Beyond Planar Symmetry: Modeling Human Perception of Reflection and Rotation Symmetries in the Wild

By Christopher Funk, Yanxi Liu. 2017

43 citations recorded by the source corpus.

Humans take advantage of real world symmetries for various tasks, yet capturing their superb symmetry perception mechanism with a computational model remains elusive. Motivated by a new study demonstrating the extremely high inter-person accuracy of human perceived symmetries in the wild, we have constructed the first deeplearning neural network for reflection and rotation symmetry detection (Sym-NET), trained on photos from MS-COCO (Microsoft-Common Object in COntext) dataset with nearly 11K consistent symmetry-labels from more than 400 human observers. We employ novel methods to convert discrete human labels into symmetry heatmaps, capture symmetry densely in an image and quantitatively evaluate Sym-NET against multiple existing computer vision algorithms. On CVPR 2013 symmetry competition testsets and unseen MSCOCO photos, Sym-NET significantly outperforms all other competitors. Beyond mathematically well-defined symmetries on a plane, Sym-NET demonstrates abilities to identify viewpoint-varied 3D symmetries, partially occluded symmetrical objects, and symmetries at a semantic level.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

1. Josh Tenenbaum
2. Xiuming Zhang
3. Chengkai Zhang
4. Zhoutong Zhang
5. Jiajun Wu
6. Ali Borji
7. Bill Freeman

In Computer Vision and Pattern Recognition

1. Jiajun Wu
2. Jitendra Malik
3. Josh Tenenbaum
4. Luc Van Gool
5. Andrea Vedaldi
6. Ming-Hsuan Yang
7. Dacheng Tao
8. Ali Borji

Citations in the corpus

• Learning to Reconstruct Shapes from Unseen Classes (2018, background): “Very recently, researchers have begun to look at the generalization power of 3D reconstruction algorithms [Shin et al., 2018, Jayaraman et al., 2018, Rock et al., 2015, Funk and Liu, 2017].”
• Pros and Cons of GAN Evaluation Measures (2018, background): “For example, understanding how humans perceive symmetry [19, 26] or image clutter [67] in generated images versus natural scenes can give clues regarding the plausibility of the generated images.”