AniGS：基于不一致 Gaussian 重建的单图像可动画 Gaussian 化身
AniGS: Animatable Gaussian Avatar from a Single Image with Inconsistent Gaussian Reconstruction
AI总结：
本文提出 AniGS，利用生成式多视角标准姿态图像与 4D Gaussian Splatting 处理视角不一致，实现单张野外图像的照片级实时 3D 人体化身动画。
摘要：
从单张图像生成可动画人类化身对于各类数字人建模应用至关重要。现有 3D 重建方法往往难以捕捉可动画模型中的精细细节，而用于可控动画的生成式方法虽然避免了显式 3D 建模，却在极端姿态下存在视角不一致问题，并伴有计算效率低下的缺陷。本文中，我们利用生成模型的能力生成精细的多视角标准姿态图像，以解决上述挑战，这些图像有助于消除可动画人类重建中的歧义。随后，我们提出一种针对不一致图像的鲁棒 3D 重建方法，使推理阶段能够实现实时渲染。具体而言，我们改造了一个基于 transformer 的视频生成模型，用于生成多视角标准姿态图像和法线图，并在大规模视频数据集上进行预训练以提升泛化能力。为处理视角不一致问题，我们将重建问题重新表述为一项 4D 任务，并引入一种使用 4D Gaussian Splatting 的高效 3D 建模方法。实验表明，我们的方法能够根据野外图像实现照片级真实感的 3D 人类化身实时动画，展示了其有效性和泛化能力。
英文摘要：
Generating animatable human avatars from a single image is essential for various digital human modeling applications. Existing 3D reconstruction methods often struggle to capture fine details in animatable models, while generative approaches for controllable animation, though avoiding explicit 3D modeling, suffer from viewpoint inconsistencies in extreme poses and computational inefficiencies. In this paper, we address these challenges by leveraging the power of generative models to produce detailed multi-view canonical pose images, which help resolve ambiguities in animatable human reconstruction. We then propose a robust method for 3D reconstruction of inconsistent images, enabling real-time rendering during inference. Specifically, we adapt a transformer-based video generation model to generate multi-view canonical pose images and normal maps, pretraining on a large-scale video dataset to improve generalization. To handle view inconsistencies, we recast the reconstruction problem as a 4D task and introduce an efficient 3D modeling approach using 4D Gaussian Splatting. Experiments demonstrate that our method achieves photorealistic, real-time animation of 3D human avatars from in-the-wild images, showcasing its effectiveness and generalization capability.
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。
