Sparsity Agnostic Depth Completion

TL;DR

This paper introduces a depth completion method that remains accurate regardless of the sparsity or distribution of input depth points, making it highly adaptable for real-world applications.

Contribution

The proposed approach is robust to varying and extremely low depth point densities, unlike previous methods that are limited to specific training conditions.

Findings

Achieves comparable accuracy to state-of-the-art on standard benchmarks.

Maintains high accuracy across different sparsity levels and distributions.

Demonstrates robustness in both indoor and outdoor environments.

Abstract

We present a novel depth completion approach agnostic to the sparsity of depth points, that is very likely to vary in many practical applications. State-of-the-art approaches yield accurate results only when processing a specific density and distribution of input points, i.e. the one observed during training, narrowing their deployment in real use cases. On the contrary, our solution is robust to uneven distributions and extremely low densities never witnessed during training. Experimental results on standard indoor and outdoor benchmarks highlight the robustness of our framework, achieving accuracy comparable to state-of-the-art methods when tested with density and distribution equal to the training one while being much more accurate in the other cases. Our pretrained models and further material are available in our project page.