Creating detailed 3D characters from a single image remains challenging due to the difficulty in separating semantic components during generation. Existing methods often produce entangled meshes with poor topology, hindering downstream applications like rigging and animation. We introduce SeparateGen, a novel framework that generates high-quality 3D characters by explicitly reconstructing them as distinct semantic components (e.g., body, clothing, hair, shoes) from a single, arbitrary-pose image. SeparateGen first leverages a multi-view diffusion model to generate consistent multi-view images in a canonical A-pose. Then, a novel component-aware reconstruction model, SC-LRM, conditioned on these multi-view images, adaptively decomposes and reconstructs each component with high fidelity. To train and evaluate SeparateGen, we contribute SC-Anime, the first large-scale dataset of 7,580 anime-style 3D characters with detailed component-level annotations. Extensive experiments demonstrate that SeparateGen significantly outperforms state-of-the-art methods in both reconstruction quality and multi-view consistency. Furthermore, our component-based approach effectively resolves mesh entanglement issues, enabling seamless rigging and asset reuse. SeparateGen thus represents a step towards generating high-quality, application-ready 3D characters from a single image. The SC-Anime dataset and our code will be publicly released.

Information hiding is a technique that embeds secret data in digital media for using in a variety of applications, including ownership protection, authentication, access control, annotation and so on. In this paper, we propose an information hiding scheme based on quantization-based embedding technique to conceal information in gray-scale image. The proposed scheme was tested with a variety of gray images. According to the experimental results, hidden information can be extracted correctly and quickly from the stego image. In addition, the stego image has only a little distortion compared with the cover image. The proposed scheme can not only hide a large amount of information in the cover image, but can also repair the stego image such that the repaired image is almost the same as the cover image.

In order to improve the compression rate of vector quantization (VQ) during compression, a re-encoding scheme, called spiral scan re-encoding (SSR), was designed to compact the indices in VQ. Based on the SSR scheme, we propose a novel lossless hiding scheme, called IHSSR. When the scheme is used, information is hidden in the compression code for increasing the bandwidth efficiency of the compressed code. The IHSSR system was developed to test the performance of the IHSSR scheme. According to the experimental results, the IHSSR system can efficiently hide secret information in the compression code of indices without modifying its content. The decoding process can obtain the hidden secret information and the indices. Only a small number of extra bits are needed to record the corresponding information.