Figure 1. New "pets" generated using ConceptLab. Each pair depicts a learned concept that was optimized to be unique and distinct from existing members of the pet category. Our method can generate a variety of novel concepts from a single broad category.

No abstract

No abstract

Recently, there has been a surge of diverse methods for performing image editing by employing pre-trained unconditional generators. Applying these methods on real images, however, remains a challenge, as it necessarily requires the inversion of the images into their latent space. To successfully invert a real image, one needs to find a latent code that reconstructs the input image accurately, and more importantly, allows for its meaningful manipulation. In this paper, we carefully study the latent space of StyleGAN, the state-of-the-art unconditional generator. We identify and analyze the existence of a distortion-editability tradeoff and a distortion-perception tradeoff within the StyleGAN latent space. We then suggest two principles for designing encoders in a manner that allows one to control the proximity of the inversions to regions that StyleGAN was originally trained on. We present an encoder based on our two principles that is specifically designed for facilitating editing on real images by balancing these tradeoffs. By evaluating its performance qualitatively and quantitatively on numerous challenging domains, including cars and horses, we show that our inversion method, followed by common editing techniques, achieves superior real-image editing quality, with only a small reconstruction accuracy drop.

Figure 1: Real image editing via StyleGAN inversion using our e4e method. For each domain we show from left to right: the original real image, the inverted image, and multiple manipulations performed using various editing techniques.

Learning disentangled representations of data is a fundamental problem in artificial intelligence. Specifically, disentangled latent representations allow generative models to control and compose the disentangled factors in the synthesis process. Current methods, however, require extensive supervision and training, or instead, noticeably compromise quality. In this paper, we present a method that learns how to represent data in a disentangled way, with minimal supervision, manifested solely using available pre-trained networks. Our key insight is to decouple the processes of disentanglement and synthesis, by employing a leading pre-trained unconditional image generator, such as StyleGAN. By learning to map into its latent space, we leverage both its state-of-the-art quality, and its rich and expressive latent space, without the burden of training it. We demonstrate our approach on the complex and high dimensional domain of human heads. We evaluate our method qualitatively and quantitatively, and exhibit its success with de-identification operations and with temporal identity coherency in image sequences. Through extensive experimentation, we show that our method successfully disentangles identity from other facial attributes, surpassing existing methods, even though they require more training and supervision.

A rapidly spreading decline of 'Minneola' tangelos, 'Shamouti' and 'Valencia' sweet oranges grafted on sour orange rootstock in the Morasha area, in the coastal plain of Israel, was found to be caused by a severe 'seedling yellows' strain of the citrus tristeza virus (CTV). Repeated ELISA tests revealed great variation in distribution of CTV throughout the canopies, even in declining trees. In a substantial number of the declining trees, samples of up to 10 twigs per tree were not always sufficient for CTV detection. The ELISA values (O.D. 405 nm) in the parts found infected were high, whereas in most of the twigs showing negative ELISA results the virus was absent as indicated by biological indexing. The Morasha strain of CTV was also characterised by rapid annual spread rates. The ratio D/E (the proportion of Declining trees found among ELISA-positive ones) is proposed as a simple index of strain severity. The epidemiological consequences of the uneven distribution of CTV and rapid decline are discussed.

No abstract