POLARIS：扩散模型中基于投影正交最小二乘的鲁棒自适应反演算法

摘要

基于扩散模型的反演去噪范式在多样化图像编辑与修复任务中表现卓越。我们重新审视其机制，揭示了导致重建质量下降的关键被忽视因素——近似噪声误差。该误差源于用第t-1步的预测结果近似替代第t步噪声，导致反演过程中产生严重的误差累积。我们提出投影正交最小二乘鲁棒自适应反演框架（POLARIS），将反演问题从误差补偿重构为误差溯源问题。与通过优化嵌入向量或潜代码来抵消累积偏差的方法不同，POLARIS将引导尺度ω视为步进变量，并推导出数学严密的公式以逐步最小化反演误差。值得注意的是，POLARIS仅需单行代码即可提升反演潜空间质量。该方法以可忽略的性能开销显著抑制噪声近似误差，持续提升下游任务的准确性。

English

The Inversion-Denoising Paradigm, which is based on diffusion models, excels in diverse image editing and restoration tasks. We revisit its mechanism and reveal a critical, overlooked factor in reconstruction degradation: the approximate noise error. This error stems from approximating the noise at step t with the prediction at step t-1, resulting in severe error accumulation throughout the inversion process. We introduce Projection-Orthogonal Least Squares for Robust and Adaptive Inversion (POLARIS), which reformulates inversion from an error-compensation problem into an error-origin problem. Rather than optimizing embeddings or latent codes to offset accumulated drift, POLARIS treats the guidance scale ω as a step-wise variable and derives a mathematically grounded formula to minimize inversion error at each step. Remarkably, POLARIS improves inversion latent quality with just one line of code. With negligible performance overhead, it substantially mitigates noise approximation errors and consistently improves the accuracy of downstream tasks.

POLARIS：扩散模型中基于投影正交最小二乘的鲁棒自适应反演算法

POLARIS: Projection-Orthogonal Least Squares for Robust and Adaptive Inversion in Diffusion Models

摘要

Support