Multi-Object Self-Supervised Depth Denoising
This work addresses depth reconstruction issues for precise tracking in robotic manipulation, but it is incremental as it builds on prior research by Shabanov et al. (2021).
The paper tackles the problem of noisy depth maps from low-quality cameras in robotic manipulation by proposing a self-supervised multi-object depth denoising pipeline that uses higher-quality sensor data as supervisory signals, resulting in a computationally efficient method for creating clean labeled datasets to train denoising neural networks.
Depth cameras are frequently used in robotic manipulation, e.g. for visual servoing. The quality of small and compact depth cameras is though often not sufficient for depth reconstruction, which is required for precise tracking in and perception of the robot's working space. Based on the work of Shabanov et al. (2021), in this work, we present a self-supervised multi-object depth denoising pipeline, that uses depth maps of higher-quality sensors as close-to-ground-truth supervisory signals to denoise depth maps coming from a lower-quality sensor. We display a computationally efficient way to align sets of two frame pairs in space and retrieve a frame-based multi-object mask, in order to receive a clean labeled dataset to train a denoising neural network on. The implementation of our presented work can be found at https://github.com/alr-internship/self-supervised-depth-denoising.