Generating Human Motion in 3D Scenes
from Text Descriptions

Abstract

Generating human motions from textual descriptions has gained growing research interest due to its wide range of applications. However, only a few works consider human-scene interactions together with text conditions, which is crucial for visual and physical realism. This paper focuses on the task of generating human motions in 3D indoor scenes given text descriptions of the human-scene interactions. This task presents challenges due to the multimodality nature of text, scene, and motion, as well as the need for spatial reasoning. To address these challenges, we propose a new approach that decomposes the complex problem into two more manageable sub-problems: (1) language grounding of the target object and (2) object-centric motion generation. For language grounding of the target object, we leverage the power of large language models. For motion generation, we design an object-centric scene representation for the generative model to focus on the target object, thereby reducing the scene complexity and facilitating the modeling of the relationship between human motions and the object. Experiments demonstrate the better motion quality of our approach compared to baselines and validate our design choices.

Method Overview

Overview of our two-stage pipeline. In the first stage, given an input scene and a text description (a), we use ChatGPT to locate the target object (b). In the second stage, human motions are synthesized by first producing human trajectories (c) and then generating local poses (d).

Localizing the Target Object

Pipeline of localizing the target object. In stage 1, given the input text description and detected object bounding boxes (bbx), we construct the first prompt asking ChatGPT the categories of target objects and anchor objects. Based on the response, the scene graph can be simplified. In stage 2, we construct the second prompt with inputs and results from stage 1, including object relations derived from the simplified scene graph. The second prompt is designed for asking ChatGPT to infer the target object. Finally, we can get the target object bounding box from the response of ChatGPT.

Sensors for Motion Generation

The visualization of the sensors. The target sensor (b) gives detailed geometry of the target object. The environment sensor (c) gives coarse spatial information around the target object. The trajectory sensor (d) is located around the human.

Qualitative Results

Generalization on the PROX Dataset

Our method can work on the unseen scenes without fine-tuning.

Diverse Results

With the same text and scene inputs, our method can generate diverse motions.

Walk to the coffee table.