Wide-baseline Novel Scene Synthesis from a Single Image

Novel view synthesis is the process of generating new images from an unseen perspective, given at least one image of a scene. There may be more than one probable novel view associated with each unseen perspective, an assumption made by existing methods. This simplifying assumption prevents these methods from being applied to more difficult novel views where the set of probable novel views is highly varied. This project proposes to investigate a new approach to generate a wide variety novel views from a single image, and can produce multiple probable outputs. The proposed project will also evaluate the efficacy of the approach with existing approaches on a wide range of camera poses. Major components of this project utilize methods that can be applied to a wider range of domains than computer vision. RBC is a major Canadian bank that can leverage developed methods as part of their products and services.

Faculty Supervisor:

Michael S. Brown;Kosta Derpanis

Student:

Jason Yu

Partner:

Borealis AI

Discipline:

Engineering - computer / electrical

Sector:

Information and communications technologies

University:

York University