We present a coupled formulation for detecting symmetric line arrangements and 3D reconstruction for producing factored facade models. Unlike most competing approaches, we benefit from large-scale model repetitions, and can robustly handle inputs with strong reflections, shadow elements, or outlier objects, which are difficult to disambiguate with only local reasoning.
Computer Graphics Forum (Proceedings of Eurographics), 2012
We introduce a novel framework for image-based 3D reconstruction of urban buildings based on symmetry priors. Starting from image-level edges, we generate a sparse and approximate set of consistent 3D lines. These lines are then used to simultaneously detect symmetric line arrangements while refining the estimated 3D model. Operating both on 2D image data and intermediate 3D feature representations, we perform iterative feature consolidation and effective outlier pruning, thus eliminating reconstruction artifacts arising from ambiguous or wrong stereo matches. We exploit non-local coherence of symmetric elements to generate precise model reconstructions, even in the presence of a significant amount of outlier image-edges arising from reflections, shadows, outlier objects, etc. We evaluate our algorithm on several challenging test scenarios, both synthetic and real. Beyond reconstruction, the extracted symmetry patterns are useful towards interactive and intuitive model manipulations.
We show the optimized repetition pattern and the final reconstruction.
A shiny coffee table with reflective and rotational symmetries reconstructed with out approach.