Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Edge-aware Graph Representation Learning and Reasoning for Face Parsing

About

Face parsing infers a pixel-wise label to each facial component, which has drawn much attention recently. Previous methods have shown their efficiency in face parsing, which however overlook the correlation among different face regions. The correlation is a critical clue about the facial appearance, pose, expression etc., and should be taken into account for face parsing. To this end, we propose to model and reason the region-wise relations by learning graph representations, and leverage the edge information between regions for optimized abstraction. Specifically, we encode a facial image onto a global graph representation where a collection of pixels ("regions") with similar features are projected to each vertex. Our model learns and reasons over relations between the regions by propagating information across vertices on the graph. Furthermore, we incorporate the edge information to aggregate the pixel-wise features onto vertices, which emphasizes on the features around edges for fine segmentation along edges. The finally learned graph representation is projected back to pixel grids for parsing. Experiments demonstrate that our model outperforms state-of-the-art methods on the widely used Helen dataset, and also exhibits the superior performance on the large-scale CelebAMask-HQ and LaPa dataset. The code is available at https://github.com/tegusi/EAGRNet.

Gusi Te, Yinglu Liu, Wei Hu, Hailin Shi, Tao Mei• 2020

Related benchmarks

TaskDatasetResultRank
Face ParsingLaPa (test)
Skin Accuracy97.3
39
Face ParsingCelebAMask-HQ
Nose Accuracy0.94
28
Face ParsingHelen (test)
Eyes Accuracy0.902
22
Face ParsingCelebAMask-HQ (test)
Face F196.2
9
Face ParsingLaPa--
7
Face ParsingHelen
Nose Accuracy96.1
6
Face ParsingCelebAMask-HQ v1 (test)
Face F196.2
5
Showing 7 of 7 rows

Other info

Code

Follow for update