Abstract
Latent Diffusion Models (LDMs) have markedly advanced the quality of image inpainting and local editing. However, the inherent latent compression often introduces pixel-level inconsistencies, such as chromatic shifts, texture mismatches, and visible seams along editing boundaries. Existing remedies, including background-conditioned latent decoding and pixel-space harmonization, usually fail to fully eliminate these artifacts in practice and do not generalize well across different latent representations or tasks. We introduce PixPerfect, a pixel-level refinement framework that delivers seamless, high-fidelity local edits across diverse LDM architectures and tasks. PixPerfect leverages (i) a differentiable discriminative pixel space that amplifies and suppresses subtle color and texture discrepancies, (ii) a comprehensive artifact simulation pipeline that exposes the refiner to realistic local editing artifacts during training, and (iii) a direct pixel-space refinement scheme that ensures broad applicability across diverse latent representations and tasks. Extensive experiments on inpainting, object removal, and insertion benchmarks demonstrate that PixPerfect substantially enhances perceptual fidelity and downstream editing performance, establishing a new standard for robust and high-fidelity localized image editing.
Abstract (translated)
潜扩散模型（LDMs）显著提高了图像修复和局部编辑的质量。然而，其固有的潜在压缩常常引入像素级别的不一致性，例如色彩偏移、纹理不匹配以及编辑边界处的可见接缝等问题。现有的补救措施，包括背景条件下的潜在解码和像素空间调和，在实际应用中往往无法完全消除这些伪影，并且在不同的潜表示或任务之间泛化效果不佳。我们引入了PixPerfect，这是一种像素级别的细化框架，它能够提供无缝、高质量的局部编辑效果，适用于各种LDM架构和任务。 PixPerfect利用了以下三个关键要素： 1. **可微分判别像素空间**：放大并抑制细微的颜色和纹理差异。 2. **全面的伪影仿真管道**：在训练过程中让细化器接触现实中的本地编辑伪影。 3. **直接的像素空间细化方案**：确保广泛的适用性，适用于各种潜在表示和任务。 在图像修复、对象移除和插入基准上的大量实验表明，PixPerfect显著提升了感知保真度和下游编辑性能，为鲁棒且高质量的局部图像编辑树立了新标准。
URL
https://arxiv.org/abs/2512.03247
