跳到正文
HuggingFace Daily Papers(社區熱門論文)·· 2026-10-14AI 評分36

SliderEdit++:改善基於指令的圖像編輯滑桿軌跡

SliderEdit++: Improved Slider Trajectories in Instruction-Based Image Editing

AI 導讀

SliderEdit++ 透過軌跡正則化與解耦,改善基於指令的圖像編輯中滑桿控制的可靠性,令控制過程更平滑、快速。研究團隊推出 SlideBench,評估編輯進展的單調性、感知連續性及滑桿解耦;SliderEdit++ 在基準上的總分較最強基線高 18.5%。採用少步數編輯骨幹後,速度約為現有滑桿式方法的 3x 至 20x。

正文

Published on Oct 14

Authors:

,

,

,

,

,

,

Abstract

SlideBench benchmarks continuous image editing and SliderEdit++ improves slider reliability via trajectory regularization and disentanglement for smoother, faster control.

Slider-based control aims to give users continuous, fine-grained control over the intensity of individual edits in instruction-based image editing. However, existing approaches fail to deliver reliable continuous controllability: traversing a slider can produce abrupt visual jumps and non-monotonic changes, while jointly controlled sliders can interfere with one another. To systematically study these limitations, we introduce SlideBench, a comprehensive benchmark for continuous image editing spanning diverse editing categories and equipped with a unified suite of metrics quantifying monotonic progression, perceptual continuity, and inter-slider disentanglement. Building on these observations, we propose SliderEdit++, which explicitly regularizes the intermediate editing trajectory rather than supervising only its endpoints. Our method combines velocity- and semantic-space trajectory regularization with spectral control to encourage smooth, predictable slider traversal, together with a disentanglement objective that reduces interference between independently controlled edits. On SlideBench, SliderEdit++ achieves state-of-the-art performance, improving the overall score by 18.5% relative to the strongest baseline. At the same time, using a few-step editing backbone makes our method approximately 3x to 20x faster than existing slider-based approaches, enabling substantially more responsive interactive editing.

View arXiv page View PDF Add to collection

Get this paper in your agent:

hf papers read 2610.14253

Don't have the latest CLI?

curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2610.14253 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2610.14253 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2610.14253 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.

來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co