【摘 要】
：
Capturing aerial videos with a quadrotor-mounted camera is a challenging creative task,as it requires the simultaneous control of the quadrotors position and the mounted cameras orientation.
【出 处】
：
2018计算机图形学与混合现实前沿研讨会
论文部分内容阅读
Capturing aerial videos with a quadrotor-mounted camera is a challenging creative task,as it requires the simultaneous control of the quadrotors position and the mounted cameras orientation.
其他文献
近年来，大量的智能手机、嵌入式设备、传感器节点等设备产生了海量的数据，相比于传统的数据处理方法，基于深度学习的卷积神经网络可以更加智能地分析和处理这些数据。然而，卷积神经网络在计算和存储方面都是十分密集的，这使得他们很难被部署到资源受限的系统中，从而也限制了它们的广泛应用。本文基于卷积神经网络的特点，首先对原始卷积神经网络进行裁剪，剪去不重要的连接，从而将密集的卷积神经网络模型转换成稀疏模型，在这
Correspondence between images is a fundamental problem in computer vision,with a variety of graphical applications.
We propose the first deep learning approach for exemplar-based colorization.
云存储系统采用虚拟化技术将分布于不同地域的计算机资源进行集中管理和分配,通过资源复用的方式,有效地提高资源利用率,也降低了软硬件维护代价.然而,资源复用导致了应用之间的相互干扰和竞争.遗憾的是,现有的分布式块存储系统对服务质量的控制与支持严重不足,特别是在资源需求量超出存储系统能力时,无法提供令人满意的服务质量,迫切地需要提出一种满足高效、稳定的存储服务质量解决方案.存储服务质量应从两个维度进行支
We present a learning-based method to control a coupled system involving both fluid and rigid bodies.
We propose a novel approach,called Progressive Parameterizations,to compute foldover-free parameterizations with low isometric distortion on disk topology meshes.
Many computer graphics problems require computing geometric shapes subject to certain constraints.
Autonomous 3D scene scanning and reconstruction of unknown indoor scenes by mo bite robots with depth sensors has become an active research area in recent years.
Humans can predict the functionality of an object even without any surroundings,since their knowledge and experience would allow them to "hallucinate the interaction or usage scenarios involving the o
The real world exhibits an abundance of non-stationary textures.Examples include textures with large scale structures,as well as spatially variant and inhomogeneous textures.