SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2009.09960 · 2020

Towards Fast, Accurate and Stable 3D Dense Face Alignment

arXiv · PDF · Open in the Atlas

Code that ran

9 of 10 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 1 violated it and 3 have no contract verdict; 4 failures of our instrument; 1 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2009.09960.json · badge: /api/ran/2009.09960.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
cleardusk/3DDFA_V2 canonical (classifier label)
classifier basis: census
7 ran · 0 no recorded run
copy not recorded community
not in the paper's declared repositories
2 ran · 1 no recorded run
FunctionStatusWhere it lives
P2sRt Ran
ran; our contract draft was wrong, not the code
this paper's copy was not recorded; identical code first harvested from cleardusk/3DDFA
pointer only · get_code("853c41eb4bb16d91")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

conv3x3 Ran
ran; our contract draft was wrong, not the code
cleardusk/3DDFA_V2/models/resnet.py
pointer only (licence: MIT); the stored copy get_code serves, from lixiaotong97/DSU, is pointer only (licence: NONE) · get_code("fac5364e2f53c6db")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from lixiaotong97/DSU, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

conv_1x1_bn Ran
ran; our contract draft was wrong, not the code
cleardusk/3DDFA_V2/models/mobilenet_v3.py
pointer only (licence: MIT); the stored copy get_code serves, from chris-boson/fashion_mnist, is pointer only (licence: NONE) · get_code("db82a4013a44fb42")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from chris-boson/fashion_mnist, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

conv_bn Ran
ran; our contract draft was wrong, not the code
cleardusk/3DDFA_V2/models/mobilenet_v3.py
pointer only (licence: MIT); the stored copy get_code serves, from chris-boson/fashion_mnist, is pointer only (licence: NONE) · get_code("84a4cf301e929085")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from chris-boson/fashion_mnist, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

make_divisible Ran
ran, honoured the contract we drafted
cleardusk/3DDFA_V2/models/mobilenet_v3.py
pointer only (licence: MIT); the stored copy get_code serves, from chris-boson/fashion_mnist, is pointer only (licence: NONE) · get_code("63ec083689f80f47")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from chris-boson/fashion_mnist, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

matrix2angle Ran
ran, violated the contract we drafted
this paper's copy was not recorded; identical code first harvested from cleardusk/3DDFA
pointer only · get_code("477c2dd5cc17773f")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

mobilenet_075 Ran
ran on a synthesized input
cleardusk/3DDFA_V2/models/mobilenet_v1.py
code served (permissive licence) · get_code("4f0e5b9aba541efe")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned MobileNet. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn
import math

torch.manual_seed(0)

ARGS = {
    "num_classes": 62,
    "input_channel": 3,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type MobileNet — a MobileNet output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a MobileNet output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
mobilenet_1 Ran
ran on a synthesized input
cleardusk/3DDFA_V2/models/mobilenet_v1.py
code served (permissive licence) · get_code("2e691025cd2d1017")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned MobileNet. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn
import math

torch.manual_seed(0)

ARGS = {
    "num_classes": 62,
    "input_channel": 3,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type MobileNet — a MobileNet output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a MobileNet output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
mobilenet_2 Ran
ran on a synthesized input
cleardusk/3DDFA_V2/models/mobilenet_v1.py
code served (permissive licence) · get_code("d3aea641fac06744")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned MobileNet. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn
import math

torch.manual_seed(0)

ARGS = {
    "num_classes": 62,
    "input_channel": 3,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type MobileNet — a MobileNet output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a MobileNet output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
parse_pose Not yet run
unverified (harvested, no recorded run)
this paper's copy was not recorded; identical code first harvested from cleardusk/3DDFA
pointer only · get_code("2144ad5b568bba67")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 10 distinct functions with an identity, 9 are also present in other papers whose code we hold (9 with at least one paper dated earlier, 2 the same month, 3 later) and 1 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
conv3x3 686 other papers
257 dated earlier, 3 the same month, 425 later, 1 same year, order not determinable · 31 only as an assembly brick
1406.2661 (2014-06)
Generative Adversarial Networks
1409.0575 (2014-09)
ImageNet Large Scale Visual Recognition Challenge
1412.6572 (2014-12)
Explaining and Harnessing Adversarial Examples
and 683 more not named here
make_divisible 12 other papers
9 dated earlier, 1 the same month, 2 later · 1 only as an assembly brick
1503.03832 (2015-03)
FaceNet: A Unified Embedding for Face Recognition and Clustering
1801.04381 (2018-01)
MobileNetV2: Inverted Residuals and Linear Bottlenecks
1811.08383 (2018-11)
TSM: Temporal Shift Module for Efficient Video Understanding
and 9 more not named here
conv_1x1_bn 4 other papers
4 dated earlier
1503.03832 (2015-03)
FaceNet: A Unified Embedding for Face Recognition and Clustering
1812.00332 (2018-12)
ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware
1905.02244 (2019-05)
Searching for MobileNetV3
and 1 more not named here
conv_bn 4 other papers
3 dated earlier, 1 later
1503.03832 (2015-03)
FaceNet: A Unified Embedding for Face Recognition and Clustering
1905.02244 (2019-05)
Searching for MobileNetV3
2001.00705 (2020-01)
Fractional Skipping: Towards Finer-Grained Dynamic CNN Inference
and 1 more not named here
P2sRt 1 other paper
1 dated earlier
1804.01005 (2018-04)
Face Alignment in Full Pose Range: A 3D Total Solution
matrix2angle 1 other paper
1 dated earlier
1804.01005 (2018-04)
Face Alignment in Full Pose Range: A 3D Total Solution
mobilenet_1 1 other paper
1 dated earlier
1807.09951 (2018-07)
Learning to Forecast and Refine Residual Motion for Image-to-Video Generation
mobilenet_2 1 other paper
1 dated earlier
1807.09951 (2018-07)
Learning to Forecast and Refine Residual Motion for Image-to-Video Generation
parse_pose 1 other paper
1 dated earlier
1804.01005 (2018-04)
Face Alignment in Full Pose Range: A 3D Total Solution

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

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.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2009.09960")
get_code_for_paper("2009.09960")
have("2009.09960")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2009.09960.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2009.09960.svg)](https://syntology.ai/paper/2009.09960)

Connect an agent — have() is free.