Cal Poly
Video Generation Techniques for Novel View Synthesis with Flow-Matching Transformers
Abstract
dc:description.abstractNovel view synthesis (NVS) aims to generate images of a scene from unseen camera viewpoints. Recent work, such as Stable Virtual Camera, shows that large-scale image diffusion models like Stable Diffusion can be adapted for pose-conditioned view synthesis by incorporating video-generation techniques with camera conditioning. In this thesis, we introduce MVFlow, a new NVS model that extends this approach to a different image generation architecture: a flow-matching diffusion transformer, specifically FLUX.1, which has demonstrated strong performance in image synthesis. We evaluate MVFlow under varying input view counts and pose distance settings. Our results show that this architectural transfer is feasible; however, the current architecture and conditioning strategy do not yet match the performance of a mature baseline such as Stable Virtual Camera.
Degree
thesis:*- Name thesis:degree_name
- MS in Computer Science
- Discipline thesis:degree_discipline
- Computer Science
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Qiu, Xiuyuan
- Contributors dc:contributor
-
- Jonathan Ventura
- Computer Science
- College of Engineering
Subjects
dc:subject × 6Identifiers
dc:identifier.*- Repository record dc:identifier
- https://digitalcommons.calpoly.edu/theses/3246