In this paper, we introduce a very large Chinese text dataset in the wild. While optical character recognition (OCR) in document images is well studied and many commercial tools are available, the detection and recognition of text in natural images is still a challenging problem, especially for some more complicated character sets such as Chinese text. Lack of training data has always been a problem, especially for deep learning methods which require massive training data. In this paper, we provide details of a newly created dataset of Chinese text with about 1 million Chinese characters from 3 850 unique ones annotated by experts in over 30 000 street view images. This is a challenging dataset with good diversity containing planar text, raised text, text under poor illumination, distant text, partially occluded text, etc. For each character, the annotation includes its underlying character, bounding box, and six attributes. The attributes indicate the character’s background complexity, appearance, style, etc. Besides the dataset, we give baseline results using state-of-the-art methods for three tasks: character recognition (top-1 accuracy of 80.5%), character detection (AP of 70.9%), and text line detection (AED of 22.1). The dataset, source code, and trained models are publicly available.

This paper presents a survey of image synthesis and editing with Generative Adversarial Networks (GANs). GANs consist of two deep networks, a generator and a discriminator, which are trained in a competitive way. Due to the power of deep networks and the competitive training manner, GANs are capable of producing reasonable and realistic images, and have shown great capability in many image synthesis and editing applications. This paper surveys recent GAN papers regarding topics including, but not limited to, texture synthesis, image inpainting, image-to-image translation, and image editing.

Photon mapping is a widely used technique for global illumination rendering. In the density estimation step of photon mapping, the indirect radiance at a shading point is estimated through a filtering process using nearby stored photons; an isotropic filtering kernel is usually used. However, using an isotropic kernel is not always the optimal choice, especially for cases when eye paths intersect with surfaces with anisotropic BRDFs. In this paper, we propose an anisotropic filtering kernel for density estimation to handle such anisotropic eye paths. The anisotropic filtering kernel is derived from the recently introduced anisotropic spherical Gaussian representation of BRDFs. Compared to conventional photon mapping, our method is able to reduce rendering errors with negligible additional cost when rendering scenes containing anisotropic BRDFs.