This paper aims to make GAN inversion and interpretability possible. Through the lens of differential geometry, the authors propose that the metric tensor has various interpretability properties – by realising it as the Hessian matrix of the distance metric.
You May Also Enjoy
This paper introduces an unsupervised method to generate masks(🎭) for facial datasets (😀) without any human annotations involved.
SDEdit is an image synthesis and editing framework based on stochastic differential equations (SDEs). SDEdit allows stroke-based image synthesis, stroke-based image editing and image compositing without task specific optimization.
An interesting method has come up that edits facial attributes, without allowing the loss of tattoos and pimples. This report will be a journey through this paper.
This report presents and summarizes the latest developments in Score based generative models – with a goal to enable better understanding of existing approaches, new sampling algorithms, exact likelihood computation and conditional generation abilties to the family of score based generative models.