基于联合潜扩散的单图反射分离
Reflection Separation from a Single Image via Joint Latent Diffusion
把预训练扩散模型的生成先验显式微调用于单图反射分离，并用跨层自注意力与分离式采样在扩散过程中解耦透射层与反射层；对做图像复原的人，这是一套可直接迁移到其他「多成分叠加图像分解」任务的扩散采样与潜变量优化框架。
原文依据 simultaneously generates transmission and reflection layers through a unified diffusion model, incorporating a novel cross-layer self-attention mechanism
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论在眩光或弱反射等极端条件下，单图反射分离极具挑战性。现有方法在眩光或弱反射场景中往往难以同时恢复两个图层，原因在于信息不足。本文提出一个针对该任务显式微调的扩散模型，利用生成式扩散先验实现稳健的分离。我们的方法通过一个统一的扩散模型同时生成透射层与反射层，并引入一种新颖的跨层自注意力机制以更好地实现特征解耦。我们进一步提出分离式采样策略，在扩散过程中迭代降低两层之间的干扰，并采用带可学习合成函数的潜变量优化步骤，以在复杂的真实场景中取得更优结果。大量实验表明，我们的方法在多个真实世界基准上超越了最优方法。项目主页：https://brian90709.github.io/diff-reflection-separation/
英文原文摘要 1016 字符
Single-image reflection separation is highly challenging under extreme conditions like glare or weak reflections. Existing methods often struggle to recover both layers in glare or weak-reflection scenarios because of insufficient information. This paper presents a diffusion model explicitly fine-tuned for this task, leveraging generative diffusion priors for robust separation. Our method simultaneously generates transmission and reflection layers through a unified diffusion model, incorporating a novel cross-layer self-attention mechanism for better feature disentanglement. We further introduce a disjoint sampling strategy to iteratively reduce interference between the layers during diffusion and a latent optimization step with a learned composition function for improved results in complex real-world scenarios. Extensive experiments demonstrate that our approach surpasses state-of-the-art methods on multiple real-world benchmarks. Project page: https://brian90709.github.io/diff-reflection-separation/