BIDCD -- Bosch Industrial Depth Completion Dataset

TL;DR

This paper introduces BIDCD, a new industrial RGBD dataset for depth completion, benchmarks a state-of-the-art model on it, and explores synthetic-to-real domain adaptation using GANs with shape-preserving loss.

Contribution

The paper presents BIDCD, a novel industrial RGBD dataset, and demonstrates its use for training depth completion models and domain adaptation with synthetic data.

Findings

State-of-the-art depth completion model achieves initial benchmark results.

GAN-based synthetic-to-real domain adaptation improves depth data realism.

Auxiliary loss helps preserve geometric shape in generated images.

Abstract

We introduce BIDCD -- the Bosch Industrial Depth Completion Dataset. BIDCD is a new RGBD dataset of metallic industrial objects, collected with a depth camera mounted on a robotic manipulator. The main purpose of this dataset is to facilitate the training of domain-specific depth completion models, to be used in logistics and manufacturing tasks. We trained a State-of-the-Art depth completion model on this dataset, and report the results, setting an initial benchmark. Further, we propose to use this dataset for learning synthetic-to-depth-camera domain adaptation. Modifying synthetic RGBD data to mimic characteristics of real-world depth acquisition could potentially enhance training on synthetic data. For this end, we trained a Generative Adversarial Network (GAN) on a synthetic industrial dataset and our real-world data. Finally, to address geometric distortions in the generated images, we introduce an auxiliary loss that promotes preservation of the original shape. The BIDCD data is publicly available at https://zenodo.org/communities/bidcd.