Self-Supervised Depth Completion for Active Stereo

by   Frederik Warburg, et al.

Active stereo systems are widely used in the robotics industry due to their low cost and high quality depth maps. These depth sensors, however, suffer from stereo artefacts and do not provide dense depth estimates. In this work, we present the first self-supervised depth completion method for active stereo systems that predicts accurate dense depth maps. Our system leverages a feature-based visual inertial SLAM system to produce motion estimates and accurate (but sparse) 3D landmarks. The 3D landmarks are used both as model input and as supervision during training. The motion estimates are used in our novel reconstruction loss that relies on a combination of passive and active stereo frames, resulting in significant improvements in textureless areas that are common in indoor environments. Due to the non-existence of publicly available active stereo datasets, we release a real dataset together with additional information for a publicly available synthetic dataset needed for active depth completion and prediction. Through rigorous evaluations we show that our method outperforms state of the art on both datasets. Additionally we show how our method obtains more complete, and therefore safer, 3D maps when used in a robotic platform


page 1

page 4

page 5

page 6

page 7

page 8

page 12

page 13


Fusion of stereo and still monocular depth estimates in a self-supervised learning context

We study how autonomous robots can learn by themselves to improve their ...

Self-Supervised Monocular Depth Hints

Monocular depth estimators can be trained with various forms of self-sup...

LiStereo: Generate Dense Depth Maps from LIDAR and Stereo Imagery

An accurate depth map of the environment is critical to the safe operati...

A Learned Stereo Depth System for Robotic Manipulation in Homes

We present a passive stereo depth system that produces dense and accurat...

SparseFormer: Attention-based Depth Completion Network

Most pipelines for Augmented and Virtual Reality estimate the ego-motion...

ActiveZero: Mixed Domain Learning for Active Stereovision with Zero Annotation

Traditional depth sensors generate accurate real world depth estimates t...

Multimodal Data Fusion for Power-On-and-GoRobotic Systems in Retail

Robotic systems for retail have gained a lot of attention due to the lab...

Please sign up or login with your details

Forgot password? Click here to reset