculated, respectively, and fused to improve the retrieval accuracy of fashion images. Moreover, the existing fashion image datasets mostly contain photos only and rarely contain the sketch-photo pairs. Thus, we contribute a fine-grained sketch-based fashion image retrieval dataset, which includes 36,074 sketch-photo pairs. Specifically, when retrieving on our Fashion Image dataset, the accuracy of our model ranks the correct match at the top-1 which is 96.6%, 92.1%, 91.0%, and 90.5% for clothes, pants, skirts, and shoes, respectively. Extensive experiments conducted on our dataset and two fine-grained instance-level datasets, i.e., QMUL-shoes and QMUL-chairs, show that our model has achieved a better performance than other existing methods. [ABSTRACT FROM AUTHOR]

The rapid growth of fabric images needs fast retrieval for related applications, such as fashion design. The goal of fabric image retrieval is to retrieve and rank relevant fabrics from a large scale fabric database to visually assist users' online shopping process in e-commerce. Most of existing solutions to this issue are not invariant with respect to 2D similarity or affine transformations, much less to 3D transformations of textured surface. In this paper, we propose a new search method with a shape based local affine invariant texture characteristics. By employing topographic map to represent fabric images, which is a complete, multi-scale and contrast invariant representation, the proposed method first obtains a tree of shapes from the topographic map. Then, a group of statistics is applied on these shapes to acquire a set of features that are invariant to 3D transformations. We finally represent these features combing relations between shapes, and based on the representation the similarity of pairs of fabric images can be estimated. To evaluate the performance of our algorithm, we conducted a series of experiments on a real-world fabric image dataset, and compared the proposed method with other previous ones. Experimental results demonstrate that the time of the proposed method spending in searching is less than 1 second, and meanwhile a higher PR score than others is obtained. [ABSTRACT FROM AUTHOR]

With the rapid growth of available 3D models in various areas, effective methods to search 3D models are becoming increasingly important. In this paper, we propose a new method for sketch-based 3D model retrieval. Different from current methods that make use of either global or local features, the proposed method uses composite features combining global and local features extracted from representative 2D views of 3D models. The global features, shape strings, represent exterior boundary shape of the views and the local features, improved Pyramid of Histograms of Orientation Gradients (iPHOG), represent their interior details. Specifically, a global feature based filtering step is adopted to select more relevant candidate models to the query sketch and a local feature based process is used to refine chosen candidates. To evaluate the performance of the proposed method with that of other previous ones, we conducted a series of experiments on public standard 3D model databases. Experimental results are presented and indicate the effectiveness of the new approach for sketch-based 3D model retrieval. [ABSTRACT FROM AUTHOR]

Nowadays, the state-of-the-art mobile visual sensors technology makes it easy to collect a great number of clothing images. Accordingly, there is an increasing demand for a new efficient method to retrieve clothing images by using mobile visual sensors. Different from traditional keyword-based and content-based image retrieval techniques, sketch-based image retrieval provides a more intuitive and natural way for users to clarify their search need. However, this is a challenging problem due to the large discrepancy between sketches and images. To tackle this problem, we present a new sketch-based clothing image retrieval algorithm based on sketch component segmentation. The proposed strategy is to first collect a large scale of clothing sketches and images and tag with semantic component labels for training dataset, and then, we employ conditional random field model to train a classifier which is used to segment query sketch into different components. After that, several feature descriptors are fused to describe each component and capture the topological information. Finally, a dynamic component-weighting strategy is established to boost the effect of important components when measuring similarities. The approach is evaluated on a large, real-world clothing image dataset, and experimental results demonstrate the effectiveness and good performance of the proposed method. [ABSTRACT FROM AUTHOR]