实测滑块：从可微图像测量中学习连续控制
Measured Sliders: Learning Continuous Controls from Differentiable Image Measurements
浏览论文内容
中文总结 AI 辅助
该研究提出Measured Sliders框架，通过可微图像测量定义连续控制，经可观测性测试、测量引导训练及解码校准，在SDXL等模型上实现有序可组合的生成控制，提升了控制的选择性与方向保留能力。
中文摘要 AI 辅助
连续滑块仅当系数变化能产生可预测的图像变化时才有用，但大多数扩散滑块的轴来自文本或学习到的表示，其尺度与可观测的图像属性脱节。因此，我们无法预先判断哪些属性可学习、直接比较控制强度，或预测多个控制组合时的干扰。我们提出Measured Sliders，一个通过闭式可微图像测量定义连续控制的框架，用公共测量空间统一整个流程。训练前，可观测性测试识别可用的监督信号；训练期间，测量引导的目标函数学习目标变化同时抑制非目标变化；训练后，解码校准将控制表示为可比较的已实现图像变化单位。单个检查点中存储多个LoRA分支，无需联合激活训练即可组合。在SDXL和FLUX.1-dev上，生成的控制有序、具选择性且可组合：553个提示中，光照方向达到rho=0.995，98.9%的单调扫描；含5个属性的检查点平均选择性为2.59，最强基线仅为1.50；96.7%的二元组合和86.1%的三元组合保留所有请求方向；可观测性测试还能区分后续成功的测量与失败候选。总体而言，图像空间测量为学习、诊断、校准和组合连续生成控制提供了共同基础。
英文摘要
Continuous sliders are useful only when coefficient changes produce predictable image changes. Yet most diffusion sliders derive their axes from text or learned representations, leaving their scales disconnected from observable image properties. Consequently, we cannot tell in advance which attributes are learnable, compare control strengths directly, or anticipate interference when multiple controls are combined. We propose Measured Sliders, a framework that defines continuous controls through closed-form differentiable image measurements. A common measurement space unifies the pipeline. Before training, an observability test identifies usable supervision. During training, a measurement-guided objective learns target movement while suppressing non-target changes. After training, decoded calibration expresses controls in comparable units of realized image change. Multiple LoRA branches are stored in one checkpoint and composed without training on joint activations. Across SDXL and FLUX.1-dev, the resulting controls are ordered, selective, and composable. On 553 prompts, lighting direction reaches rho = 0.995 and 98.9% monotone sweeps. A five-attribute checkpoint achieves average selectivity 2.59, compared with 1.50 for the strongest baseline, and preserves every requested direction in 96.7% of pair and 86.1% of triple compositions. The observability test also separates every subsequently successful measurement from the failed candidate. Overall, image-space measurement provides a common basis for learning, diagnosing, calibrating, and composing continuous generative controls.
发表机构
- School of Computer Science, The University of Sydney（悉尼大学计算机科学学院）
机构由 AI 辅助整理，请以论文原文为准。
