Magic Forest Illustrated by Aubrey Beardsley in “Le Morte D`Arthur”: Image Semantics and its Russian “Replication”

The “magic forest” illustrated by Aubrey Beardsley in spite of the continuity in relation to the Pre-Raphaelite and the reconstructed Middle Ages / Renaissance in the works, dedicated to Arthur on the pages of the Kelmscott Press publications, has a number of peculiar features. The semantics of the natural images of the black-and-white illustrations to Thomas Malory's “Le Morte D`Arthur” turns out to be consonant with both the folklore (pagan in its essence) ideas about the forest as other world, and the Christian symbolism of the passion forest, this uncultivated “exile lands”. The essential features of the “Beardsley`s forest” can include its gloominess (black grass, spectacular haze of frames), inaccessibility (thickets of giant bindweed “stifling” knights, fence of trunks, represented as the border of the forest edge, thorns, reminding of the torments of earthly love and its sinfulness). Thomas Malory reduces the element of unbelievable in his narration; Beardsley, on the contrary, returns dragons, fairies, satyrs to the Forest. The paper addresses the background of the first publications of his “forest” graphics in Russia, notes the transfer of emphasis from the medieval forest topic to the motif of the landscape garden that is more consonant with the rockail aesthetics. The authors also draw comparison of interpretation of the forest image and its goat-footed guardians, satyrs, in the representation of the English illustrator and in the text of the “Northern Symphony” by A. Bely.

A survey of image semantics-based visual simultaneous localization and mapping: Application-oriented solutions to autonomous navigation of mobile robots

As one of the typical application-oriented solutions to robot autonomous navigation, visual simultaneous localization and mapping is essentially restricted to simplex environmental understanding based on geometric features of images. By contrast, the semantic simultaneous localization and mapping that is characterized by high-level environmental perception has apparently opened the door to apply image semantics to efficiently estimate poses, detect loop closures, build 3D maps, and so on. This article presents a detailed review of recent advances in semantic simultaneous localization and mapping, which mainly covers the treatments in terms of perception, robustness, and accuracy. Specifically, the concept of “semantic extractor” and the framework of “modern visual simultaneous localization and mapping” are initially presented. As the challenges associated with perception, robustness, and accuracy are being stated, we further discuss some open problems from a macroscopic view and attempt to find answers. We argue that multiscaled map representation, object simultaneous localization and mapping system, and deep neural network-based simultaneous localization and mapping pipeline design could be effective solutions to image semantics-fused visual simultaneous localization and mapping.

The Missing Data Encoder: Cross-Channel Image Completion with Hide-and-Seek Adversarial Network

Image completion is the problem of generating whole images from fragments only. It encompasses inpainting (generating a patch given its surrounding), reverse inpainting/extrapolation (generating the periphery given the central patch) as well as colorization (generating one or several channels given other ones). In this paper, we employ a deep network to perform image completion, with adversarial training as well as perceptual and completion losses, and call it the “missing data encoder” (MDE). We consider several configurations based on how the seed fragments are chosen. We show that training MDE for “random extrapolation and colorization” (MDE-REC), i.e. using random channel-independent fragments, allows a better capture of the image semantics and geometry. MDE training makes use of a novel “hide-and-seek” adversarial loss, where the discriminator seeks the original non-masked regions, while the generator tries to hide them. We validate our models qualitatively and quantitatively on several datasets, showing their interest for image completion, representation learning as well as face occlusion handling.