DDD: Deep indoor panoramic Depth estimation with Density maps consistency

We introduce a novel deep neural network for rapid and structurally consistent monocular 360° depth estimation in indoor environments. The network infers a depth map from a single gravity-aligned or gravity-rectified equirectangular image of the environment, ensuring that the predicted depth aligns with the typical depth distribution and features of cluttered interior spaces, which are usually enclosed by walls, ceilings, and floors. By leveraging the distinct characteristics of vertical and horizontal features in man-made indoor environments, we introduce a lean network architecture that employs gravity-aligned feature flattening and specialized vision transformers that utilize the input's omnidirectional nature, without segmentation into patches and positional encoding. To enhance the structural consistency of the predicted depth, we introduce a new loss function that evaluates the consistency of density maps by projecting points derived from the inferred depth map onto horizontal and vertical planes. This lightweight architecture has very small computational demands, provides greater structural consistency than competing methods, and does not require the explicit imposition of strong structural priors.