[论文解读] A-NeRF: Articulated Neural Radiance Fields for Learning Human Shape, Appearance, and Pose

Shih-Yang Su, Frank Yu+2 more|arXiv (Cornell University)|Feb 11, 2021

Human Motion and Animation被引用 92

一句话总结

所提供的文本是 NeurIPS 格式化指令，而非 A-NeRF 论文内容，因此没有可用的方法论或实验细节。

ABSTRACT

While deep learning reshaped the classical motion capture pipeline with feed-forward networks, generative models are required to recover fine alignment via iterative refinement. Unfortunately, the existing models are usually hand-crafted or learned in controlled conditions, only applicable to limited domains. We propose a method to learn a generative neural body model from unlabelled monocular videos by extending Neural Radiance Fields (NeRFs). We equip them with a skeleton to apply to time-varying and articulated motion. A key insight is that implicit models require the inverse of the forward kinematics used in explicit surface models. Our reparameterization defines spatial latent variables relative to the pose of body parts and thereby overcomes ill-posed inverse operations with an overparameterization. This enables learning volumetric body shape and appearance from scratch while jointly refining the articulated pose; all without ground truth labels for appearance, pose, or 3D shape on the input videos. When used for novel-view-synthesis and motion capture, our neural model improves accuracy on diverse datasets. Project website: https://lemonatsu.github.io/anerf/ .

研究动机与目标

• 由于所提供的来源专注于 NeurIPS 格式化指令而非 A-NeRF 论文，因此不可用。
• 无法从所提供的文本中提取实际论文的研究目标。
• 内容不包含 A-NeRF 的目标或动机。

提出的方法

• 无法从所提供的来源获取；文本包含格式化指南，而非研究方法。
• 所提供的内容中不存在 A-NeRF 的核心方程或技术。
• 无法从所给材料中提取体系结构或训练细节。

实验结果

研究问题

• RQ1 无法从所提供的格式化指令中确定具体的研究问题。
• RQ2 未提供与 A-NeRF 相关的实验性或理论性问题。

主要发现

• 无法报告任何发现，因为所提供的文本是格式化指南，而非论文内容。