Generating and Exploiting Probabilistic Monocular Depth Estimates
This addresses the need for efficient and adaptable depth estimation in computer vision, though it is incremental as it builds on existing probabilistic methods.
The authors tackled the problem of specialized networks for different depth inference tasks by proposing a versatile task-agnostic monocular model that outputs a probability distribution over scene depth, enabling high accuracy across diverse applications without retraining.
Beyond depth estimation from a single image, the monocular cue is useful in a broader range of depth inference applications and settings---such as when one can leverage other available depth cues for improved accuracy. Currently, different applications, with different inference tasks and combinations of depth cues, are solved via different specialized networks---trained separately for each application. Instead, we propose a versatile task-agnostic monocular model that outputs a probability distribution over scene depth given an input color image, as a sample approximation of outputs from a patch-wise conditional VAE. We show that this distributional output can be used to enable a variety of inference tasks in different settings, without needing to retrain for each application. Across a diverse set of applications (depth completion, user guided estimation, etc.), our common model yields results with high accuracy---comparable to or surpassing that of state-of-the-art methods dependent on application-specific networks.