Transfer in Photography Composition

Abstract

In this paper, we propose novel photography recomposition method, which aims at transferring the photography composition of a reference image to an input image automatically. Without any user interaction, our approach first identifies the salient foreground objects or image regions of interest, and the recomposition is performed by solving a graph-matching based optimization task. With additional post-processing step to preserve the locality and boundary information of the recomposed visual components, we can solve the task of photography recomposition without the uses of any prior knowledge on photography or predetermined image aesthetics rules. Experiments on a variety of images, including transferring the photography composition from real photos, sketches or even paintings, would confirm the effectiveness of our proposed method.

Identification of Panoramic Photographic Image Composition Using Fuzzy Rules

“…Recently, Chang et al [ 20 ] proposed a photography recomposition method that automatically transfers the composition type of a reference image to an input image. An in-depth study about taking a good picture was proposed in [ 21 ], especially for photographic composition.…”

“…However, those methods only consider the photographic composition based on the case of traditional images. In addition, some automatic identification methods for modifying the photo composition are proposed [ 20 , 22 ]. At first, salient regions such as subjects are extracted from the image and then their locations are changed to match the predetermined types of photo compositions, for example, the center composition and rule of thirds.…”

“…Contrast rule: The regions surrounding the main subject will have low contrast, and the feature SDNGV can measure this in Equation (20). The main subject has a significant contrast with its surrounding region, while the SDNGV is smaller than the predefined threshold value T SDNGV .…”

A Comprehensive Survey on Computational Aesthetic Evaluation of Visual Art Images: Metrics and Challenges

“…Discrete approaches rearrange the patches to obtain the recomposed image. The cut-andpaste approaches extract foreground objects from the input image and then paste them back into optimal positions based on a set of photographic composition rules and constraints [122], of which the dependence-aware scheme [132] relocates the foreground objects together with their dependent regions to the optimal position, while the exemplar-based approach relocates the photo subjects [133] using the graphmatch optimization. Seam carving-based approaches [134] rearrange a given image by iteratively inserting and removing a set of seams containing significant objects on the contrary direction.…”