本文介绍了使用多尺度深度网络从单张图像预测深度图的方法。论文中，全局粗略网络首先预训练于ImageNet，其输出被精细网络作为第一层图像特征使用，以编辑粗略预测并匹配局部细节。数据增强包括缩放、平移、旋转和颜色变化等，以增加模型泛化能力。采用尺度不变误差衡量预测精度，网络最终输出是对数深度。实验在NYU Depth和KITTI数据集上进行，并提出未来可以结合3D几何信息如表面法线以提升性能。
Eigen, David, Christian Puhrsch, and Rob Fergus. “Depth map prediction from a single image using a multi-scale deep network.” Advances in neural information processing systems. 2014. (Citations: 161).
Need to use the monocular depth cues such as line angles and perspective, objective sizes, image position, and atmospheric effects. This task is inherently ambiguous. Given an image, an infinite number of possible world scenes may have produced it.
2 Architecture
In a Nutshell See Fig. 14.• A coarse-scale network first predicts the depth of the scene at a global level.
• This is then refined within local regions by a fine-scale network.
• Both stacks are applied to the original input.
• The coarse network’s output is passed to the fine network as additional first-layer image features.
最低0.47元/天 解锁文章
1137
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
