IGAF: Incremental Guided Attention Fusion for Depth Super-Resolution

TL;DR

This paper introduces IGAF, a novel sensor fusion method that uses incremental guided attention to enhance low-resolution depth maps with high-resolution RGB images, achieving state-of-the-art super-resolution results.

Contribution

The paper presents the Incremental Guided Attention Fusion (IGAF) module, a new approach for effectively fusing RGB and depth features for high-quality depth super-resolution.

Findings

Achieves state-of-the-art results on NYU v2 dataset for multiple upsampling factors.

Outperforms baselines in zero-shot settings on Middlebury, Lu, and RGB-D-D datasets.

Provides a robust and effective depth super-resolution model.

Abstract

Accurate depth estimation is crucial for many fields, including robotics, navigation, and medical imaging. However, conventional depth sensors often produce low-resolution (LR) depth maps, making detailed scene perception challenging. To address this, enhancing LR depth maps to high-resolution (HR) ones has become essential, guided by HR-structured inputs like RGB or grayscale images. We propose a novel sensor fusion methodology for guided depth super-resolution (GDSR), a technique that combines LR depth maps with HR images to estimate detailed HR depth maps. Our key contribution is the Incremental guided attention fusion (IGAF) module, which effectively learns to fuse features from RGB images and LR depth maps, producing accurate HR depth maps. Using IGAF, we build a robust super-resolution model and evaluate it on multiple benchmark datasets. Our model achieves state-of-the-art results compared to all baseline models on the NYU v2 dataset for $\times 4$, $\times 8$, and $\times 16$ upsampling. It also outperforms all baselines in a zero-shot setting on the Middlebury, Lu, and RGB-D-D datasets. Code, environments, and models are available on GitHub.