The number of photos and videos being taken each second is staggering, and keeps rising. Photos and videos are a cornerstone of communication, yet exiting tools such as Photoshop are overwhelming and hard to master, and typically supply low-level interactions that must be combined to achieve high-level goals. New tools are needed: goal-oriented tools which are easy to use, allowing users to reflect unique creative objectives.
I will start the talk by showing how zooming in on a specific input domain can produce a strong prior that in turn leads to powerful algorithms. We will explore the domain of human portraits, showing our works on perspective manipulation and lighting optimization. We will then discuss other strategies for the creation of useable editing tools, detailing our works on image recoloring and distractor removal. I will end the talk with several (exciting!) directions for future work.
Ohad Fried, is a postdoctoral research scholar at Stanford University, working with Prof. Maneesh Agrawala. His work lies in the intersection of computer graphics, computer vision, and HCI. For his PhD he worked with Prof. Adam Finkelstein as part of the Princeton Graphics group. He holds an M.Sc. in Computer Science and a B.Sc. in Computational Biology, both from The Hebrew University. His research focuses on tools, algorithms, and new paradigms for photo and video editing.