Abstract
Humans perceive and construct the surrounding world as an arrangement of simple parametric models. In particular, man-made environments commonly consist of volumetric primitives such as cuboids or cylinders. Inferring these primitives is an important step to attain high-level, abstract scene descriptions. Previous approaches directly estimate shape parameters from a 2D or 3D input, and are only able to reproduce simple objects, yet unable to accurately parse more complex 3D scenes. In contrast, we propose a robust estimator for primitive fitting, which can meaningfully abstract real-world environments using cuboids. A RANSAC estimator guided by a neural network fits these primitives to 3D features, such as a depth map. We condition the network on previously detected parts of the scene, thus parsing it one-by-one. To obtain 3D features from a single RGB image, we additionally optimise a feature extraction CNN in an end-to-end manner. However, naively minimising point-to-primitive distances leads to large or spurious cuboids occluding parts of the scene behind. We thus propose an occlusion-aware distance metric correctly handling opaque scenes. The proposed algorithm does not require labour-intensive labels, such as cuboid annotations, for training. Results on the challenging NYU Depth v2 dataset demonstrate that the proposed algorithm successfully abstracts cluttered real-world 3D scene layouts.
Original language | English |
---|---|
Title of host publication | 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) |
Publisher | IEEE |
Pages | 13065-13074 |
Number of pages | 10 |
ISBN (Electronic) | 978-1-6654-4509-2 |
ISBN (Print) | 978-1-6654-4510-8 |
DOIs | |
Publication status | Published - 13 Nov 2021 |
Event | IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2021 - Nashville, TN, USA, Virtual Event Duration: 19 Jun 2021 → 25 Jun 2021 |
Conference
Conference | IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2021 |
---|---|
Abbreviated title | CVPR 2021 |
City | Virtual Event |
Period | 19/06/21 → 25/06/21 |
Keywords
- 2024 OA procedure