FlowDepth: Decoupling Optical Flow for Self-Supervised Monocular Depth Estimation
This work addresses accuracy issues in depth estimation for autonomous driving and robotics, representing an incremental improvement over existing methods.
The paper tackled the mismatch problem from moving objects and unfair photometric errors in self-supervised monocular depth estimation by proposing FlowDepth with a Dynamic Motion Flow Module and Depth-Cue-Aware Blur, achieving state-of-the-art results on KITTI and Cityscapes datasets.
Self-supervised multi-frame methods have currently achieved promising results in depth estimation. However, these methods often suffer from mismatch problems due to the moving objects, which break the static assumption. Additionally, unfairness can occur when calculating photometric errors in high-freq or low-texture regions of the images. To address these issues, existing approaches use additional semantic priori black-box networks to separate moving objects and improve the model only at the loss level. Therefore, we propose FlowDepth, where a Dynamic Motion Flow Module (DMFM) decouples the optical flow by a mechanism-based approach and warps the dynamic regions thus solving the mismatch problem. For the unfairness of photometric errors caused by high-freq and low-texture regions, we use Depth-Cue-Aware Blur (DCABlur) and Cost-Volume sparsity loss respectively at the input and the loss level to solve the problem. Experimental results on the KITTI and Cityscapes datasets show that our method outperforms the state-of-the-art methods.