IGAF: Incremental Guided Attention Fusion for Depth Super-Resolution
This work addresses the need for accurate depth estimation in fields such as robotics and medical imaging by improving depth map resolution, though it appears incremental as it builds on existing guided fusion methods.
The paper tackles the problem of enhancing low-resolution depth maps to high-resolution ones using guided depth super-resolution, achieving state-of-the-art results on benchmark datasets like NYU v2 for upsampling factors up to 16x and outperforming baselines in zero-shot settings.
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.