on: Dec. 2019
in: ECCV

Dense RepPoints: Representing Visual Objects with Dense Point Sets

Yinghao Xu*
Ze Yang*
Han Xue*
Raquel Urtasun
Liwei Wang
Stephen Lin
Han Hu

ArXiv

@inproceedings{dense2020,
  title = {Dense RepPoints: Representing Visual Objects with Dense Point Sets},
  author = {Xu, Yinghao and Yang, Ze and Xue, Han and Urtasun, Raquel and Wang, Liwei and Lin, Stephen and Hu, Han},
  booktitle = {ECCV},
  year = {2020}
}

We present a new object representation, called Dense RepPoints, that utilizes a large set of points to describe an object at multiple levels, including both box level and pixel level. Techniques are proposed to efficiently process these dense points, maintaining near-constant complexity with increasing point numbers. Dense RepPoints is shown to represent and learn object segments well, with the use of a novel distance transform sampling method combined with set-to-set supervision. The distance transform sampling combines the strengths of contour and grid representations, leading to performance that surpasses counterparts based on contours or grids. Code is available at https://github.com/justimyhxu/Dense-RepPoints.