An Empty Room is All We Want: Automatic Defurnishing of Indoor Panoramas

Mira Slavcheva, Dave Gausebeck, Kevin Chen, David Buchhofer, Azwad Sabik, Chen Ma, Sachal Dhillon, Olaf Brandt, Alan Dolhasz; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2024, pp. 7384-7394

Abstract

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.

Related Material

[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Slavcheva_2024_CVPR, author = {Slavcheva, Mira and Gausebeck, Dave and Chen, Kevin and Buchhofer, David and Sabik, Azwad and Ma, Chen and Dhillon, Sachal and Brandt, Olaf and Dolhasz, Alan}, title = {An Empty Room is All We Want: Automatic Defurnishing of Indoor Panoramas}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2024}, pages = {7384-7394} }