A new method is presented for producing photo collages that preserve content correlation of photos. We use deep learning techniques to find correlation among given photos to facilitate their embedding on the canvas, and develop an efficient combinatorial optimization technique to make correlated photos stay close to each other. To make efficient use of canvas space, our method first extracts salient regions of photos and packs only these salient regions. We allow the salient regions to have arbitrary shapes, therefore yielding informative, yet more compact collages than by other similar collage methods based on salient regions. We present extensive experimental results, user study results, and comparisons against the state-of-the-art methods to show the superiority of our method.

We introduce in this paper a new approach that conveniently converts conversational videos into comics with manga-style layout. With our approach, the manga-style layout of a comic page is achieved in a content-driven manner, and the main components, including panels and word balloons, that constitute a visually pleasing comic page are intelligently organized . Our approach extracts key frames on speakers by using a speaker detection technique such that word balloons can be placed near the corresponding speakers. We qualitatively measure the information contained in a comic page. With the initial layout automatically determined, the final comic page is obtained by maximizing such a measure and optimizing the parameters relating to the optimal display of comics. An efficient Markov chain Monte Carlo sampling algorithm is designed for the optimization. Our user study demonstrates that users much prefer our manga-style comics to purely Western style comics. Extensive experiments and comparisons against previous work also verify the effectiveness of our approach.

In this paper, we propose a novel edge prior for image interpolation which assumes that the variation of image intensity away from an edge is locally similar along the edge. Based on this edge prior, our method first approximates the gradient of the HR image which is then refined by diffusion. The unknown HR pixels are estimated by a weighted average of their neighbouring LR samples, with the weights being determined with respect to the gradient. This new approach performs significantly better than several representative edge-directed image interpolation methods in terms of PSNR and SSIM, as well as subjective visual quality in most of our test cases. Annoying artifacts (such as blurring, jaggies, ringing, etc.) are also greatly suppressed.