Self-Guided Instance-Aware Network for Depth Completion and Enhancement

TL;DR

This paper introduces a self-guided, instance-aware neural network for depth completion that enhances boundary accuracy and structure preservation by leveraging instance features, geometric context, and synthetic training data.

Contribution

The proposed SG-IANet uniquely combines self-guided instance features, geometric context, and synthetic data training to improve depth completion accuracy and structure preservation.

Findings

Outperforms previous depth completion methods on synthetic and real datasets.

Effectively preserves object boundaries and structures in depth maps.

Demonstrates strong generalization with synthetic training data.

Abstract

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.