Interactive digital photomontage

Abstract

We describe an interactive, computer-assisted framework for combining parts of a set of photographs into a single composite picture, a process we call "digital photomontage." Our framework makes use of two techniques primarily: graph-cut optimization, to choose good seams within the constituent images so that they can be combined as seamlessly as possible; and gradient-domain fusion, a process based on Poisson equations, to further reduce any remaining visible artifacts in the composite. Also central to the framework is a suite of interactive tools that allow the user to specify a variety of high-level image objectives, either globally across the image, or locally through a painting-style interface. Image objectives are applied independently at each pixel location and generally involve a function of the pixel values (such as "maximum contrast") drawn from that same location in the set of source images. Typically, a user applies a series of image objectives iteratively in order to create a finished composite. The power of this framework lies in its generality; we show how it can be used for a wide variety of applications, including "selective composites" (for instance, group photos in which everyone looks their best), relighting, extended depth of field, panoramic stitching, clean-plate production, stroboscopic visualization of movement, and time-lapse mosaics.

A focus fusion framework with anisotropic depth map smoothing

“…A representative of segmentation-based techniques is the method of Agarwala et al [13]. In particular to evaluate our depth map estimation, we additionaly compare our results to the depth-from-defocus method of Aguet et al [44].…”

“…Unfortunately this may also cause smoothing of important image structures such that the resulting images appear blurred and not sharp everywhere. Hence, researchers came up with the idea of not applying the smoothness constraint on the resulting image itself, but on the per-pixel decision of the in-focus areas: In [13,14,15,16,17,18] the authors determine an initial decision map by means of a specific sharpness criterion. Subsequently they segment these maps into regions that belong to the same input frames.…”

“…These segments are then used to fuse the input images to an all-in-focus composite, or even to recover an underlying 3-D surface. Agarwala et al [13] use graphcut optimisation to segment different in-focus areas and fuse the input images in the gradient domain.Šroubek et al [14] propose a level-set segmentation on the decision map solving a suitable PDE. Similarly, in the method of Li and Yang [15] the images are segmented with the normalized cut method; this method is further extended in the work of Liu et al [19].…”

A Hierarchical Approach for High-Quality and Fast Image Completion

“…Once the graph and energy function are given, the shift-map labeling is computed using multi-label graph-cuts algorithm [14,15].…”

Morphological image compositing

“…It consists of minimizing a cost function defined by a dissimilarity measurement between the sum of the distance (L p norm) between the derivatives of the initial image and the composed image. A similar gradient-domain fusion based on Poisson equations and combined with a graph-cut optimization scheme relying on a minimization procedure described in [8] is developed by Agarwala et al [2]. The use of graph-cut techniques for image compositing was originally explored by Kwatra et al [21] in the context of texture synthesis, where patch regions from a sample image or video are transformed and stitched together along optimal seams to generate a new output.…”