10 papers with code • 1 benchmarks • 4 datasets
By stacking RUs in a deep-to-shallow manner, SRN exploits the 'flow' of errors among multiple scales to ease the problems of fitting complex outputs with limited layers, suppressing the complex backgrounds, and effectively matching object symmetry of different scales.
Symmetry is one of the significant visual properties inside an image plane, to identify the geometrically balanced structures through real-world objects.
The end-to-end deep learning approach, referred to as a side-output residual network (SRN), leverages the output residual units (RUs) to fit the errors between the object ground-truth symmetry and the side-outputs of multiple stages.
Finally, we make available a collection of images of graph drawings with specific symmetric features that can be used in machine learning systems for training, testing and validation purposes.
In this paper, we present a novel learning framework to automatically discover global planar reflective symmetry of a 3D shape.
Such data augmentation technique can be exploited as a preliminary process to be executed before the adoption of an Offline Reinforcement Learning architecture, increasing its performance.
We demonstrate and analyze the performance of the extended algorithm to detect localised symmetries and the machine learning model to classify rotational symmetries.