用多尺度纹理实现高保真可驱动全身虚拟人，近景渲染更真实。
CloseUpAvatar: High-Fidelity Animatable Full-Body Avatars with Mixture of Multi-Scale Textures
- 用低频与高频纹理平面表示虚拟人，近景自动启用高清细节。
- 在演员数据集上实现更广视角的逼真渲染，帧率保持高效。
- 适合需要近景高精度渲染的虚拟人应用，如影视与游戏。
我们提出 CloseUpAvatar——一种新型可驱动人体虚拟人表示方法，能处理更广泛的摄像机运动，同时保持近景视图的高质量渲染。CloseUpAvatar 将虚拟人建模为一组带有两套可学习纹理（低频与高频）的纹理平面。当摄像机靠近人体表面时，系统自动切换至高频纹理并逐步降低其影响，随距离增加而平滑衰减。这种参数化方式使渲染质量随摄像机距离动态调整，在更广泛视角下实现逼真效果，优于以往方法。我们在高分辨率输入图像的 ActorsHQ 数据集上进行了实验，结果表明该方法在新视角渲染上兼具定性与定量优势，且通过限制所需基元数量，保持了高帧率性能。
原文摘要 · Abstract (English)
We present a CloseUpAvatar - a novel approach for articulated human avatar representation dealing with more general camera motions, while preserving rendering quality for close-up views. CloseUpAvatar represents an avatar as a set of textured planes with two sets of learnable textures for low and high-frequency detail. The method automatically switches to high-frequency textures only for cameras positioned close to the avatar's surface and gradually reduces their impact as the camera moves farther away. Such parametrization of the avatar enables CloseUpAvatar to adjust rendering quality based on camera distance ensuring realistic rendering across a wider range of camera orientations than previous approaches. We provide experiments using the ActorsHQ dataset with high-resolution input images. CloseUpAvatar demonstrates both qualitative and quantitative improvements over existing methods in rendering from novel wide range camera positions, while maintaining high FPS by limiting the number of required primitives.
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。