SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2005.10954 · 2020

Head2Head: Video-based Neural Head Synthesis

arXiv · PDF · Open in the Atlas

Code that ran

6 of 8 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; 1 failure of our instrument; 2 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/2005.10954.json · badge: /api/ran/2005.10954.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
michaildoukas/head2head community (classifier label)
classifier basis not recorded on the link
6 ran · 2 no recorded run
FunctionStatusWhere it lives
EPE Ran
ran, honoured the contract we drafted
michaildoukas/head2head/models/flownet2_pytorch/losses.py
pointer only (licence: MIT); the stored copy get_code serves, from Jia-Research-Lab/MSAD, is pointer only (licence: NONE) · get_code("6baff9bff3755d04")
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 Jia-Research-Lab/MSAD, 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.

define_D Ran
ran on a synthesized input
michaildoukas/head2head/models/networks.py
code served (permissive licence) · get_code("953a15dff017fbf8")
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 MultiscaleDiscriminator. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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 functools
import numpy as np

torch.manual_seed(0)

ARGS = {
    'input_nc': 3,
    'ndf': 64,
    'n_layers_D': 3,
    'norm': 'instance',
    'num_D': 3,
    'getIntermFeat': False,
    'is_image_discriminator': False,
    'gpu_ids': [],
    'opt': []
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type MultiscaleDiscriminator — a MultiscaleDiscriminator output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a MultiscaleDiscriminator 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
get_image_paths_dict Ran
ran on a synthesized input
michaildoukas/head2head/preprocessing/compute_distances.py
code served (permissive licence) · get_code("4fa005acc55069c6")
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 OrderedDict. 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 os
import tempfile
import shutil
import collections

# Create a temporary directory structure with the expected layout
temp_dir = tempfile.mkdtemp()

# Create subdirectories with 'real' and 'fake' folders
real_dir = os.path.join(temp_dir, 'real')
fake_dir = os.path.join(temp_dir, 'fake')

os.makedirs(real_dir, exist_ok=True)
os.makedirs(fake_dir, exist_ok=True)

# Create some dummy .png files in the real directory
for i in range(3):
    with open(os.path.join(real_dir, f'image_{i}.png'), 'w') as f:
        f.write('dummy')

# Create some dummy .png files in the fake directory
for i in range(2):
    with open(os.path.join(fake_dir, f'image_{i}.png'), 'w') as f:
        f.write('dummy')

# Create another subdirectory with real folder to test multiple sequences
real_dir2 = os.path.join(temp_dir, 'real_seq2')
os.makedirs(real_dir2, exist_ok=True)
for i in range(2):
    with open(os.path.join(real_dir2, f'image_{i}.png'), 'w') as f:
        f.write('dummy')

ARGS = {
    'dir': temp_dir
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type OrderedDict — a OrderedDict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a OrderedDict 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
get_norm_layer Ran
ran; our contract draft was wrong, not the code
michaildoukas/head2head/models/networks.py
pointer only (licence: MIT); the stored copy get_code serves, from VITA-Group/DeblurGANv2, is pointer only (licence: NOASSERTION) · get_code("b63de0bdabb1c981")
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 VITA-Group/DeblurGANv2, 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.

is_image_file Ran
ran, violated the contract we drafted
michaildoukas/head2head/preprocessing/compute_distances.py
code served (permissive licence) · get_code("70425fe6d8c34c2c")
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 bool, 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.

ARGS = {
    'filename': 'test_image.png'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type bool, 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
paths_exist Ran
ran on a synthesized input
michaildoukas/head2head/preprocessing/compute_distances.py
code served (permissive licence) · get_code("509c87da7b8ffd26")
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 bool, 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 os
import tempfile

# Create temporary files to use as valid paths
temp_dir = tempfile.mkdtemp()
temp_file1 = os.path.join(temp_dir, "image1.jpg")
temp_file2 = os.path.join(temp_dir, "image2.png")

# Create the actual files so they exist
open(temp_file1, 'w').close()
open(temp_file2, 'w').close()

ARGS = {
    "image_pths": [temp_file1, temp_file2]
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type bool, 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
create_model Not yet run
unverified (harvested, no recorded run)
michaildoukas/head2head/models/models.py
code served (permissive licence) · get_code("8fdccb27ab8f90bd")
How it ran

no invocation recorded.

define_G Not yet run
unverified (harvested, no recorded run)
michaildoukas/head2head/models/networks.py
code served (permissive licence) · get_code("48b827b4222dbf75")
How it ran

no invocation recorded.

Also present in other papers' code

Of 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 distinct functions with an identity, 3 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 3 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
is_image_file 62 other papers
14 dated earlier, 48 later
1609.04802 (2016-09)
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network
1703.07511 (2017-03)
Deep Photo Style Transfer
1710.10916 (2017-10)
StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial Networks
and 59 more not named here
EPE 2 other papers
2 later
2109.06875 (2021-09)
Multi-Scale Aligned Distillation for Low-Resolution Detection
2308.13133 (2023-08)
AccFlow: Backward Accumulation for Long-Range Optical Flow
get_norm_layer 1 other paper
1 later
2405.16749 (2024-05)
DMPlug: A Plug-in Method for Solving Inverse Problems with Diffusion Models

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

In this paper, we propose a novel machine learning architecture for facial reenactment. In particular, contrary to the model-based approaches or recent frame-based methods that use Deep Convolutional Neural Networks (DCNNs) to generate individual frames, we propose a novel method that (a) exploits the special structure of facial motion (paying particular attention to mouth motion) and (b) enforces temporal consistency. We demonstrate that the proposed method can transfer facial expressions, pose and gaze of a source actor to a target video in a photo-realistic fashion more accurately than state-of-the-art methods.

For agents

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

get_harvested_code_for_paper("2005.10954")
get_code_for_paper("2005.10954")
have("2005.10954")

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

curl https://syntology.ai/api/ran/2005.10954.json

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

[![Syntology run record](https://syntology.ai/api/ran/2005.10954.svg)](https://syntology.ai/paper/2005.10954)

Connect an agent — have() is free.