Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

NeMo: 3D Neural Motion Fields from Multiple Video Instances of the Same Action

About

The task of reconstructing 3D human motion has wideranging applications. The gold standard Motion capture (MoCap) systems are accurate but inaccessible to the general public due to their cost, hardware and space constraints. In contrast, monocular human mesh recovery (HMR) methods are much more accessible than MoCap as they take single-view videos as inputs. Replacing the multi-view Mo- Cap systems with a monocular HMR method would break the current barriers to collecting accurate 3D motion thus making exciting applications like motion analysis and motiondriven animation accessible to the general public. However, performance of existing HMR methods degrade when the video contains challenging and dynamic motion that is not in existing MoCap datasets used for training. This reduces its appeal as dynamic motion is frequently the target in 3D motion recovery in the aforementioned applications. Our study aims to bridge the gap between monocular HMR and multi-view MoCap systems by leveraging information shared across multiple video instances of the same action. We introduce the Neural Motion (NeMo) field. It is optimized to represent the underlying 3D motions across a set of videos of the same action. Empirically, we show that NeMo can recover 3D motion in sports using videos from the Penn Action dataset, where NeMo outperforms existing HMR methods in terms of 2D keypoint detection. To further validate NeMo using 3D metrics, we collected a small MoCap dataset mimicking actions in Penn Action,and show that NeMo achieves better 3D reconstruction compared to various baselines.

Kuan-Chieh Wang, Zhenzhen Weng, Maria Xenochristou, Joao Pedro Araujo, Jeffrey Gu, C. Karen Liu, Serena Yeung• 2022

Related benchmarks

TaskDatasetResultRank
2D Human Pose EstimationMoCap dataset
Recon Error (Baseball Pitch)15.7
5
3D Human Motion RecoveryMoCap Baseball Pitch
MPJPE (Entire Sequence)85.8
5
3D Human Motion RecoveryMoCap Baseball Swing
MPJPE (mm)65.3
5
3D Human Motion RecoveryMoCap Tennis Serve
MPJPE (Entire Sequence)80.6
5
3D Human Motion RecoveryMoCap Tennis Swing
MPJPE (Entire Sequence, mm)65.4
5
3D Human Motion RecoveryMoCap Golf Swing
MPJPE (Entire Sequence, mm)78.9
5
3D Human Motion RecoveryMoCap Mean Across Actions
MPJPE (Entire Sequence, mm)75.2
5
2D Human Pose EstimationPenn-Action (test)
Recon Error (Baseball Pitch)13.31
4
3D Human Motion RecoveryMoCap dataset
Global MPJPE (Baseball Pitch)151.4
2
Showing 9 of 9 rows

Other info

Code

Follow for update