Object-centered image stitching
This work solves the problem of object-related stitching artifacts for users who require high-quality, realistic stitched images, representing an incremental improvement to existing methods.
The paper addresses problematic failures in image stitching where objects are cropped, omitted, or duplicated. By modifying the energy function in the seam finding stage to penalize these object-related errors, the authors achieve substantially more realistic stitching results on challenging imagery.
Image stitching is typically decomposed into three phases: registration, which aligns the source images with a common target image; seam finding, which determines for each target pixel the source image it should come from; and blending, which smooths transitions over the seams. As described in [1], the seam finding phase attempts to place seams between pixels where the transition between source images is not noticeable. Here, we observe that the most problematic failures of this approach occur when objects are cropped, omitted, or duplicated. We therefore take an object-centered approach to the problem, leveraging recent advances in object detection [2,3,4]. We penalize candidate solutions with this class of error by modifying the energy function used in the seam finding stage. This produces substantially more realistic stitching results on challenging imagery. In addition, these methods can be used to determine when there is non-recoverable occlusion in the input data, and also suggest a simple evaluation metric that can be used to evaluate the output of stitching algorithms.