Autonomous Character-Scene Interaction Synthesis from Text Instruction

TL;DR

This paper introduces a novel framework that synthesizes complex, multi-stage human interaction motions in 3D environments directly from text instructions, leveraging diffusion models and scene-aware representations.

Contribution

It presents a new approach combining auto-regressive diffusion models, scene perception, and language integration to automate character animation from simple text inputs.

Findings

High-quality multi-stage motion synthesis from text

Effective scene-aware motion integration

A new annotated motion dataset for training

Abstract

Synthesizing human motions in 3D environments, particularly those with complex activities such as locomotion, hand-reaching, and human-object interaction, presents substantial demands for user-defined waypoints and stage transitions. These requirements pose challenges for current models, leading to a notable gap in automating the animation of characters from simple human inputs. This paper addresses this challenge by introducing a comprehensive framework for synthesizing multi-stage scene-aware interaction motions directly from a single text instruction and goal location. Our approach employs an auto-regressive diffusion model to synthesize the next motion segment, along with an autonomous scheduler predicting the transition for each action stage. To ensure that the synthesized motions are seamlessly integrated within the environment, we propose a scene representation that considers the local perception both at the start and the goal location. We further enhance the coherence of the generated motion by integrating frame embeddings with language input. Additionally, to support model training, we present a comprehensive motion-captured dataset comprising 16 hours of motion sequences in 120 indoor scenes covering 40 types of motions, each annotated with precise language descriptions. Experimental results demonstrate the efficacy of our method in generating high-quality, multi-stage motions closely aligned with environmental and textual conditions.