EasyControlEdge: A Foundation-Model Fine-Tuning for Edge Detection
This work addresses edge detection challenges for domains such as architecture and healthcare, but it is incremental as it builds on existing foundation models.
The paper tackled the problem of achieving crisp and data-efficient edge detection in real-world applications like floor plans and medical images by adapting an image-generation foundation model, resulting in consistent gains on benchmarks like BSDS500 and NYUDv2, especially in no-post-processing crispness and with limited training data.
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.