Introduces the first framework and large-scale dataset for detecting 3D-grounded reflection symmetries from single in-the-wild RGB images of architectural landmarks using signed distance maps on predicted geometry.
Symmetrynet: Learning to predict reflectional and rotational symmetries of 3d shapes from single- view rgb-d images.ACM TOG, 39(6):1–14, 2020
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
ArchSym: Detecting 3D-Grounded Architectural Symmetries in the Wild
Introduces the first framework and large-scale dataset for detecting 3D-grounded reflection symmetries from single in-the-wild RGB images of architectural landmarks using signed distance maps on predicted geometry.