Self-supervised learning using view synthesis
Recently, there has been great progress in synthesizing novel views on objects [1,2,3,4]. At the same time, augmentations have been found to be crucial component in self-supervised learning systems . In such systems, generated views could serve as a form of augmentation which do not shift the intensity distribution of the image (other than e.g. color augmentation).
 Wiles et al.: SynSin: End-to-end View Synthesis from a Single Image
 NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis
 T. Chen et al.: A simple framework for contrastive learning of visual representations
- Good mathematical understanding (in particular statistics and linear algebra)
- Python programming
- Experience in machine learning