SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2203.14057 · CVPR · 2022

FaceVerse: a Fine-grained and Detail-controllable 3D Face Morphable Model from a Hybrid Dataset

Tao Yu, Zhiyuan Chen, Liang Li, Yebin Liu, Chenguang Ma, Lizhen Wang

arXiv · PDF · Open in the Atlas

Code that ran

5 of 6 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; 0 honoured the contract we drafted, 1 violated it and 4 have no contract verdict; 0 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/2203.14057.json · badge: /api/ran/2203.14057.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
lizhenwangt/faceverse canonical (classifier label)
classifier basis not recorded on the link
5 ran · 1 no recorded run
FunctionStatusWhere it lives
get_l2 Ran
ran on a synthesized input
lizhenwangt/faceverse/faceversev3_jittor/faceverse_cuda/losses.py
code served (permissive licence) · get_code("da86f0dd69458f13")
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 Tensor, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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

torch.manual_seed(0)

# The function get_l2 takes a tensor and returns the sum of squares
# It uses .pow(2) and .sum() methods on the tensor
# We need to provide a valid torch tensor as the argument

tensor = torch.randn(2, 4)

ARGS = {
    "tensor": tensor
}
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 Tensor, ndim 0, dtype family float, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
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
get_lm_weights Ran
ran on a synthesized input
lizhenwangt/faceverse/model/losses.py
code served (permissive licence) · get_code("6da2645761e5216b")
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 Tensor, ndim 1, dtype family float, shape (66,) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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

torch.manual_seed(0)

# The function get_lm_weights takes a device parameter
# It creates a tensor, modifies it, normalizes it, and returns it
# We need to pass a valid torch device

device = torch.device('cpu')

ARGS = {
    'device': device
}
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 Tensor, ndim 1, dtype family float, shape (66,) — shape (66,) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
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
init_optim_with_id Ran
ran on a synthesized input
lizhenwangt/faceverse/fit_images.py
code served (permissive licence) · get_code("51092b816d483dcc")
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 tuple, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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

torch.manual_seed(0)

class MockFaceVerseModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.rot = nn.Parameter(torch.randn(3))
        self.trans = nn.Parameter(torch.randn(2))
        self.id = nn.Parameter(torch.randn(4))
        self.exp = nn.Parameter(torch.randn(5))
        self.gamma = nn.Parameter(torch.randn(6))
        self.tex = nn.Parameter(torch.randn(7))
    
    def get_rot_tensor(self):
        return self.rot
    
    def get_trans_tensor(self):
        return self.trans
    
    def get_id_tensor(self):
        return self.id
    
    def get_exp_tensor(self):
        return self.exp
    
    def get_gamma_tensor(self):
        return self.gamma
    
    def get_tex_tensor(self):
        return self.tex

class Args:
    def __init__(self):
        self.rf_lr = 0.001
        self.nrf_lr = 0.0005

ARGS = {
    "args": Args(),
    "faceverse_model": MockFaceVerseModel()
}
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 tuple, ndim 1, dtype family float — a tuple output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
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
lm_loss Ran
ran on a synthesized input
lizhenwangt/faceverse/model/losses.py
code served (permissive licence) · get_code("0442c536a4eefcee")
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 Tensor, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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

torch.manual_seed(0)

# Construct arguments for lm_loss function
# pred_lms: predicted landmarks, shape (batch_size, num_landmarks, 2)
# gt_lms: ground truth landmarks, shape (batch_size, num_landmarks, 2)
# weight: weights for each landmark, shape (num_landmarks,)
# img_size: image size (default 224)

batch_size = 2
num_landmarks = 4
img_size = 224

# Create pred_lms tensor: (batch=2, landmarks=4, coords=2)
pred_lms = torch.randn(batch_size, num_landmarks, 2) * 100

# Create gt_lms tensor: (batch=2, landmarks=4, coords=2)
gt_lms = torch.randn(batch_size, num_landmarks, 2) * 100

# Create weight tensor: (landmarks=4,)
weight = torch.ones(num_landmarks)

ARGS = {
    'pred_lms': pred_lms,
    'gt_lms': gt_lms,
    'weight': weight,
    'img_size': img_size
}
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 Tensor, ndim 0, dtype family float, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
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
make_kernel Ran
ran, violated the contract we drafted
lizhenwangt/faceverse/network.py
pointer only (licence: BSD-2-Clause); the stored copy get_code serves, from dkn16/multi-fidel-gan-21cm, is pointer only (licence: NOASSERTION) · get_code("6f65e378a4313f87")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (BSD-2-Clause), but get_code serves the stored copy, first harvested from dkn16/multi-fidel-gan-21cm, and GitHub could not classify the licence of that repository (NOASSERTION). 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.

photo_loss Not yet run
unverified (harvested, no recorded run)
lizhenwangt/faceverse/model/losses.py
code served (permissive licence) · get_code("6adbc885322a47af")
How it ran

no invocation recorded.

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 1 the same month, 1 later) and 5 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
make_kernel 40 other papers
19 dated earlier, 4 the same month, 17 later · 10 only as an assembly brick
1812.04948 (2018-12)
A Style-Based Generator Architecture for Generative Adversarial Networks
1912.04958 (2019-12)
Analyzing and Improving the Image Quality of StyleGAN
2007.06600 (2020-07)
Closed-Form Factorization of Latent Semantics in GANs
and 37 more not named here

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

Figure 1. Our hybrid dataset, the base and detail model of FaceVerse, as well as our single-image fitting result.

For agents

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

get_harvested_code_for_paper("2203.14057")
get_code_for_paper("2203.14057")
have("2203.14057")

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

curl https://syntology.ai/api/ran/2203.14057.json

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

[![Syntology run record](https://syntology.ai/api/ran/2203.14057.svg)](https://syntology.ai/paper/2203.14057)

Connect an agent — have() is free.