الملخص
Sliders provide an intuitive interface for continuous image editing. In current generative approaches, however, the slider is simply a rescaling of the method's strength parameter, such as an adapter coefficient, a prompt weight, or an interpolation factor. This strength relates poorly to perceptual change. The image can partially revert as the slider moves, long stretches of the range produce no visible difference, and short intervals transform the image abruptly. Remapping the strength could fix this uneven pace, but only if the trajectory is monotone, which current methods do not enforce. We therefore distinguish the slider from the strength, and require perceptual distance from the input to grow linearly with the slider value. We introduce UniSlider, a lightweight LoRA trained on a few-step editing backbone so that its strength approximates this ideal slider. Few-step sampling lets us impose this objective in pixel space without intermediate ground truth, and the backbone's output is preserved at full strength. However, a low-rank adapter cannot make the strength fully uniform. Our slider is thus an inference-time remapping of the strength, obtained by adaptive sampling. Since training optmizes to make the trajectory monotone, this remapping closes the remaining gap without extra training or parameters. On a new benchmark of 300 continuous edits evaluating uniformity, monotonicity, edit fidelity, and identity preservation, UniSlider outperforms all prior methods and is preferred in a user study.
الكلمات المفتاحية
بيانات النشر
- المجلة
- غير متاح
- وصول مفتوح
- وصول مفتوح أخضر
اقتبس هذه المقالة
APA 7
Serrano-Lozano, D., Ceylan, D., Hold-Geoffroy, Y., Georgiev, I., Vazquez-Corral, J., & Frühstück, A. (2026). UniSlider: Perceptually Uniform Sliders for Continuous Image Editing. https://omanscience.com/ar/articles/unislider-perceptually-uniform-sliders-for-continuous-image-editing
MLA 9
Serrano-Lozano, David, et al. "UniSlider: Perceptually Uniform Sliders for Continuous Image Editing." https://omanscience.com/ar/articles/unislider-perceptually-uniform-sliders-for-continuous-image-editing.
شيكاغو (المؤلف–التاريخ)
Serrano-Lozano, David, Duygu Ceylan, Yannick Hold-Geoffroy, Iliyan Georgiev, Javier Vazquez-Corral, and Anna Frühstück. 2026. "UniSlider: Perceptually Uniform Sliders for Continuous Image Editing." https://omanscience.com/ar/articles/unislider-perceptually-uniform-sliders-for-continuous-image-editing.
هارفارد
Serrano-Lozano, D., Ceylan, D., Hold-Geoffroy, Y., Georgiev, I., Vazquez-Corral, J. and Frühstück, A. (2026) 'UniSlider: Perceptually Uniform Sliders for Continuous Image Editing', Available at: https://omanscience.com/ar/articles/unislider-perceptually-uniform-sliders-for-continuous-image-editing.
فانكوفر
Serrano-Lozano D, Ceylan D, Hold-Geoffroy Y, Georgiev I, Vazquez-Corral J, Frühstück A. UniSlider: Perceptually Uniform Sliders for Continuous Image Editing. https://omanscience.com/ar/articles/unislider-perceptually-uniform-sliders-for-continuous-image-editing
IEEE
D. Serrano-Lozano, D. Ceylan, Y. Hold-Geoffroy, I. Georgiev, J. Vazquez-Corral, and A. Frühstück, "UniSlider: Perceptually Uniform Sliders for Continuous Image Editing," https://omanscience.com/ar/articles/unislider-perceptually-uniform-sliders-for-continuous-image-editing.