We present a method to infer a dense depth map from a color image and associated sparse depth measurements. Our main contribution lies in the design of an annealing process for determining co-visibility (occlusions, disocclusions) and the degree of regularization to impose on the model. We show that regularization and co-visibility are related via the fitness (residual) of model to data and both can be unified into a single framework to improve the learning process. Our method is an adaptive weighting scheme that guides optimization by measuring the residual at each pixel location over each training step for (i) estimating a soft visibility mask and (ii) determining the amount of regularization. We demonstrate the effectiveness our method by applying it to several recent unsupervised depth completion methods and improving their performance on public benchmark datasets, without incurring additional trainable parameters or increase in inference time. Code available at: https://github.com/alexklwong/adaframe-depth-completion.

翻译：我们提出一种方法,从彩色图像和相关的稀薄深度测量中推断出密密深图。我们的主要贡献在于设计一个防冲过程,以确定共同可见性(隔离、分离)和对模型施加的规范化程度。我们表明,正规化和共同可见性通过模型的适合(备用)与数据相关,两者都可以统一成一个单一的框架来改进学习过程。我们的方法是一个适应性加权计划,通过测量每个培训步骤的像素位置的残渣来指导优化,以便(一) 估计软可见度遮罩和(二) 确定正规化的数量。我们展示了我们的方法的有效性,将它应用到最近一些未经监督的深度完成方法上,并改进它们在公共基准数据集上的绩效,同时不产生额外的可培训参数或增加推断时间。代码见:https://github.com/alexklwong/adaframe-destruction。