Electrical and Computer Engineering ETDs

Publication Date



Current methods for combining different images produce visible artifacts when the sources have very different textures and structures, come from far view points, or capture dynamic scenes with motions. In this thesis, we propose a patch-based synthesis algorithm to plausibly combine different images that have color, texture, structural, and geometric inconsistencies. For some applications such as cloning and stitching where a gradual blend is required, we present a new method for synthesizing a transition region between two source images, such that inconsistent properties change gradually from one source to the other. We call this process image melding. For gradual blending, we generalized patch-based optimization foundation with three key generalizations: First, we enrich the patch search space with additional geometric and photometric transformations. Second, we integrate image gradients into the patch representation and replace the usual color averaging with a screened Poisson equation solver. Third, we propose a new energy based on mixed L2/L0 norms for colors and gradients that produces a gradual transition between sources without sacrificing texture sharpness. Together, all three generalizations enable patch-based solutions to a broad class of image melding problems involving inconsistent sources: object cloning, stitching challenging panoramas, hole filling from multiple photos, and image harmonization. We also demonstrate another application which requires us to address inconsistencies across the images: high dynamic range (HDR) reconstruction using sequential exposures. In this application, the results will suffer from objectionable artifacts for dynamic scenes if the inconsistencies caused by significant scene motions are not handled properly. In this thesis, we propose a new approach to HDR reconstruction that uses information in all exposures while being more robust to motion than previous techniques. Our algorithm is based on a novel patch-based energy-minimization formulation that integrates alignment and reconstruction in a joint optimization through an equation we call the HDR image synthesis equation. This allows us to produce an HDR result that is aligned to one of the exposures yet contains information from all of them. These two applications (image melding and high dynamic range reconstruction) show that patch based methods like the one proposed in this dissertation can address inconsistent images and could open the door to many new image editing applications in the future.


Image processing--Digital techniques., Image reconstruction., Morphing (Computer animation)


National Science Foundation under grant IIS-0845396, Adobe Systems Inc

Document Type




Degree Name

Computer Engineering

Level of Degree


Department Name

Electrical and Computer Engineering

First Advisor

Sen, Pradeep

First Committee Member (Chair)

Ghani, Nasir

Second Committee Member

Mostofi, Yasamin

Third Committee Member

Kniss, Joe