A New Distributional Ranking Loss With Uncertainty: Illustrated in Relative Depth Estimation
This work addresses depth estimation for computer vision applications, offering incremental improvements through a novel loss function and uncertainty modeling.
The paper tackles relative depth estimation from a single image by formulating it as a probability distribution estimation problem, achieving state-of-the-art results with a new ranking loss that also outputs confidence estimates, which are shown to correlate with accuracy and improve downstream metric depth estimation.
We propose a new approach for the problem of relative depth estimation from a single image. Instead of directly regressing over depth scores, we formulate the problem as estimation of a probability distribution over depth and aim to learn the parameters of the distributions which maximize the likelihood of the given data. To train our model, we propose a new ranking loss, Distributional Loss, which tries to increase the probability of farther pixel's depth being greater than the closer pixel's depth. Our proposed approach allows our model to output confidence in its estimation in the form of standard deviation of the distribution. We achieve state of the art results against a number of baselines while providing confidence in our estimations. Our analysis show that estimated confidence is actually a good indicator of accuracy. We investigate the usage of confidence information in a downstream task of metric depth estimation, to increase its performance.