Datasets › REALY
REALY (Region-aware benchmark based on the LYHM)
The REALY benchmark aims to introduce a region-aware evaluation pipeline to measure the fine-grained normalized mean square error (NMSE) of 3D face reconstruction methods from under-controlled image sets.
Given the reconstructed mesh from the 2D image in REALY by a specific method, the REALY benchmark calculates the similarity of ground-truth scans on four regions (nose, mouth, forehead, cheek) with the predicted mesh.
Benchmarks archive 2025-07-28
All 2 leaderboards whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.
| First row (archive order) | Paper | Code | ||||
|---|---|---|---|---|---|---|
| 3D Face Reconstruction | REALY | HiFace-f all 1.275 | HiFace: High-Fidelity 3D Face Reconstruction by Learning... | — | 24 | Compare |
| 3D Face Reconstruction | REALY (side-view) | HiFace-f all 1.308 | HiFace: High-Fidelity 3D Face Reconstruction by Learning... | — | 19 | Compare |
Papers archive 2025-07-28
21 shown of 21 papers with a leaderboard row on this dataset's benchmarks, newest first. The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset; the archive's count for this dataset is 24. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.
Dataset loaders archive 2025-07-28
1 loader as listed in the archive; links are outbound and not re-checked here.
Tasks archive 2025-07-28
License archive 2025-07-28
Modalities archive 2025-07-28
Languages archive 2025-07-28
Variants archive 2025-07-28
- REALY
- REALY (side-view)
2 variant names, as the archive lists them.
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