AI
Architect-Ant: Editable Automatic Furnishing of Architectural Floor Plans
Publication: Hugging Face Daily Papers
Author: Not available in collected metadata
Source published: 29/09/2026, 20:00:00 UTC
Briefing created: 03/10/2026, 05:06:19 UTC
Based on a feed excerpt; full article content has not been acquired. Source evidence retrieved 02/10/2026, 12:18:25 UTC.
Briefings
This article presents Architect-Ant, a framework for generating furniture layouts from real architectural floor plans using a pretrained model. The system learns professional furnishing patterns through supervised fine-tuning on a curated dataset of 505 professional plans, achieving low geometric violations while maintaining high functional completeness. The resulting layouts are object-level editable and can be converted into 3D scenes, offering a direct constraint-aware alternative to costly iterative agentic inference.
Key points
- Architect-Ant is a framework that generates furniture layouts from real architectural floor plans using a pretrained model.
- The system learns professional furnishing patterns through supervised fine-tuning on a curated dataset of 505 professional plans.
Context and limitations
The dataset contains 505 real professional architectural floor plans with dense furniture annotations, but coverage is limited to this specific curated collection rather than all available real-world data.
Generated by Bittrees-hosted qwen35-2b sha256:aaf42c8b7c3c on 03/10/2026, 05:06:19 UTC. Based on publisher-provided feed evidence; may not cover the full original article. Check the source for details.
View archived briefing on IPFS
bafybeicn7aoxnjvc46f6fop2xqkxut3o43733dgd22s2rmaf3ixoptvbhe