Papers › Towards Fast, Accurate and Stable 3D Dense Face Alignment

Towards Fast, Accurate and Stable 3D Dense Face Alignment

21 Sep 2020ECCV 2020 8arXiv:2009.09960archive 2025-07-28

Jianzhu Guo, Xiangyu Zhu, Yang Yang, Fan Yang, Zhen Lei, Stan Z. Li

Existing methods of 3D dense face alignment mainly concentrate on accuracy, thus limiting the scope of their practical applications. In this paper, we propose a novel regression framework named 3DDFA-V2 which makes a balance among speed, accuracy and stability. Firstly, on the basis of a lightweight backbone, we propose a meta-joint optimization strategy to dynamically regress a small set of 3DMM parameters, which greatly enhances speed and accuracy simultaneously. To further improve the stability on videos, we present a virtual synthesis method to transform one still image to a short-video which incorporates in-plane and out-of-plane face moving. On the premise of high accuracy and stability, 3DDFA-V2 runs at over 50fps on a single CPU core and outperforms other state-of-the-art heavy models simultaneously. Experiments on several challenging datasets validate the efficiency of our method. Pre-trained models and code are available at https://github.com/cleardusk/3DDFA_V2.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2009.09960")

Code

Syntology Ran 6 of 10 code samples harvested from 1 repository linked to this paper; 4 have no recorded run. Of those that ran: 1 ran · honoured contract; 1 ran · violated contract; 4 ran · our draft was wrong.

By repository: official repository: 7 samples from 1 repository, 4 ran; 3 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

cleardusk/3DDFA_V2 officialmentioned in paperpytorchMIT report
cleardusk/3DDFA mentioned in paperpytorch report
scoutant/face-blur mentioned on GitHubpytorch report

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

10 samples harvested; 6 ran; 1 honoured the contract we drafted; 4 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · honoured contract
1ran · violated contract
4ran · our draft was wrong
4unverified

Licence: 3 of the 10 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from cleardusk/3DDFA_V2. Some samples are identical code Syntology first harvested from another repository; for those, this paper's copy is not located and its licence is not recorded. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

conv3x3 cleardusk/3DDFA_V2/models/resnet.py official repository ran · our draft was wrong MIT (permissive) · fac5364e2f53c6db · report
conv_1x1_bn cleardusk/3DDFA_V2/models/mobilenet_v3.py official repository ran · our draft was wrong MIT (permissive) · db82a4013a44fb42 · report
conv_bn cleardusk/3DDFA_V2/models/mobilenet_v3.py official repository ran · our draft was wrong MIT (permissive) · 84a4cf301e929085 · report
make_divisible cleardusk/3DDFA_V2/models/mobilenet_v3.py official repository ran · honoured contract fingerprinted MIT (permissive) · 63ec083689f80f47 · report
mobilenet_075 cleardusk/3DDFA_V2/models/mobilenet_v1.py official repository unverified MIT (permissive) · 4f0e5b9aba541efe · report
mobilenet_1 cleardusk/3DDFA_V2/models/mobilenet_v1.py official repository unverified MIT (permissive) · 2e691025cd2d1017 · report
mobilenet_2 cleardusk/3DDFA_V2/models/mobilenet_v1.py official repository unverified MIT (permissive) · d3aea641fac06744 · report
P2sRt identical code first harvested elsewhere ran · our draft was wrong fingerprinted licence of this copy not recorded · 853c41eb4bb16d91 · report
matrix2angle identical code first harvested elsewhere ran · violated contract licence of this copy not recorded · 477c2dd5cc17773f · report
parse_pose identical code first harvested elsewhere unverified licence of this copy not recorded · 2144ad5b568bba67 · report

Tasks

3D Face Modelling3D Face ReconstructionFace AlignmentFace RecognitionFace Reconstruction

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Face Reconstruction AFLW2000-3D 3DDFA-V2 Mean NME 3.56% #4 of 8 Archive leaderboard report
3D Face Reconstruction Florence 3DDFA_V2 Mean NME 3.56 #16 of 16 Archive leaderboard report
3D Face Reconstruction NoW Benchmark 3DDFA_V2 Mean Reconstruction Error (mm) 1.57 #11 of 17 Archive leaderboard report
3D Face Reconstruction NoW Benchmark 3DDFA_V2 Median Reconstruction Error 1.23 #11 of 17 Archive leaderboard report
3D Face Reconstruction NoW Benchmark 3DDFA_V2 Stdev Reconstruction Error (mm) 1.39 #11 of 17 Archive leaderboard report
3D Face Reconstruction REALY 3DDFA-v2 @cheek 1.757 (±0.642) #13 of 24 Archive leaderboard report
3D Face Reconstruction REALY 3DDFA-v2 @forehead 2.447 (±0.647) #13 of 24 Archive leaderboard report
3D Face Reconstruction REALY 3DDFA-v2 @mouth 1.597 (±0.478) #13 of 24 Archive leaderboard report
3D Face Reconstruction REALY 3DDFA-v2 @nose 1.903 (±0.517) #13 of 24 Archive leaderboard report
3D Face Reconstruction REALY 3DDFA-v2 all 1.926 #13 of 24 Archive leaderboard report
3D Face Reconstruction REALY (side-view) 3DDFA-v2 @cheek 1.781 (±0.636) #9 of 19 Archive leaderboard report
3D Face Reconstruction REALY (side-view) 3DDFA-v2 @forehead 2.465 (±0.622) #9 of 19 Archive leaderboard report
3D Face Reconstruction REALY (side-view) 3DDFA-v2 @mouth 1.642 (±0.501) #9 of 19 Archive leaderboard report
3D Face Reconstruction REALY (side-view) 3DDFA-v2 @nose 1.883 (±0.499) #9 of 19 Archive leaderboard report
3D Face Reconstruction REALY (side-view) 3DDFA-v2 all 1.943 #9 of 19 Archive leaderboard report
3D Face Reconstruction Stirling-HQ (FG2018 3D face reconstruction challenge) 3DDFA_V2 Mean Reconstruction Error (mm) 1.91 #2 of 4 Archive leaderboard report
3D Face Reconstruction Stirling-LQ (FG2018 3D face reconstruction challenge) 3DDFA_V2 Mean Reconstruction Error (mm) 2.10 #3 of 4 Archive leaderboard report
Face Alignment AFLW 3DDFA_V2 Mean NME 4.43 #2 of 3 Archive leaderboard report
Face Alignment AFLW2000-3D 3DDFA_V2 Balanced NME (2D Sparse Alignment) 3.51% #6 of 14 Archive leaderboard report
Face Alignment AFLW2000-3D 3DDFA_V2 Mean NME(3D Dense Alignment) 4.18% #6 of 14 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

1x1 ConvolutionAverage PoolingBatch NormalizationConvolutionDense ConnectionsDepthwise ConvolutionDepthwise Separable ConvolutionGlobal Average PoolingMobileNetV1Pointwise ConvolutionReLUSoftmax

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