EasyControlEdge: A Foundation-Model Fine-Tuning for Edge Detection
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918343736295424 |
|---|---|
| author | Nakamura, Hiroki Iino, Hiroto Okada, Masashi Taniguchi, Tadahiro |
| author_facet | Nakamura, Hiroki Iino, Hiroto Okada, Masashi Taniguchi, Tadahiro |
| contents | We propose EasyControlEdge, adapting an image-generation foundation model to edge detection. In real-world edge detection (e.g., floor-plan walls, satellite roads/buildings, and medical organ boundaries), crispness and data efficiency are crucial, yet producing crisp raw edge maps with limited training samples remains challenging. Although image-generation foundation models perform well on many downstream tasks, their pretrained priors for data-efficient transfer and iterative refinement for high-frequency detail preservation remain underexploited for edge detection. To enable crisp and data-efficient edge detection using these capabilities, we introduce an edge-specialized adaptation of image-generation foundation models. To better specialize the foundation model for edge detection, we incorporate an edge-oriented objective with an efficient pixel-space loss. At inference, we introduce guidance based on unconditional dynamics, enabling a single model to control the edge density through a guidance scale. Experiments on BSDS500, NYUDv2, BIPED, and CubiCasa compare against state-of-the-art methods and show consistent gains, particularly under no-post-processing crispness evaluation and with limited training data. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_16238 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | EasyControlEdge: A Foundation-Model Fine-Tuning for Edge Detection Nakamura, Hiroki Iino, Hiroto Okada, Masashi Taniguchi, Tadahiro Computer Vision and Pattern Recognition We propose EasyControlEdge, adapting an image-generation foundation model to edge detection. In real-world edge detection (e.g., floor-plan walls, satellite roads/buildings, and medical organ boundaries), crispness and data efficiency are crucial, yet producing crisp raw edge maps with limited training samples remains challenging. Although image-generation foundation models perform well on many downstream tasks, their pretrained priors for data-efficient transfer and iterative refinement for high-frequency detail preservation remain underexploited for edge detection. To enable crisp and data-efficient edge detection using these capabilities, we introduce an edge-specialized adaptation of image-generation foundation models. To better specialize the foundation model for edge detection, we incorporate an edge-oriented objective with an efficient pixel-space loss. At inference, we introduce guidance based on unconditional dynamics, enabling a single model to control the edge density through a guidance scale. Experiments on BSDS500, NYUDv2, BIPED, and CubiCasa compare against state-of-the-art methods and show consistent gains, particularly under no-post-processing crispness evaluation and with limited training data. |
| title | EasyControlEdge: A Foundation-Model Fine-Tuning for Edge Detection |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2602.16238 |