Align3D diffusion model generates photo-faithful 3D indoor layouts
Researchers introduced Align3D, an image-conditioned diffusion model that generates 3D indoor layouts faithful to a single input photograph while remaining physically plausible.
Read the full story at arXiv cs.CV ↗
Timeline · 1 report
- 2026-11-10 05:00 · arXiv cs.CV
Align3D: Image-Structure Co-Aligned 3D Scene Generation with Observability-Aware Fidelity-Preserving Guidance