Defurnishing with X-Ray Vision: Joint Removal of Furniture from Panoramas and Mesh

We present a pipeline for generating defurnished replicas of indoor spaces represented as textured meshes and corresponding multi-view panoramic images. To achieve this, we first segment and remove furniture from the mesh representation, extend planes, and fill holes, obtaining a simplified defurnished mesh (SDM). This SDM acts as an ``X-ray'' of the scene's underlying structure, guiding the defurnishing process. We extract Canny edges from depth and normal images rendered from the SDM. We then use these as a guide to remove the furniture from panorama images via ControlNet inpainting. This control signal ensures the availability of global geometric information that may be hidden from a particular panoramic view by the furniture being removed. The inpainted panoramas are used to texture the mesh. We show that our approach produces higher quality assets than methods that rely on neural radiance fields, which tend to produce blurry low-resolution images, or RGB-D inpainting, which is highly susceptible to hallucinations.

@article{dolhasz2025_2506.05338,
  title={ Defurnishing with X-Ray Vision: Joint Removal of Furniture from Panoramas and Mesh },
  author={ Alan Dolhasz and Chen Ma and Dave Gausebeck and Kevin Chen and Gregor Miller and Lucas Hayne and Gunnar Hovden and Azwad Sabik and Olaf Brandt and Mira Slavcheva },
  journal={arXiv preprint arXiv:2506.05338},
  year={ 2025 }
}