用单步推理实现高效图像分解，适合实时应用。
FlowIID: Single-Step Intrinsic Image Decomposition via Latent Flow Matching
- 基于潜在空间流匹配构建轻量架构
- 单次推理完成反照率与阴影分离，参数少性能优
- 适合嵌入式或实时视觉系统部署
固有图像分解（IID）将图像分解为反照率和阴影成分，是光照重渲染与材质编辑等实际应用的核心步骤。现有模型虽效果良好，但参数量大，难以在真实场景中与其他模型集成。为此，本文提出基于流匹配的解决方案——FlowIID，其结合了受变分自编码器引导的潜在空间与流匹配模块，实现了反照率与阴影的稳定分解。该模型不仅参数高效，且可在单次前向传播中完成推理。尽管结构紧凑，其在多个基准测试中仍达到甚至超越现有方法的性能，适用于资源受限及实时视觉任务的部署。
原文摘要 · Abstract (English)
Intrinsic Image Decomposition (IID) separates an image into albedo and shading components. It is a core step in many real-world applications, such as relighting and material editing. Existing IID models achieve good results, but often use a large number of parameters. This makes them costly to combine with other models in real-world settings. To address this problem, we propose a flow matching-based solution. For this, we design a novel architecture, FlowIID, based on latent flow matching. FlowIID combines a VAE-guided latent space with a flow matching module, enabling a stable decomposition of albedo and shading. FlowIID is not only parameter-efficient, but also produces results in a single inference step. Despite its compact design, FlowIID delivers competitive and superior results compared to existing models across various benchmarks. This makes it well-suited for deployment in resource-constrained and real-time vision applications.
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。