Panoramic depth estimation gains importance with more 360°images being widely available. However, traditional mono-to-depth approaches, optimized for a limited field of view, show subpar performance when naively adapted. Methods tailored to process panoramic input improve predictions but can not overcome ambiguous visual information and scale-uncertainty inherent to the task.

In this paper we show the benefits of leveraging sound for improved panoramic depth estimation. Specifically, we harness audible echoes from emitted chirps as they contain rich geometric and material cues about the surrounding environment. We show that these auditory cues can enhance a state-of-the-art panoramic depth prediction framework. By integrating sound information, we improve this vision-only baseline by ≈ 12%.

Our approach requires minimal modifications to the underlying architecture, making it easily applicable to other baseline models. We validate its efficacy on the Matterport3D and Replica datasets, demonstrating remarkable improvements in depth estimation accuracy.