COUCH: Towards Controllable Human-Chair Interactions

TL;DR

This paper introduces COUCH, a framework for synthesizing controllable human-chair interactions by predicting contact-aware control signals, supported by a new dataset, enabling fine-grained motion control and demonstrating superior results.

Contribution

The paper presents a novel contact-conditioned human-object interaction synthesis method and introduces the COUCH Dataset for human-chair interactions.

Findings

Significant improvements over existing methods in quantitative metrics.

Enables user-specified and automatic contact control.

Provides a large, annotated dataset for human-chair interactions.

Abstract

Humans interact with an object in many different ways by making contact at different locations, creating a highly complex motion space that can be difficult to learn, particularly when synthesizing such human interactions in a controllable manner. Existing works on synthesizing human scene interaction focus on the high-level control of action but do not consider the fine-grained control of motion. In this work, we study the problem of synthesizing scene interactions conditioned on different contact positions on the object. As a testbed to investigate this new problem, we focus on human-chair interaction as one of the most common actions which exhibit large variability in terms of contacts. We propose a novel synthesis framework COUCH that plans ahead the motion by predicting contact-aware control signals of the hands, which are then used to synthesize contact-conditioned interactions. Furthermore, we contribute a large human-chair interaction dataset with clean annotations, the COUCH Dataset. Our method shows significant quantitative and qualitative improvements over existing methods for human-object interactions. More importantly, our method enables control of the motion through user-specified or automatically predicted contacts.