Multi-level Optimization Approaches to Computer Vision

Опубликовано 7 мая 2020, 20:56

On a broad level, computer graphics involves representing 3D information in 2D. Computer vision can be thought of as the inverse problem - inferring 3D information from a projected representation. This talk will discuss two deep learning approaches to 3D human pose estimation and single-view object reconstruction that attempt to learn about solution feasibility while incorporating simple computer graphics techniques to ensure consistency with observations. The first approach optimizes a GAN to produce a parameterization of the feasible solution space, then seeks a solution in that space which is maximally consistent with observations. The follow-up approach is based on combining these optimization steps into a single nested optimization problem.

See more at microsoft.com/en-us/research/v...