Unsupervised Monocular Depth Prediction for Indoor Continuous Video Streams
This work addresses the scarcity of depth prediction methods for indoor environments, which is an incremental improvement for applications like robotics or augmented reality.
The paper tackles unsupervised monocular depth prediction for indoor video streams by evaluating existing methods and improving architecture design, resulting in outperforming previous state-of-the-art approaches on TUM RGB-D and self-collected datasets.
This paper studies unsupervised monocular depth prediction problem. Most of existing unsupervised depth prediction algorithms are developed for outdoor scenarios, while the depth prediction work in the indoor environment is still very scarce to our knowledge. Therefore, this work focuses on narrowing the gap by firstly evaluating existing approaches in the indoor environments and then improving the state-of-the-art design of architecture. Unlike typical outdoor training dataset, such as KITTI with motion constraints, data for indoor environment contains more arbitrary camera movement and short baseline between two consecutive images, which deteriorates the network training for the pose estimation. To address this issue, we propose two methods: Firstly, we propose a novel reconstruction loss function to constraint pose estimation, resulting in accuracy improvement of the predicted disparity map; secondly, we use an ensemble learning with a flipping strategy along with a median filter, directly taking operation on the output disparity map. We evaluate our approaches on the TUM RGB-D and self-collected datasets. The results have shown that both approaches outperform the previous state-of-the-art unsupervised learning approaches.