Towards Open Domain Text-Driven Synthesis of Multi-Person Motions

The European Conference on Computer Vision (ECCV) 2024
Teaser Image

Abstract

This work aims to generate natural and diverse group motions of multiple humans from textual descriptions. While single-person text-to-motion generation is extensively studied, it remains challenging to synthesize motions for more than one or two subjects from in-the-wild prompts, mainly due to the lack of available datasets. In this work, we curate human pose and motion datasets by estimating pose information from large-scale image and video datasets. Our models use a transformer-based diffusion framework that accommodates multiple datasets with any number of subjects or frames. Experiments explore both generation of multi-person static poses and generation of multi-person motion sequences. To our knowledge, our method is the first to generate multi-subject motion sequences with high diversity and fidelity from a large variety of textual prompts.

Dataset

To address the data scarcity problem in multi-person domain, we introduce two datasets: LAION-Pose and WebVid-Motion, containing (image, pose, text) and (video, motion, text) tuples extracted from in-the-wild images and videos.

Dataset Overview

Model Architecture

Our model is a diffusion framework consisting of interleaving pose and motion layers. At each pose/motion layer, we reshape the temporal/subject dimension into the batch dimension so that the layer focuses on generating per frame subject interac- tion and per-subject temporal movements respectively. Each layer is implemented as a transformer encoder. Diffusion time steps and text or pose conditions are encoded and summed up as a condition token concatenated to the beginning of the sequence.

Model Architecture

BibTeX


          @inproceedings{shan2024multiperson,
            title={Towards Open Domain Text-Driven Synthesis of Multi-Person Motions},
            author={Mengyi Shan, Lu Dong, Yutao Han, Yuan Yao, Tao Liu, Ifeoma Nwogu, Guo-Jun Qi, Mitch Hill},
            year={2024},
            booktitle={European Conference on Computer Vision (ECCV)},
          }