Browse State-of-the-Art › Face Alignment

Face Alignment

106 papers with code · 26 benchmarks · 17 datasets archive 2025-07-28

Computer VisionMiscellaneousMusic

Face alignment is the task of identifying the geometric structure of faces in digital images, and attempting to obtain a canonical alignment of the face based on translation, scale, and rotation.

( Image credit: 3DDFA_V2 )

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

26 leaderboard tables shown for this task, 26 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted. 10 shown of 26 until expanded.

DatasetBest model (first row in archive order)PaperCodeSyntologyCompare
300W (48 rows) STAR STAR Loss: Reducing Semantic Ambiguity in Facial Landmark Detection code Syntology official (archive's flag): 4 ran · 4 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified Compare
WFLW (36 rows) SH-FAN Subpixel Heatmap Regression for Facial Landmark Localization — — Compare
COFW (28 rows) FiFA Fiducial Focus Augmentation for Facial Landmark Detection — — Compare
AFLW-19 (23 rows) FiFA Fiducial Focus Augmentation for Facial Landmark Detection — — Compare
AFLW2000-3D (14 rows) MNN+OR (reannotated) Multi-task head pose estimation in-the-wild code — Compare
WFW (Extra Data) (11 rows) SH-FAN Subpixel Heatmap Regression for Facial Landmark Localization — — Compare
300W Split 2 (7 rows) SPIGA Shape Preserving Facial Landmarks with Graph Attention Networks code — Compare
COFW-68 (7 rows) SPIGA Shape Preserving Facial Landmarks with Graph Attention Networks code — Compare
AFLW2000 (5 rows) MNN+ORB (Reannotated) Multi-task head pose estimation in-the-wild code — Compare
300W Split 2 (300W-LP) (4 rows) SH-FAN Subpixel Heatmap Regression for Facial Landmark Localization — — Compare
COFW-68 (300WLP) (4 rows) SH-FAN Subpixel Heatmap Regression for Facial Landmark Localization — — Compare
FaceScape (4 rows) ASM ASM: Adaptive Skinning Model for High-Quality 3D Face Modeling — — Compare
AFLW (3 rows) SynergyNet Synergy between 3DMM and 3D Landmarks for Accurate 3D Facial Geometry code — Compare
AFLW-LFPA (3 rows) FPN Joint 3D Face Reconstruction and Dense Alignment with Position Map... code Syntology official (archive's flag): 8 ran · 8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified Compare
300W (Common) (2 rows) SPIGA Shape Preserving Facial Landmarks with Graph Attention Networks code — Compare
AFLW-Full (2 rows) Binary Face Alignment Binarized Convolutional Landmark Localizers for Human Pose... code — Compare
IBUG (2 rows) DenseU-Net + Dual Transformer Stacked Dense U-Nets with Dual Transformers for Robust Face Alignment code — Compare
MERL-RAV (2 rows) SPIGA Shape Preserving Facial Landmarks with Graph Attention Networks code — Compare
300-VW (C) (1 row) 2D-FAN How far are we from solving the 2D & 3D Face Alignment problem?... code Syntology official (archive's flag): 12 ran · 14 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified Compare
3DFAW (1 row) 3D Face alignment Two-stage Convolutional Part Heatmap Regression for the 1st 3D... code — Compare
AFLW-PIFA (21 points) (1 row) Face alignment Convolutional aggregation of local evidence for large pose face alignment — — Compare
AFLW-PIFA (34 points) (1 row) Face alignment Convolutional aggregation of local evidence for large pose face alignment — — Compare
CelebA + AFLW Unaligned (1 row) Progressive Face SR Progressive Face Super-Resolution via Attention to Facial Landmark code — Compare
CelebA Aligned (1 row) Progressive Face SR Progressive Face Super-Resolution via Attention to Facial Landmark code — Compare
LS3D-W Balanced (1 row) 3D-FAN How far are we from solving the 2D & 3D Face Alignment problem?... code Syntology official (archive's flag): 12 ran · 14 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified Compare
Menpo (1 row) LUVLi LUVLi Face Alignment: Estimating Landmarks' Location, Uncertainty,... code — Compare

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. Each line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

17 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

No subtask under this task in the archive's task tree.

Parent tasks archive 2025-07-28

Papers archive 2025-07-28

archive papers tagged: 308 · with a code link: 106 · where Syntology ran a sample: 23 (21 with a run with no instrument failure, 2 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (23 of 308 tagged: 21 with a run with no instrument failure, 2 where every run was a failure of Syntology's instrument)

Page 1 of 4: papers 1 to 100 of 308, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.

Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.

Syntology lines on 23 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.

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