SIRR-LMM: Single-image Reflection Removal via Large Multimodal Model
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866908815265366016 |
|---|---|
| author | Guo, Yu Lao, Zhiqiang Song, Xiyun Zhou, Yubin Yu, Heather |
| author_facet | Guo, Yu Lao, Zhiqiang Song, Xiyun Zhou, Yubin Yu, Heather |
| contents | Glass surfaces create complex interactions of reflected and transmitted light, making single-image reflection removal (SIRR) challenging. Existing datasets suffer from limited physical realism in synthetic data or insufficient scale in real captures. We introduce a synthetic dataset generation framework that path-traces 3D glass models over real background imagery to create physically accurate reflection scenarios with varied glass properties, camera settings, and post-processing effects. To leverage the capabilities of Large Multimodal Model (LMM), we concatenate the image layers into a single composite input, apply joint captioning, and fine-tune the model using task-specific LoRA rather than full-parameter training. This enables our approach to achieve improved reflection removal and separation performance compared to state-of-the-art methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_07209 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | SIRR-LMM: Single-image Reflection Removal via Large Multimodal Model Guo, Yu Lao, Zhiqiang Song, Xiyun Zhou, Yubin Yu, Heather Computer Vision and Pattern Recognition Artificial Intelligence Graphics Glass surfaces create complex interactions of reflected and transmitted light, making single-image reflection removal (SIRR) challenging. Existing datasets suffer from limited physical realism in synthetic data or insufficient scale in real captures. We introduce a synthetic dataset generation framework that path-traces 3D glass models over real background imagery to create physically accurate reflection scenarios with varied glass properties, camera settings, and post-processing effects. To leverage the capabilities of Large Multimodal Model (LMM), we concatenate the image layers into a single composite input, apply joint captioning, and fine-tune the model using task-specific LoRA rather than full-parameter training. This enables our approach to achieve improved reflection removal and separation performance compared to state-of-the-art methods. |
| title | SIRR-LMM: Single-image Reflection Removal via Large Multimodal Model |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Graphics |
| url | https://arxiv.org/abs/2601.07209 |