Lightweight Optimal-Transport Harmonization on Edge Devices
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917084658663424 |
|---|---|
| author | Larchenko, Maria Guskov, Dmitry Lobashev, Alexander Derevyanko, Georgy |
| author_facet | Larchenko, Maria Guskov, Dmitry Lobashev, Alexander Derevyanko, Georgy |
| contents | Color harmonization adjusts the colors of an inserted object so that it perceptually matches the surrounding image, resulting in a seamless composite. The harmonization problem naturally arises in augmented reality (AR), yet harmonization algorithms are not currently integrated into AR pipelines because real-time solutions are scarce. In this work, we address color harmonization for AR by proposing a lightweight approach that supports on-device inference. For this, we leverage classical optimal transport theory by training a compact encoder to predict the Monge-Kantorovich transport map. We benchmark our MKL-Harmonizer algorithm against state-of-the-art methods and demonstrate that for real composite AR images our method achieves the best aggregated score. We release our dedicated AR dataset of composite images with pixel-accurate masks and data-gathering toolkit to support further data acquisition by researchers. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_12785 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Lightweight Optimal-Transport Harmonization on Edge Devices Larchenko, Maria Guskov, Dmitry Lobashev, Alexander Derevyanko, Georgy Computer Vision and Pattern Recognition Artificial Intelligence Graphics Color harmonization adjusts the colors of an inserted object so that it perceptually matches the surrounding image, resulting in a seamless composite. The harmonization problem naturally arises in augmented reality (AR), yet harmonization algorithms are not currently integrated into AR pipelines because real-time solutions are scarce. In this work, we address color harmonization for AR by proposing a lightweight approach that supports on-device inference. For this, we leverage classical optimal transport theory by training a compact encoder to predict the Monge-Kantorovich transport map. We benchmark our MKL-Harmonizer algorithm against state-of-the-art methods and demonstrate that for real composite AR images our method achieves the best aggregated score. We release our dedicated AR dataset of composite images with pixel-accurate masks and data-gathering toolkit to support further data acquisition by researchers. |
| title | Lightweight Optimal-Transport Harmonization on Edge Devices |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Graphics |
| url | https://arxiv.org/abs/2511.12785 |