Guidance2 min read
Align3D: Image-Structure Co-Aligned 3D Scene Generation with Observability-Aware Fidelity-Preserving Guidance
We present Align3D, an image-conditioned diffusion model that generates 3D indoor layouts that are both faithful to a single input photograph and physically plausible beyond the observed view.
By Chenliang Zhou, Yifan Wang, Andrzej Banburski-FaheyarXiv - cs.CV (CV)
Read the full story
Originally published by arXiv - cs.CV (CV) on Nov 9, 2026.
Comments
Sign in to join the discussion.