VSDiffusion：通过可见性约束扩散镇定模糊的阴影生成
VSDiffusion: Taming Ill-Posed Shadow Generation via Visibility-Constrained Diffusion
AI总结：
VSDiffusion通过可见性约束扩散框架，结合多尺度结构指导和软先验图，有效生成逼真阴影，提升复杂场景下的几何一致性。
摘要：
生成逼真的投影阴影以插入前景物体是图像合成中至关重要的却具有挑战性的问题，其中在复杂场景中保持阴影和物体的几何一致性仍然困难，因为阴影形成本身具有不明确的性质。为了解决这个问题，我们提出了VSDiffusion，一种可见性约束的两阶段框架，旨在通过引入可见性先验来缩小解空间。在第一阶段，我们预测一个粗略的阴影掩膜以定位可能的阴影生成区域。在第二阶段，通过从复合图像中估计的光照和深度线索进行条件扩散，以生成准确的阴影。在VSDiffusion中，我们通过两种互补的路径注入可见性先验。首先，一个具有阴影门控交叉注意力的可见性控制分支，提供多尺度的结构指导。然后，一个学习到的软先验图，重新加权训练损失以增强几何校正。此外，我们还引入了高频引导增强模块以锐化边界并改善与背景的纹理交互。在广泛使用的公共DESOBAv2数据集上的实验表明，我们提出的VSDiffusion能够生成准确的阴影，并在大多数评估指标上建立了新的SOTA结果。
英文摘要：
Generating realistic cast shadows for inserted foreground objects is a crucial yet challenging problem in image composition, where maintaining geometric consistency of shadow and object in complex scenes remains difficult due to the ill-posed nature of shadow formation. To address this issue, we propose VSDiffusion, a visibility-constrained two-stage framework designed to narrow the solution space by incorporating visibility priors. In Stage I, we predict a coarse shadow mask to localize plausible shadow generated regions. And in Stage II, conditional diffusion is performed guided by lighting and depth cues estimated from the composite to generate accurate shadows. In VSDiffusion, we inject visibility priors through two complementary pathways. First, a visibility control branch with shadow-gated cross attention that provides multi-scale structural guidance. Then, a learned soft prior map that reweights training loss in error-prone regions to enhance geometric correction. Additionally, we also introduce high-frequency guided enhancement module to sharpen boundaries and improve texture interaction with the background. Experiments on widely used public DESOBAv2 dataset demonstrated that our proposed VSDiffusion can generate accurate shadow, and establishes new SOTA results across most evaluation metrics.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
