Self-Guided Instance-Aware Network for Depth Completion and Enhancement
This addresses depth completion for applications like robotics or autonomous driving, but it is incremental as it builds on existing methods with specific enhancements.
The paper tackles the problem of depth completion, where sparse depth measurements are used to infer dense depth images, by proposing a self-guided instance-aware network (SG-IANet) that improves edge clarity and structure consistency, outperforming previous methods in experiments on synthetic and real-world datasets.
Depth completion aims at inferring a dense depth image from sparse depth measurement since glossy, transparent or distant surface cannot be scanned properly by the sensor. Most of existing methods directly interpolate the missing depth measurements based on pixel-wise image content and the corresponding neighboring depth values. Consequently, this leads to blurred boundaries or inaccurate structure of object. To address these problems, we propose a novel self-guided instance-aware network (SG-IANet) that: (1) utilize self-guided mechanism to extract instance-level features that is needed for depth restoration, (2) exploit the geometric and context information into network learning to conform to the underlying constraints for edge clarity and structure consistency, (3) regularize the depth estimation and mitigate the impact of noise by instance-aware learning, and (4) train with synthetic data only by domain randomization to bridge the reality gap. Extensive experiments on synthetic and real world dataset demonstrate that our proposed method outperforms previous works. Further ablation studies give more insights into the proposed method and demonstrate the generalization capability of our model.