矫正潜空间以实现生成式单图像反射去除
Rectifying Latent Space for Generative Single-Image Reflection Removal
将编辑用途的潜扩散模型改造为图像复原工具，核心思路是通过反射等变VAE对齐潜空间与反射形成的线性物理过程，并用可学习任务特定文本嵌入和深度引导早分支采样提升生成质量，为利用生成模型解决高度病态逆问题提供了可复用的潜空间结构化方法。
原文依据 a reflection-equivariant VAE that aligns the latent space with the linear physics of reflection formation
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论单图像反射去除是一个高度病态的问题，现有方法难以推理受损区域的组成，导致其在真实场景中恢复和泛化失败。本工作重新利用一个编辑用途的潜扩散模型，使其能够有效感知和处理高度模糊的分层图像输入，并产生高质量输出。我们认为这种转换的挑战源于一个关键但被忽视的问题，即语义编码器的潜空间缺乏将合成图像解释为其组成层线性叠加的固有结构。我们的方法建立在三个协同组件之上，包括一个反射等变变分自编码器，使潜空间与反射形成的线性物理过程对齐；一个可学习的任务特定文本嵌入，用于精确引导并绕过模糊语言；以及一个深度引导的早分支采样策略，利用生成随机性以获得有希望的结果。大量实验表明，我们的模型在多个基准上达到新的SOTA性能，并对具有挑战性的真实世界案例具有良好的泛化能力。
英文原文摘要 1160 字符
Single-image reflection removal is a highly ill-posed problem, where existing methods struggle to reason about the composition of corrupted regions, causing them to fail at recovery and generalization in the wild. This work reframes an editing-purpose latent diffusion model to effectively perceive and process highly ambiguous, layered image inputs, yielding high-quality outputs. We argue that the challenge of this conversion stems from a critical yet overlooked issue, i.e., the latent space of semantic encoders lacks the inherent structure to interpret a composite image as a linear superposition of its constituent layers. Our approach is built on three synergistic components, including a reflection-equivariant VAE that aligns the latent space with the linear physics of reflection formation, a learnable task-specific text embedding for precise guidance that bypasses ambiguous language, and a depth-guided early-branching sampling strategy to harness generative stochasticity for promising results. Extensive experiments reveal that our model achieves new SOTA performance on multiple benchmarks and generalizes well to challenging real-world cases.