Papers › Sparse Local Patch Transformer for Robust Face Alignment and Landmarks Inherent...
Sparse Local Patch Transformer for Robust Face Alignment and Landmarks Inherent Relation Learning
Jiahao Xia, Weiwei qu, Wenjian Huang, JianGuo Zhang, Xi Wang, Min Xu
Heatmap regression methods have dominated face alignment area in recent years while they ignore the inherent relation between different landmarks. In this paper, we propose a Sparse Local Patch Transformer (SLPT) for learning the inherent relation. The SLPT generates the representation of each single landmark from a local patch and aggregates them by an adaptive inherent relation based on the attention mechanism. The subpixel coordinate of each landmark is predicted independently based on the aggregated feature. Moreover, a coarse-to-fine framework is further introduced to incorporate with the SLPT, which enables the initial landmarks to gradually converge to the target facial landmarks using fine-grained features from dynamically resized local patches. Extensive experiments carried out on three popular benchmarks, including WFLW, 300W and COFW, demonstrate that the proposed method works at the state-of-the-art level with much less computational complexity by learning the inherent relation between facial landmarks. The code is available at the project website.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
1 archive task tag without a task page not shown.
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Face Alignment | 300W | SLPT | NME_inter-ocular (%, Challenge) | 4.90 | #17 of 48 | Archive leaderboard | report |
| Face Alignment | 300W | SLPT | NME_inter-ocular (%, Common) | 2.75 | #17 of 48 | Archive leaderboard | report |
| Face Alignment | 300W | SLPT | NME_inter-ocular (%, Full) | 3.17 | #17 of 48 | Archive leaderboard | report |
| Face Alignment | COFW | SLPT | NME (inter-ocular) | 3.32 | #9 of 28 | Archive leaderboard | report |
| Face Alignment | COFW | SLPT | NME (inter-pupil) | 4.79 | #9 of 28 | Archive leaderboard | report |
| Face Alignment | COFW-68 | SPLT | NME (inter-ocular) | 4.10 | #2 of 7 | Archive leaderboard | report |
| Face Alignment | WFLW | SLPT | AUC@10 (inter-ocular) | 59.5 | #10 of 36 | Archive leaderboard | report |
| Face Alignment | WFLW | SLPT | FR@10 (inter-ocular) | 2.76 | #10 of 36 | Archive leaderboard | report |
| Face Alignment | WFLW | SLPT | NME (inter-ocular) | 4.14 | #10 of 36 | Archive leaderboard | report |
| Face Alignment | WFW (Extra Data) | SPLT | AUC@10 (inter-ocular) | 59.50 | #6 of 11 | Archive leaderboard | report |
| Face Alignment | WFW (Extra Data) | SPLT | FR@10 (inter-ocular) | 2.76 | #6 of 11 | Archive leaderboard | report |
| Face Alignment | WFW (Extra Data) | SPLT | NME (inter-ocular) | 4.14 | #6 of 11 | 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