SceneTeract: Probing and Improving Agent-Aware Activity Reasoning in 3D Indoor Scenes
Indoor 3D scenes are ultimately meant to be used: an embodied agent should be able to navigate, reach objects, and complete diverse activities. Yet whether a given scene actually supports these activities for a specific agent profile is rarely verified. Existing evaluations of indoor 3D scenes typically focus on visual quality and semantic plausibility. In contrast, the feasibility of an activity depends on geometric, agent-specific constraints such as reach, clearance, and navigable space availability. These properties are not captured by visual plausibility metrics, and, as we show, VLMs, which are increasingly used to reason about 3D scenes, often fail to determine action feasibility i...
| Authors | Léopold Maillard, Francis Engelmann, Tom Durand et al. |
|---|---|
| Primary category | cs.CV |
| Published | 31 March 2026 |
| Last updated at source | 17 September 2026 |
Connected in the knowledge graph
- leopoldmaillard/sceneteract-grpoDataset · cited by
Models and datasets referencing this paper
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.