UniSlider: Perceptually Uniform Sliders for Continuous Image Editing
arXiv cs.AI · 6 Oct 2026, 03:58 AEST
UniSlider introduces a new approach to continuous image editing using perceptually uniform sliders. It outperforms previous methods in uniformity, monotonicity, edit fidelity, and identity preservation.
Key facts
- Sliders provide an intuitive interface for continuous image editing.
- We therefore distinguish the slider from the strength, and require perceptual distance from the input to grow linearly with the slider value.
- 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.
Read aloud
UniSlider introduces a new approach to continuous image editing using perceptually uniform sliders. It outperforms previous methods in uniformity, monotonicity, edit fidelity, and identity preservation. Sliders provide an intuitive interface for continuous image editing. We therefore distinguish the slider from the strength, and require perceptual distance from the input to grow linearly with the slider value. On a new benchmark of three hundred continuous edits evaluating uniformity, monotonicity, edit fidelity, and identity preservation, UniSlider outperforms all prior methods and is preferred in a user study.
Sources in this cluster
- UniSlider: Perceptually Uniform Sliders for Continuous Image Editing
arXiv cs.AI · 6 Oct 2026, 03:58 AEST