深入探究非对称信息动力学以实现高保真虚拟试穿

中文摘要 AI 辅助

虚拟试穿（VTON）需要精确的像素级保真度，然而主流的扩散变换器（DiTs）常常遭受纹理退化和结构漂移的问题。我们识别出标准联合注意力机制中的对称交互是这些失败的一个根源。尽管这种交互在通用编辑中支持语义灵活性，但在VTON中，它们允许随机噪声破坏确定性的服装特征。我们通过非对称信息动力学分析这一问题，并引入两个诊断指标：用于特征无偏性的条件注意力熵（CAE）和用于注入有效性的注入信息通量（IIF）。我们的分析表明，对称的双向注意力会破坏条件特征并削弱条件信号。为解决这些局限性，我们提出了RealFit框架，该框架结合了单向信息流（UIF）和解耦时间步调制（DTM）。UIF将服装条件与随机噪声隔离以保持服装身份，而DTM优化调制尺度以维持强条件信号。由此产生的时间不变条件分支支持条件KV缓存，将推理时间减少约75%。RealFit为条件生成提供了一种原则性方法，实现了最先进的保真度和效率。

英文摘要

Virtual try-on (VTON) requires precise pixel-level fidelity, yet mainstream Diffusion Transformers (DiTs) often suffer from texture degradation and structural drift. We identify symmetric interactions in standard joint-attention mechanisms as a source of these failures. Although such interactions support semantic flexibility in general-purpose editing, they allow stochastic noise to corrupt deterministic garment features in VTON. We analyze this problem through asymmetric information dynamics and introduce two diagnostic indicators: Conditional Attention Entropy (CAE) for feature unbiasedness and Injected Information Flux (IIF) for injection effectiveness. Our analysis suggests that symmetric bidirectional attention can corrupt conditional features and attenuate the conditional signal. To address these limitations, we propose RealFit, a framework that combines Unidirectional Information Flow (UIF) with Decoupled Timestep Modulation (DTM). UIF isolates the garment condition from stochastic noise to preserve garment identity, while DTM optimizes the modulation scale to maintain a strong conditional signal. The resulting time-invariant condition branch enables a conditional KV cache that reduces inference time by approximately 75%. RealFit offers a principled approach to conditional generation with state-of-the-art fidelity and efficiency.

发表机构

• Alibaba Group（阿里巴巴集团）

机构由 AI 辅助整理，请以论文原文为准。