AutoPoster: A Highly Automatic and Content-aware Design System for Advertising Poster Generation

Advertising posters, a form of information presentation, combine visual and linguistic modalities. Creating a poster involves multiple steps and necessitates design experience and creativity. This paper introduces AutoPoster, a highly automatic and content-aware system for generating advertising posters. With only product images and titles as inputs, AutoPoster can automatically produce posters of varying sizes through four key stages: image cleaning and retargeting, layout generation, tagline generation, and style attribute prediction. To ensure visual harmony of posters, two content-aware models are incorporated for layout and tagline generation. Moreover, we propose a novel multi-task Style Attribute Predictor (SAP) to jointly predict visual style attributes. Meanwhile, to our knowledge, we propose the first poster generation dataset that includes visual attribute annotations for over 76k posters. Qualitative and quantitative outcomes from user studies and experiments substantiate the efficacy of our system and the aesthetic superiority of the generated posters compared to other poster generation methods.

A multilateral filtering method applied to airplane runway image

By considering the features of the airport runway image filtering, an improved bilateral filtering method was proposed which can remove noise with edge preserving. Firstly the steerable filtering decomposition is used to calculate the sub-band parameters of 4 orients, and the texture feature matrix is then obtained from the sub-band local median energy. The texture similar, the spatial closer and the color similar functions are used to filter the image.The effect of the weighting function parameters is qualitatively analyzed also. In contrast with the standard bilateral filter and the simulation results for the real airport runway image show that the multilateral filtering is more effective than the standard bilateral filtering.