Dense RepPoints:
Representing Visual Objects with Dense Point Sets

Ze Yang*
Yinghao Xu*
Han Xue*
Zheng Zhang
Raquel Urtasun
Liwei Wang
Stephen Lin
Han Hu
Checkout our Paper and Code !!

Using Dense RepPoints to represent Visual object in different geometric forms. And generating image segments by ConcaveHull and Triangulation.


We present a new object representation, called Dense RepPoints, which utilize a large number of points to describe the multi-grained object representation of both box level and pixel level. Techniques are proposed to efficiently process these dense points, which maintains near constant complexity with increasing point number. The Dense RepPoints is proved to represent and learn object segment well, by a novel distance transform sampling method combined with a set-to-set supervision. The novel distance transform sampling method combines the strength of contour and grid representation, which significantly outperforms the counter-parts using contour or grid representations. On COCO, it achieves 39.6 mask AP and 48.3 bbox AP.


The visualization of the points and instance masks inferenced by using Triangulation. Top: The distribution of learned points are nearly around mask boundary(225 points). Bottom: The foreground mask infered by triangulation as well as barycentric interpolation on COCO test-dev images.


        title   = {Dense RepPoints: Representing Visual Objects with Dense Point Sets},
        author  = {Yang, Ze and Xu, Yinghao and Xue, Han and Zhang, Zheng and Urtasun, 
                   Raquel and Wang, Liwei and Lin, Stephen and Hu, Han},
        journal = {arXiv preprint arXiv:1912.11473},
        year    = {2019}