</> Code with Papers by Syntology

Datasets › NoW Benchmark

NoW Benchmark

Introduced by Soubhik Sanyal et al. in Learning to Regress 3D Face Shape and Expression from an Image without 3D Supervision16 May 2019 archive 2025-07-28

The goal of this benchmark is to introduce a standard evaluation metric to measure the accuracy and robustness of 3D face reconstruction methods under variations in viewing angle, lighting, and common occlusions.

The dataset contains 2054 2D images of 100 subjects, captured with an iPhone X, and a separate 3D head scan for each subject. This head scan serves as ground truth for the evaluation. The subjects are selected to contain variations in age, BMI, and sex (55 female, 45 male).

HomepageBenchmarksPapers JSON

Benchmarks archive 2025-07-28

All 1 leaderboard 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)PaperCode
3D Face Reconstruction NoW Benchmark DenseLandmarks (Multi-view) Median Reconstruction Error 0.81 3D face reconstruction with dense landmarks — 17 Compare

Papers archive 2025-07-28

15 shown of 15 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 27. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.

DateSamples run Syntology
Towards Metrical Reconstruction of Human Faces 1 1 13 Apr 2022 not harvested
3D face reconstruction with dense landmarks 0 2 6 Apr 2022 not harvested
Synergy between 3DMM and 3D Landmarks for Accurate 3D Facial Geometry 4 1 19 Oct 2021 not harvested
Robust Model-based Face Reconstruction through Weakly-Supervised Outlier Segmentation 1 1 17 Jun 2021 not harvested
Collaborative Regression of Expressive Bodies using Moderation 1 1 11 May 2021 not harvested
Towards High Fidelity Monocular Face Reconstruction with Rich Reflectance using Self-supervised Learning and Ray Tracing 0 1 29 Mar 2021 not harvested
Learning an Animatable Detailed 3D Face Model from In-The-Wild Images 2 1 7 Dec 2020 not harvested
Towards Fast, Accurate and Stable 3D Dense Face Alignment 3 1 21 Sep 2020 ran 6 of 10 samples (4 unverified; 3 pointer-only for licence)
“Look Ma, no landmarks!” – Unsupervised, Model-based Dense Face Alignment 1 1 1 Aug 2020 not harvested
Self-Supervised Monocular 3D Face Reconstruction by Occlusion-Aware Multi-view Geometry Consistency 1 1 24 Jul 2020 ran 0 of 16 samples (16 unverified)
Learning to Regress 3D Face Shape and Expression from an Image without 3D Supervision 2 1 16 May 2019 ran 0 of 6 samples (6 unverified)
Accurate 3D Face Reconstruction with Weakly-Supervised Learning: From Single Image to Image Set 4 2 20 Mar 2019 ran 11 of 36 samples (25 unverified)
Joint 3D Face Reconstruction and Dense Alignment with Position Map Regression Network 4 1 21 Mar 2018 ran 0 of 10 samples (10 unverified)
Learning a model of facial shape and expression from 4D scans 9 1 1 Nov 2017 not harvested
Regressing Robust and Discriminative 3D Morphable Models with a very Deep Neural Network 5 1 15 Dec 2016 not harvested

Dataset loaders archive 2025-07-28

soubhiksanyal/now_evaluation

1 loader as listed in the archive; links are outbound and not re-checked here.

Tasks archive 2025-07-28

3D Face Reconstruction

License archive 2025-07-28

Custom

Modalities archive 2025-07-28

Images3d meshes

Languages archive 2025-07-28

No language tagged.

Variants archive 2025-07-28

  • NoW Benchmark

1 variant name, 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