Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Realistic Full-Body Tracking from Sparse Observations via Joint-Level Modeling

About

To bridge the physical and virtual worlds for rapidly developed VR/AR applications, the ability to realistically drive 3D full-body avatars is of great significance. Although real-time body tracking with only the head-mounted displays (HMDs) and hand controllers is heavily under-constrained, a carefully designed end-to-end neural network is of great potential to solve the problem by learning from large-scale motion data. To this end, we propose a two-stage framework that can obtain accurate and smooth full-body motions with the three tracking signals of head and hands only. Our framework explicitly models the joint-level features in the first stage and utilizes them as spatiotemporal tokens for alternating spatial and temporal transformer blocks to capture joint-level correlations in the second stage. Furthermore, we design a set of loss terms to constrain the task of a high degree of freedom, such that we can exploit the potential of our joint-level modeling. With extensive experiments on the AMASS motion dataset and real-captured data, we validate the effectiveness of our designs and show our proposed method can achieve more accurate and smooth motion compared to existing approaches.

Xiaozheng Zheng, Zhuo Su, Chao Wen, Zhou Xue, Xiaojie Jin• 2023

Related benchmarks

TaskDatasetResultRank
Human Motion ReconstructionAMASS (Protocol 1)
MPJRE2.9
18
Full-body motion generationGORP (Real MC)
MPJPE5.97
16
Motion generation from hand-tracking signalGORP (Real HT)
MPJPE6.62
16
Human Pose EstimationAMASS (Protocol 1)
MPJPE4.92
12
Egocentric Motion ReconstructionEE4D-Motion (test)
Semantic Alignment Score0.829
11
Full-body motion generationGORP (Simulated MC)
MPJPE4.81
8
Full-body Avatar ReconstructionAMASS Setting S1 (test)
MPJRE2.9
8
Full-body Avatar ReconstructionAMASS (S1)
MPJRE2.4
8
Full-body motion estimation (Hand Tracking)A-P2 (test)
MPJRE5.71
8
Human Pose EstimationAMASS Protocol 2, Upper body ×0.7 (test)
MPJPE7.44
8
Showing 10 of 25 rows

Other info

Follow for update