An Empty Room is All We Want: Automatic Defurnishing of Indoor Panoramas
This work addresses the need for automated defurnishing in indoor scene editing, but it is incremental as it builds on existing inpainting methods with specific enhancements.
The paper tackles the problem of removing furniture from indoor panorama images by proposing a pipeline that uses Stable Diffusion for inpainting, achieving high-fidelity and geometrically plausible results without room layout estimation, with demonstrated qualitative and quantitative improvements over existing techniques.
We propose a pipeline that leverages Stable Diffusion to improve inpainting results in the context of defurnishing -- the removal of furniture items from indoor panorama images. Specifically, we illustrate how increased context, domain-specific model fine-tuning, and improved image blending can produce high-fidelity inpaints that are geometrically plausible without needing to rely on room layout estimation. We demonstrate qualitative and quantitative improvements over other furniture removal techniques.