PanoDR: Spherical Panorama Diminished Reality for Indoor Scenes

• Published in: 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) pp. 3711 - 3721
• Main Authors: Gkitsas, Vasileios, Sterzentsenko, Vladimiros, Zioulis, Nikolaos, Albanis, Georgios, Zarpalas, Dimitrios
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.06.2021
• Subjects: Computer vision; Conferences; Image segmentation; Measurement; Pattern recognition; Planning; Predictive models
• ISSN: 2160-7516
• DOI: 10.1109/CVPRW53098.2021.00412

The rising availability of commercial 360° cameras that democratize indoor scanning, has increased the interest for novel applications, such as interior space re-design. Diminished Reality (DR) fulfills the requirement of such applications, to remove existing objects in the scene, essentially translating this to a counterfactual inpainting task. While recent advances in data-driven inpainting have shown significant progress in generating realistic samples, they are not constrained to produce results with reality mapped structures. To preserve the 'reality' in indoor (re-)planning applications, the scene's structure preservation is crucial. To ensure structure-aware counterfactual inpainting, we propose a model that initially predicts the structure of a indoor scene and then uses it to guide the reconstruction of an empty - background only - representation of the same scene. We train and compare against other state-of-the-art methods on a version of the Structured3D dataset [47] modified for DR, showing superior results in both quantitative metrics and qualitative results, but more interestingly, our approach exhibits a much faster convergence rate. Code and models are available at github.com/VCL3D/PanoDR/