用单对闪光/无闪光图像分离玻璃反射，效果优于现有方法。
Flash-Split: 2D Reflection Removal with Flash Cues and Latent Diffusion Separation
- 通过双分支扩散模型在潜在空间分离反射与透射成分
- 在真实场景中实现领先性能，显著超越基线方法
- 适合需要高质量图像去反射的应用场景
透明表面（如玻璃）会产生复杂反射，遮挡图像并影响下游计算机视觉任务。本文提出 Flash-Split，一种基于单对（可能错位）闪光/无闪光图像的鲁棒反射分离框架。核心思想是在潜在空间利用闪光提示进行反射分离。该框架包含两阶段：第一阶段通过条件于编码后的闪光/无闪光潜在对的双分支扩散模型，分离反射与透射潜在表示，有效缓解闪光/无闪光错位问题；第二阶段通过跨潜在解码过程，对分离后的潜在表示恢复高分辨率、忠实细节，条件于分离前的原始图像。在挑战性真实场景上的验证表明，Flash-Split达到当前最优反射分离性能，显著优于基线方法。
原文摘要 · Abstract (English)
Transparent surfaces, such as glass, create complex reflections that obscure images and challenge downstream computer vision applications. We introduce Flash-Split, a robust framework for separating transmitted and reflected light using a single (potentially misaligned) pair of flash/no-flash images. Our core idea is to perform latent-space reflection separation while leveraging the flash cues. Specifically, Flash-Split consists of two stages. Stage 1 separates apart the reflection latent and transmission latent via a dual-branch diffusion model conditioned on an encoded flash/no-flash latent pair, effectively mitigating the flash/no-flash misalignment issue. Stage 2 restores high-resolution, faithful details to the separated latents, via a cross-latent decoding process conditioned on the original images before separation. By validating Flash-Split on challenging real-world scenes, we demonstrate state-of-the-art reflection separation performance and significantly outperform the baseline methods.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。