IGAF: Incremental Guided Attention Fusion for Depth Super-Resolution
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912176161161216 |
|---|---|
| author | Tragakis, Athanasios Kaul, Chaitanya Mitchell, Kevin J. Dai, Hang Murray-Smith, Roderick Faccio, Daniele |
| author_facet | Tragakis, Athanasios Kaul, Chaitanya Mitchell, Kevin J. Dai, Hang Murray-Smith, Roderick Faccio, Daniele |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_01723 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | IGAF: Incremental Guided Attention Fusion for Depth Super-Resolution Tragakis, Athanasios Kaul, Chaitanya Mitchell, Kevin J. Dai, Hang Murray-Smith, Roderick Faccio, Daniele Computer Vision and Pattern Recognition 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. |
| title | IGAF: Incremental Guided Attention Fusion for Depth Super-Resolution |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2501.01723 |