Abstract | ||
---|---|---|
The rising availability of commercial 360 degrees 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/ |
Year | DOI | Venue |
---|---|---|
2021 | 10.1109/CVPRW53098.2021.00412 | 2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGITION WORKSHOPS (CVPRW 2021) |
DocType | ISSN | Citations |
Conference | 2160-7508 | 0 |
PageRank | References | Authors |
0.34 | 0 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Vasileios Gkitsas | 1 | 0 | 1.01 |
Vladimiros Sterzentsenko | 2 | 3 | 3.12 |
Nikolaos Zioulis | 3 | 34 | 10.15 |
Georgios Albanis | 4 | 0 | 0.34 |
Dimitrios Zarpalas | 5 | 303 | 33.96 |