Month: April 2019
-
Calendar
June 2021
Monday
Tuesday
Wednesday
Thursday
Friday
Saturday
Sunday
May 31, 2021
2:00 pm: PhD Seminars X
2:00 pm: PhD Seminars X
May 31, 2021
–
Talk 1
Speaker
Muxingzi Li (Titane)
Title
Approximating shapes in images with low-complexity polygons
Abstract
We present an algorithm for extracting and vectorizing objects in images with polygons. Departing from a polygonal partition that oversegments an image into convex cells, the algorithm refines the geometry of the partition while labeling its cells by a semantic class. The result is a set of polygons, each capturing an object in the image. The quality of a configuration is measured by an energy that accounts for both the fidelity to input data and the complexity of the output polygons. To efficiently explore the configuration space, we perform splitting and merging operations in tandem on the cells of the polygonal partition. The exploration mechanism is controlled by a priority queue that sorts the operations most likely to decrease the energy. We show the potential of our algorithm on different types of scenes, from organic shapes to man-made objects through floor maps, and demonstrate its efficiency compared to existing vectorization methods.
June 1, 2021
June 2, 2021
June 3, 2021
June 4, 2021
June 5, 2021
June 6, 2021
June 7, 2021
June 8, 2021
June 9, 2021
June 10, 2021
June 11, 2021
June 12, 2021
June 13, 2021
June 14, 2021
June 15, 2021
June 16, 2021
June 17, 2021
June 18, 2021
June 19, 2021
June 20, 2021
June 21, 2021
June 22, 2021
June 23, 2021
June 24, 2021
June 25, 2021
June 26, 2021
June 27, 2021
June 28, 2021
June 29, 2021
June 30, 2021
July 1, 2021
July 2, 2021
July 3, 2021
July 4, 2021
-
Calendar
June 2021 Monday Tuesday Wednesday Thursday Friday Saturday Sunday May 31, 2021 2:00 pm: PhD Seminars X
2:00 pm: PhD Seminars XMay 31, 2021 –
Talk 1
Speaker
Muxingzi Li (Titane)
Title
Approximating shapes in images with low-complexity polygons
Abstract
We present an algorithm for extracting and vectorizing objects in images with polygons. Departing from a polygonal partition that oversegments an image into convex cells, the algorithm refines the geometry of the partition while labeling its cells by a semantic class. The result is a set of polygons, each capturing an object in the image. The quality of a configuration is measured by an energy that accounts for both the fidelity to input data and the complexity of the output polygons. To efficiently explore the configuration space, we perform splitting and merging operations in tandem on the cells of the polygonal partition. The exploration mechanism is controlled by a priority queue that sorts the operations most likely to decrease the energy. We show the potential of our algorithm on different types of scenes, from organic shapes to man-made objects through floor maps, and demonstrate its efficiency compared to existing vectorization methods.
June 1, 2021 June 2, 2021 June 3, 2021 June 4, 2021 June 5, 2021 June 6, 2021 June 7, 2021 June 8, 2021 June 9, 2021 June 10, 2021 June 11, 2021 June 12, 2021 June 13, 2021 June 14, 2021 June 15, 2021 June 16, 2021 June 17, 2021 June 18, 2021 June 19, 2021 June 20, 2021 June 21, 2021 June 22, 2021 June 23, 2021 June 24, 2021 June 25, 2021 June 26, 2021 June 27, 2021 June 28, 2021 June 29, 2021 June 30, 2021 July 1, 2021 July 2, 2021 July 3, 2021 July 4, 2021
