基于多视角语义一致性的通用人体高斯点云生成
Generalizable Human Gaussian Splatting via Multi-view Semantic Consistency
AI总结：
本文提出基于多视角语义一致性的方法，通过预测深度图和跨视角注意力机制，解决多视角输入下人体3D高斯点云定位不一致问题，提升渲染质量。
摘要：
最近，从稀疏视角输入生成逼真人体渲染的通用性高斯点云方法得到了积极研究。现有方法主要依赖显式几何约束或预定义结构表示来精确定位3D高斯点。尽管这些方法在该领域取得了显著进展，但仍然由于人体复杂运动和不同视角之间重叠有限，导致多视角输入下特征表示不一致。为了解决这个问题，我们提出了一种新的方法，通过将每个视角编码的潜在嵌入投影到共享的3D空间，并基于跨视角注意力重新校准它们所属的同一身体部分，从而帮助模型解决高纹理区域和遮挡身体部分中的空间歧义，最终实现3D高斯点云的准确定位。在基准数据集上的实验结果表明，所提出的方法有效提高了从稀疏视角输入生成通用性高斯点云的性能。
英文摘要：
Recently, generalizable human Gaussian splatting from sparse-view inputs has been actively studied for the photorealistic human rendering. Most existing methods rely on explicit geometric constraints or predefined structural representations to accurately position 3D Gaussians. Although these approaches have shown the remarkable progress in this field, they still suffer from inconsistent feature representations across multi-view inputs due to complex articulations of the human body and limited overlaps between different views. To address this problem, we propose a novel method to accurately localize 3D Gaussians and ultimately improve the quality of human rendering. The key idea is to unproject latent embeddings encoded from each viewpoint into a shared 3D space through predicted depth maps and recalibrate them belonging to the same body part based on cross-view attention. This helps the model resolve the spatial ambiguity occurring in highly textured regions as well as occluded body parts, thus leading to the accurate localization of 3D Gaussians. Experimental results on benchmark datasets show that the proposed method efficiently improves the performance of generalizable human Gaussian splatting from sparse-view inputs.
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。
