Instance Segmentation of Scene Sketches Using Natural Image Priors
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_ | 1866915274967482368 |
|---|---|
| author | Tang, Mia Vinker, Yael Yan, Chuan Zhang, Lvmin Agrawala, Maneesh |
| author_facet | Tang, Mia Vinker, Yael Yan, Chuan Zhang, Lvmin Agrawala, Maneesh |
| contents | Sketch segmentation involves grouping pixels within a sketch that belong to the same object or instance. It serves as a valuable tool for sketch editing tasks, such as moving, scaling, or removing specific components. While image segmentation models have demonstrated remarkable capabilities in recent years, sketches present unique challenges for these models due to their sparse nature and wide variation in styles. We introduce InkLayer, a method for instance segmentation of raster scene sketches. Our approach adapts state-of-the-art image segmentation and object detection models to the sketch domain by employing class-agnostic fine-tuning and refining segmentation masks using depth cues. Furthermore, our method organizes sketches into sorted layers, where occluded instances are inpainted, enabling advanced sketch editing applications. As existing datasets in this domain lack variation in sketch styles, we construct a synthetic scene sketch segmentation dataset, InkScenes, featuring sketches with diverse brush strokes and varying levels of detail. We use this dataset to demonstrate the robustness of our approach. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_09608 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Instance Segmentation of Scene Sketches Using Natural Image Priors Tang, Mia Vinker, Yael Yan, Chuan Zhang, Lvmin Agrawala, Maneesh Computer Vision and Pattern Recognition Graphics Sketch segmentation involves grouping pixels within a sketch that belong to the same object or instance. It serves as a valuable tool for sketch editing tasks, such as moving, scaling, or removing specific components. While image segmentation models have demonstrated remarkable capabilities in recent years, sketches present unique challenges for these models due to their sparse nature and wide variation in styles. We introduce InkLayer, a method for instance segmentation of raster scene sketches. Our approach adapts state-of-the-art image segmentation and object detection models to the sketch domain by employing class-agnostic fine-tuning and refining segmentation masks using depth cues. Furthermore, our method organizes sketches into sorted layers, where occluded instances are inpainted, enabling advanced sketch editing applications. As existing datasets in this domain lack variation in sketch styles, we construct a synthetic scene sketch segmentation dataset, InkScenes, featuring sketches with diverse brush strokes and varying levels of detail. We use this dataset to demonstrate the robustness of our approach. |
| title | Instance Segmentation of Scene Sketches Using Natural Image Priors |
| topic | Computer Vision and Pattern Recognition Graphics |
| url | https://arxiv.org/abs/2502.09608 |