超越时间平滑：空间能量预算稳定一步扩散编辑
Beyond Temporal Smoothing: Spatial Energy Budgets Stabilize One-Step Diffusion Editing
AI总结：
针对一步扩散编辑中的空间能量分配不当问题，提出BudEdit方法，通过将能量预算重新分配给编辑相关区域而非时间平滑，在PIE-Bench上全面超越ChordEdit，提升编辑质量与背景保持。
AI中文摘要：
一步文本引导扩散编辑效率高，但容易出现空间分配不当的更新，从而扭曲编辑对象并改变背景。现有方法通常通过对各时间步的编辑场求平均来提高稳定性。我们则识别出空间能量分配不当是一种独特且可测量的失败模式：在两次独立的噪声抽取中，残差场本质上不可重复，使得背景场无法可靠地用于直接传输，而其总能量仍为当前抽取设定了可用的幅度。BudEdit将该幅度转化为明确的预算，并将其重新分配给由残差能量和交叉注意力联合选择的编辑相关区域，控制编辑能量的使用位置，而非在时间步上求平均。由此产生的免训练、免反演编辑器将预算用于传输，并复用该预算在低噪声门控细化中缩放修正量。预算注入场精确匹配其规定的预算，并构造性地在识别出的背景支撑上消失。在PIE-Bench基准上使用SD-Turbo，BudEdit在每种方法报告的默认设置下，在所有11项评估指标上均优于ChordEdit，包括背景PSNR提升2.1 dB，DINO降低31%，LPIPS降低36%，同时改善所有五项编辑质量指标，并在比较中报告了最低的运行时间。
英文摘要：
One-step text-guided diffusion editing is efficient but prone to spatially misallocated updates that distort the edited object and alter the background. Existing methods often improve stability by averaging the editing field across timesteps. We instead identify spatial energy misallocation as a distinct and measurable failure mode: across two independent noise draws, the residual field is essentially unrepeatable, making the background field unreliable for direct transport, while its total energy still sets a usable magnitude for the draw at hand. BudEdit turns that magnitude into an explicit budget and reallocates it to edit-relevant regions selected jointly by residual energy and cross-attention, controlling where editing energy is spent rather than averaging over timesteps. The resulting training-free, inversion-free editor spends the budget on transport and reuses it to scale a correction in a lower-noise gated refinement. The budgeted injection field matches its prescribed budget exactly and vanishes on the identified background support, by construction. On PIE-Bench with SD-Turbo, BudEdit outperforms ChordEdit under each method's reported default settings on all 11 evaluated metrics, including a $2.1$\,dB gain in background PSNR, $31$\% lower DINO, and $36$\% lower LPIPS, while improving all five editing-quality metrics and reporting the lowest runtime in the comparison.
