Completion as Enhancement: A Degradation-Aware Selective Image Guided Network for Depth Completion

TL;DR

This paper presents SigNet, a degradation-aware framework that transforms depth completion into depth enhancement, utilizing non-CNN densification and RGB high-frequency components for improved depth accuracy.

Contribution

SigNet introduces a novel degradation-aware approach that redefines depth completion as enhancement, leveraging self-supervised degradation modeling and RGB-D fusion for superior performance.

Findings

Achieves state-of-the-art results on multiple datasets.

Effectively integrates RGB high-frequency information.

Outperforms traditional CNN-based depth completion methods.

Abstract

In this paper, we introduce the Selective Image Guided Network (SigNet), a novel degradation-aware framework that transforms depth completion into depth enhancement for the first time. Moving beyond direct completion using convolutional neural networks (CNNs), SigNet initially densifies sparse depth data through non-CNN densification tools to obtain coarse yet dense depth. This approach eliminates the mismatch and ambiguity caused by direct convolution over irregularly sampled sparse data. Subsequently, SigNet redefines completion as enhancement, establishing a self-supervised degradation bridge between the coarse depth and the targeted dense depth for effective RGB-D fusion. To achieve this, SigNet leverages the implicit degradation to adaptively select high-frequency components (e.g., edges) of RGB data to compensate for the coarse depth. This degradation is further integrated into a multi-modal conditional Mamba, dynamically generating the state parameters to enable efficient global high-frequency information interaction. We conduct extensive experiments on the NYUv2, DIML, SUN RGBD, and TOFDC datasets, demonstrating the state-of-the-art (SOTA) performance of SigNet.