Dense RepPoints: Representing Visual Objects with Dense Point Sets
This work addresses object representation in computer vision, offering a novel approach that improves over existing methods, though it appears incremental in advancing point-based representations.
The paper tackles the problem of representing visual objects by introducing Dense RepPoints, a method using dense point sets for multi-level object description, which achieves performance surpassing contour- or grid-based counterparts through a novel distance transform sampling technique.
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 \url{https://github.com/justimyhxu/Dense-RepPoints}.