Person-In-Situ：具有遮挡感知姿态控制的场景一致人物图像插入
Person-In-Situ: Scene-Consistent Human Image Insertion with Occlusion-Aware Pose Control
AI总结：
本文提出两种基于3D姿态控制和潜在扩散模型的人物插入方法，无需遮挡掩码即可在场景中自然合成人物并保持场景一致性，优于现有方法。
摘要：
将人物合成到场景图像中在娱乐和广告等领域具有广泛应用。然而，现有方法通常无法处理被前景物体遮挡的插入人物，并且会不自然地将人物放置在最前层。此外，它们对插入人物姿态的控制能力有限。为解决这些挑战，我们提出了两种方法。两种方法都允许通过3D身体模型进行显式姿态控制，并利用潜在扩散模型在上下文合适的深度合成人物，从而自然地处理遮挡而无需遮挡掩码。第一种是两阶段方法：模型首先通过监督学习学习包含人物的场景深度图，然后据此合成人物。第二种方法隐式学习遮挡，并在没有显式深度监督的情况下直接从输入数据合成人物。定量和定性评估表明，两种方法在更好地保持场景一致性的同时准确反映遮挡和用户指定姿态方面，均优于现有方法。
英文摘要：
Compositing human figures into scene images has broad applications in areas such as entertainment and advertising. However, existing methods often cannot handle occlusion of the inserted person by foreground objects and unnaturally place the person in the frontmost layer. Moreover, they offer limited control over the inserted person's pose. To address these challenges, we propose two methods. Both allow explicit pose control via a 3D body model and leverage latent diffusion models to synthesize the person at a contextually appropriate depth, naturally handling occlusions without requiring occlusion masks. The first is a two-stage approach: the model first learns a depth map of the scene with the person through supervised learning, and then synthesizes the person accordingly. The second method learns occlusion implicitly and synthesizes the person directly from input data without explicit depth supervision. Quantitative and qualitative evaluations show that both methods outperform existing approaches by better preserving scene consistency while accurately reflecting occlusions and user-specified poses.
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。
