Self-Supervised Learning for Transparent Object Depth Completion Using Depth from Non-Transparent Objects
This work addresses the costly annotation problem in depth perception for transparent objects, offering an incremental improvement for computer vision applications like robotics.
The paper tackles the challenge of depth completion for transparent objects by proposing a self-supervised method that simulates depth deficits in non-transparent regions, achieving performance comparable to supervised approaches and improving model performance with limited training samples.
The perception of transparent objects is one of the well-known challenges in computer vision. Conventional depth sensors have difficulty in sensing the depth of transparent objects due to refraction and reflection of light. Previous research has typically train a neural network to complete the depth acquired by the sensor, and this method can quickly and accurately acquire accurate depth maps of transparent objects. However, previous training relies on a large amount of annotation data for supervision, and the labeling of depth maps is costly. To tackle this challenge, we propose a new self-supervised method for training depth completion networks. Our method simulates the depth deficits of transparent objects within non-transparent regions and utilizes the original depth map as ground truth for supervision. Experiments demonstrate that our method achieves performance comparable to supervised approach, and pre-training with our method can improve the model performance when the training samples are small.