Papers › PropagationNet: Propagate Points to Curve to Learn Structure Information
PropagationNet: Propagate Points to Curve to Learn Structure Information
Xiehe Huang, Weihong Deng, Haifeng Shen, Xiubao Zhang, Jieping Ye
Deep learning technique has dramatically boosted the performance of face alignment algorithms. However, due to large variability and lack of samples, the alignment problem in unconstrained situations, \emph{e.g}\onedot large head poses, exaggerated expression, and uneven illumination, is still largely unsolved. In this paper, we explore the instincts and reasons behind our two proposals, \emph{i.e}\onedot Propagation Module and Focal Wing Loss, to tackle the problem. Concretely, we present a novel structure-infused face alignment algorithm based on heatmap regression via propagating landmark heatmaps to boundary heatmaps, which provide structure information for further attention map generation. Moreover, we propose a Focal Wing Loss for mining and emphasizing the difficult samples under in-the-wild condition. In addition, we adopt methods like CoordConv and Anti-aliased CNN from other fields that address the shift-variance problem of CNN for face alignment. When implementing extensive experiments on different benchmarks, \emph{i.e}\onedot WFLW, 300W, and COFW, our method outperforms state-of-the-arts by a significant margin. Our proposed approach achieves 4.05\% mean error on WFLW, 2.93\% mean error on 300W full-set, and 3.71\% mean error on COFW.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
No code repository is listed for this paper in the archive or in Syntology's graph.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Face Alignment | 300W | PropNet | NME_inter-ocular (%, Challenge) | 3.99 | #7 of 48 | Archive leaderboard | report |
| Face Alignment | 300W | PropNet | NME_inter-ocular (%, Common) | 2.67 | #7 of 48 | Archive leaderboard | report |
| Face Alignment | 300W | PropNet | NME_inter-ocular (%, Full) | 2.93 | #7 of 48 | Archive leaderboard | report |
| Face Alignment | 300W | PropNet | NME_inter-pupil (%, Challenge) | 5.75 | #7 of 48 | Archive leaderboard | report |
| Face Alignment | 300W | PropNet | NME_inter-pupil (%, Common) | 3.7 | #7 of 48 | Archive leaderboard | report |
| Face Alignment | 300W | PropNet | NME_inter-pupil (%, Full) | 4.1 | #7 of 48 | Archive leaderboard | report |
| Face Alignment | COFW | PropNet | NME (inter-ocular) | 3.71% | #16 of 28 | Archive leaderboard | report |
| Face Alignment | WFLW | PropNet | AUC@10 (inter-ocular) | 61.58 | #4 of 36 | Archive leaderboard | report |
| Face Alignment | WFLW | PropNet | FR@10 (inter-ocular) | 2.96 | #4 of 36 | Archive leaderboard | report |
| Face Alignment | WFLW | PropNet | NME (inter-ocular) | 4.05 | #4 of 36 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Methods
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections