Vision tasks that consume such data include automatic scene classification and segmentation, 3D reconstruction, human activity recognition, robotic visual navigation, and more.Ĭall for papers: We invite extended abstracts for work on tasks related to 3D scene generation or tasks leveraging generated 3D scenes. images) or from high-level specifications (e.g. We define "generation of 3D environments" to include methods that generate 3D scenes from sensory inputs (e.g.
In this workshop, we aim to bring together researchers working on automatic generation of 3D environments for computer vision research with researchers who are making use of 3D environment data for a variety of computer vision tasks. To enable large-scale embodied visual learning in 3D environments, we must go beyond such static datasets and instead pursue the automatic synthesis of novel, task-relevant virtual environments. While these existing datasets are a valuable resource, they are also finite in size and don't adapt to the needs of different vision tasks. The community has recently benefited from large scale datasets of both synthetic 3D environments and reconstructions of real spaces, and the development of 3D simulation frameworks for studying embodied agents. Furthermore, AI/vision/robotics researchers are also turning to virtual environments to train data-hungry models for tasks such as visual navigation, 3D reconstruction, activity recognition, and more.Īs the vision community turns from passive internet-images-based vision tasks to applications such as the ones listed above, the need for virtual 3D environments becomes critical. Game developers, VR/AR designers, architects, and interior design firms are all increasingly making use virtual 3D scenes for prototyping and final products.
People spend a large percentage of their lives indoors-in bedrooms, living rooms, offices, kitchens, and other such spaces-and the demand for virtual versions of these real-world spaces has never been higher.
0 kommentar(er)
