Locomotion-Action-Manipulation:
Synthesizing Human-Scene Interactions in Complex 3D Environments

Jiye Lee Hanbyul Joo

Seoul National University

ICCV 2023

We present LAMA, a method to synthesize natural and plausible long term human movements in complex indoor environments by using human motion capture data only. The synthesized motion include a series of easily observable daily life actions, including locomotion, interactions with 3D scenes, and manipulations of 3D objects.

ABSTRACT

Synthesizing interaction-involved human motions has been challenging due to the high complexity of 3D environments and the diversity of possible human behaviors within. We present LAMA, Locomotion-Action-MAnipulation, to synthesize natural and plausible long term human movements in complex indoor environments. The key motivation of LAMA is to build a unified framework to encompass a series of everyday motions including locomotion, scene interaction, and object manipulation. Unlike existing methods that require motion data "paired'' with scanned 3D scenes for supervision, we formulate the problem as a test-time optimization by using human motion capture data only for synthesis. LAMA leverages a reinforcement learning framework coupled with motion matching algorithm for optimization, and further exploits a motion editing framework via manifold learning to cover possible variations in interaction and manipulation. Throughout extensive experiments, we demonstrate that LAMA outperforms previous approaches in synthesizing realistic motions in various challenging scenarios.

MORE RESULTS
VIDEO
ACK.

This work was supported by SNU-Naver Hyperscale AI Center, SNU Creative-Pioneering Researchers Program, and NRF grant funded by the Korea government (MSIT) (No. 2022R1A2C209272411).

BIBTEX
                                
    @article{lee2023lama,
        title = {Locomotion-Action-Manipulation: 
               Synthesizing Human-Scene Interactions in Complex 3D Environments},
        author = {Lee, Jiye and Joo, Hanbyul},
        journal = {arXiv preprint arXiv:2301.02667},
        year = {2023}
    }