Sparsity Agnostic Depth Completion
This addresses a practical limitation for real-world depth sensing applications where input point characteristics vary unpredictably.
The paper tackles the problem of depth completion methods being sensitive to specific density and distribution of input points, which limits real-world deployment. Their sparsity-agnostic approach achieves comparable accuracy to state-of-the-art methods under matched training conditions and significantly better accuracy with uneven distributions or extremely low densities.
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.