SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2009.00149 · 2020

GIF: Generative Interpretable Faces

arXiv · PDF · Open in the Atlas

Code that ran

2 of 2 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, 0 violated it and 0 have no contract verdict; 2 failures of our instrument; 0 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/2009.00149.json · badge: /api/ran/2009.00149.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
ParthaEth/GIF canonical (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
FunctionStatusWhere it lives
corrupt_flame_given_sigma Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
ParthaEth/GIF/plots/generate_random_samples.py
code served (permissive licence) · get_code("487131cc50d6ed1e")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned ndarray, ndim 2, dtype family float, shape (2, 236) 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 numpy as np

# Create a small flm_params array for testing
num_smpl_to_eval_on = 2
code_size = 236
flm_params = np.zeros((num_smpl_to_eval_on, code_size)).astype('float32')

# Set some non-zero values in the relevant indices to make testing meaningful
flm_params[:, :10] = np.random.randn(num_smpl_to_eval_on, 10).astype('float32')  # shape params
flm_params[:, 100:110] = np.random.randn(num_smpl_to_eval_on, 10).astype('float32')  # exp_jaw params
flm_params[:, 151] = np.random.randn(num_smpl_to_eval_on).astype('float32')  # pose param
flm_params[:, 153] = np.random.randn(num_smpl_to_eval_on).astype('float32')  # jaw param

ARGS = {
    'flm_params': flm_params,
    'corruption_type': 'all',
    'sigma': 0.1,
    'jaw_sigma': 0.05,
    'pose_sigma': 0.02
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 2, dtype family float, shape (2, 236) — shape (2, 236) 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
ge_gen_in Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
ParthaEth/GIF/plots/generate_random_samples.py
code served (permissive licence) · get_code("a0a5450b8d5f8ada")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned Tensor, ndim 4, dtype family float, shape (2, 8, 4, 3) 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
import numpy as np

torch.manual_seed(0)

num_smpl_to_eval_on = 128
code_size = 236

# flm_params: shape (num_smpl_to_eval_on, code_size)
flm_params = np.zeros((num_smpl_to_eval_on, code_size)).astype('float32')

# textured_rndr: a tensor with some channels (e.g., 3 for RGB)
# Using batch size 2 for tiny test
batch_size = 2
height = 4
width = 3
texture_channels = 3
normal_channels = 5  # distinct from texture_channels

textured_rndr = torch.randn(batch_size, texture_channels, height, width)

# norm_map: a tensor with different number of channels (e.g., 3 for normal vectors)
norm_map = torch.randn(batch_size, normal_channels, height, width)

# normal_map_cond: boolean flag
normal_map_cond = True

# texture_cond: boolean flag
texture_cond = True

ARGS = {
    'flm_params': flm_params,
    'textured_rndr': textured_rndr,
    'norm_map': norm_map,
    'normal_map_cond': normal_map_cond,
    'texture_cond': texture_cond
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 4, dtype family float, shape (2, 8, 4, 3) — shape (2, 8, 4, 3) 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

Also present in other papers' code

Of 2 samples lifted from this paper's linked repositories, 2 carry a function identity and 0 do not. Of the 2 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 2 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.

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

Photo-realistic visualization and animation of expressive human faces have been a long standing challenge. 3D face modeling methods provide parametric control but generates unrealistic images, on the other hand, generative 2D models like GANs (Generative Adversarial Networks) output photo-realistic face images, but lack explicit control. Recent methods gain partial control, either by attempting to disentangle different factors in an unsupervised manner, or by adding control post hoc to a pre-trained model. Unconditional GANs, however, may entangle factors that are hard to undo later. We condition our generative model on pre-defined control parameters to encourage disentanglement in the generation process. Specifically, we condition StyleGAN2 on FLAME, a generative 3D face model. While conditioning on FLAME parameters yields unsatisfactory results, we find that conditioning on rendered FLAME geometry and photometric details works well. This gives us a generative 2D face model named GIF (Generative Interpretable Faces) that offers FLAME's parametric control. Here, interpretable refers to the semantic meaning of different parameters. Given FLAME parameters for shape, pose, expressions, parameters for appearance, lighting, and an additional style vector, GIF outputs photo-realistic face images. We perform an AMT based perceptual study to quantitatively and qualitatively evaluate how well GIF follows its conditioning. The code, data, and trained model are publicly available for research purposes at http://gif.is.tue.mpg.de.

For agents

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

get_harvested_code_for_paper("2009.00149")
get_code_for_paper("2009.00149")
have("2009.00149")

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

curl https://syntology.ai/api/ran/2009.00149.json

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

[![Syntology run record](https://syntology.ai/api/ran/2009.00149.svg)](https://syntology.ai/paper/2009.00149)

Connect an agent — have() is free.