A-NeRF: Articulated Neural Radiance Fields for Learning Human Shape, Appearance, and Pose
arXiv:2102.06199
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/ .
arXiv commentNeurIPS 2021. Project website: https://lemonatsu.github.io/anerf/
References in corpus (8)
- Rethinking Atrous Convolution for Semantic Image Segmentation
- VNect: Real-time 3D Human Pose Estimation with a Single RGB Camera
- Learning from Synthetic Humans
- Lifting from the Deep: Convolutional 3D Pose Estimation from a Single Image
- Deep Appearance Models for Face Rendering
- MotioNet: 3D Human Motion Reconstruction from Monocular Video with Skeleton Consistency
- OriNet: A Fully Convolutional Network for 3D Human Pose Estimation
- Unite the People: Closing the Loop Between 3D and 2D Human Representations