Synthesizing Photorealistic Images with Deep Generative Learning
It addresses image synthesis problems for computer vision applications, but appears incremental as it builds on existing deep generative learning paradigms.
This thesis tackled visual synthesis tasks like image translation and completion by developing new learning-based approaches, demonstrating superiority in generating plausible and realistic images, with some methods also aiding depth estimation.
The goal of this thesis is to present my research contributions towards solving various visual synthesis and generation tasks, comprising image translation, image completion, and completed scene decomposition. This thesis consists of five pieces of work, each of which presents a new learning-based approach for synthesizing images with plausible content as well as visually realistic appearance. Each work demonstrates the superiority of the proposed approach on image synthesis, with some further contributing to other tasks, such as depth estimation.