Sparsity Agnostic Depth Completion

Andrea Conti · Matteo Poggi · Stefano Mattoccia

[Paper] [Code]

Overview

State-of-the-art Depth Completion 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. We present a framework:

• robust to uneven distributions and extremely low densities by structure
• trained with a fixed pattern and density as competitors, without any need of augmenting

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.

Qualitative Results

Reference

@InProceedings{Conti_2023_WACV,
    author    = {Conti, Andrea and Poggi, Matteo and Mattoccia, Stefano},
    title     = {Sparsity Agnostic Depth Completion},
    booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)},
    month     = {January},
    year      = {2023},
    pages     = {5871-5880}
}
}