In Virtual Reality (VR), adversarial attack remains a significant security threat. Most deep learning-based methods for physical and digital adversarial attacks focus on enhancing attack performance by crafting advers...
详细信息
ISBN:
(纸本)9798350374490;9798350374506
In Virtual Reality (VR), adversarial attack remains a significant security threat. Most deep learning-based methods for physical and digital adversarial attacks focus on enhancing attack performance by crafting adversarial examples that contain large printable distortions that are easy for human observers to identify. However, attackers rarely impose limitations on the naturalness and comfort of the appearance of the generated attack image, resulting in a noticeable and unnatural attack. To address this challenge, we propose a framework to incorporate style transfer to craft adversarial inputs of natural styles that exhibit minimal detectability and maximum natural appearance, while maintaining superior attack capabilities.
Hand-object occlusion is crucial to enhance the realism of Augmented Reality, especially for egocentric hand-object interaction scenes. In this paper, a hand segmentation-based depth correction approach is proposed, w...
详细信息
ISBN:
(纸本)9798350348392
Hand-object occlusion is crucial to enhance the realism of Augmented Reality, especially for egocentric hand-object interaction scenes. In this paper, a hand segmentation-based depth correction approach is proposed, which can help to realize real-time hand-object occlusion. We introduce a lightweight convolutional neural network to quickly obtain real hand segmentation mask. Based on the hand mask, different strategies are adopted to correct the depth data of hand and non-hand regions, which can implement hand-object occlusion and object-object occlusion simultaneously to deal with complex hand situations during interaction. The experimental results demonstrate the feasibility of our approach presenting visually appealing occlusion effects.
Hoarding behaviour is a widespread issue in which people have difficulty discarding or parting with their possessions. We present our work to address hoarding behaviours in people and promote the selling or donating o...
详细信息
ISBN:
(数字)9781665453653
ISBN:
(纸本)9781665453653
Hoarding behaviour is a widespread issue in which people have difficulty discarding or parting with their possessions. We present our work to address hoarding behaviours in people and promote the selling or donating of items that they no longer use or value through an online marketplace application (app). We introduce DeclutterAR, a feature linked to the marketplace app that uses Diminished Reality to remove real-world objects in the Augmented Reality (AR) scene, allowing you to visualise your "cluttered spaces" as "decluttered spaces". DeclutterAR also allows users to sort removed objects to sell or give away. This work describes the system implementation and preliminary user study and discusses concepts of using Diminished Reality to motivate and support users in visualising target behaviours.
暂无评论