SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1904.03349 · 2019

Progressive Pose Attention Transfer for Person Image Generation

arXiv · PDF · Open in the Atlas

Code that ran

7 of 9 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, 0 violated it and 6 have no contract verdict; 0 failures 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/1904.03349.json · badge: /api/ran/1904.03349.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
tengteng95/Pose-Transfer canonical (classifier label)
classifier basis: census
7 ran · 2 no recorded run
FunctionStatusWhere it lives
addBounding Ran
ran on a synthesized input
tengteng95/Pose-Transfer/ssd_score/compute_ssd_score_fashion.py
code served (permissive licence) · get_code("60b258f4dc8a7d3d")
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 ndarray, ndim 3, dtype family int, shape (4, 85, 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 numpy as np

# Create a small test image with shape (height, width, channels)
# Using distinct dimensions: 4 height, 5 width, 3 channels (RGB)
image = np.random.randint(0, 256, size=(4, 5, 3), dtype=np.uint8)

ARGS = {
    "image": image,
    "bound": 40
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
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 3, dtype family int, shape (4, 85, 3) — shape (4, 85, 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
cords_to_map Ran
ran on a synthesized input
tengteng95/Pose-Transfer/tool/generate_pose_map_fashion.py
code served (permissive licence) · get_code("53d6f76c39c24dd4")
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 ndarray, ndim 3, dtype family int, shape (32, 48, 4) 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

MISSING_VALUE = -1

# Read the function signature and body
# Parameters: cords, img_size, sigma=6
# cords: array of points, shape (num_points, 2) with values or MISSING_VALUE
# img_size: tuple (height, width) for image dimensions
# sigma: float, gaussian parameter (has default value 6)

# Create small test data
cords = np.array([
    [10, 15],      # Valid point
    [5, 20],       # Valid point
    [MISSING_VALUE, MISSING_VALUE],  # Missing point (will be skipped)
    [8, 12]        # Valid point
], dtype=np.float32)

img_size = (32, 48)  # (height, width) - distinct dimensions

sigma = 6

ARGS = {
    'cords': cords,
    'img_size': img_size,
    'sigma': sigma
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
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 3, dtype family int, shape (32, 48, 4) — shape (32, 48, 4) 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
cords_to_map Ran
ran on a synthesized input
tengteng95/Pose-Transfer/tool/generate_pose_map_market.py
code served (permissive licence) · get_code("b1180deb4573e01e")
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 ndarray, ndim 3, dtype family float, shape (32, 48, 4) 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

MISSING_VALUE = -1

# Construct arguments for cords_to_map function
# Parameters: cords, img_size, sigma=6

# cords: array of coordinates with shape (num_points, 2)
# Each point is [y, x] coordinates
# Include some valid points and some with MISSING_VALUE
cords = np.array([
    [10.0, 15.0],      # valid point
    [20.0, 25.0],      # valid point
    [MISSING_VALUE, 30.0],  # missing y coordinate
    [5.0, MISSING_VALUE],   # missing x coordinate
], dtype='float32')

# img_size: tuple of (height, width) for the output map
img_size = (32, 48)

# sigma: standard deviation for gaussian kernel
sigma = 6

ARGS = {
    'cords': cords,
    'img_size': img_size,
    'sigma': sigma
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
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 3, dtype family float, shape (32, 48, 4) — shape (32, 48, 4) 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_norm_layer Ran
ran on a synthesized input
tengteng95/Pose-Transfer/models/networks.py
code served (permissive licence) · get_code("ce809996d1428958")
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 partial. 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 functools

torch.manual_seed(0)

# The function get_norm_layer takes one parameter: norm_type
# It returns a norm layer class or partial function based on the norm_type string
# Valid values are: 'batch', 'batch_sync', 'instance', 'none'
# We'll test with 'instance' as it's a straightforward case

ARGS = {
    'norm_type': 'instance'
}
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 partial — a partial output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a partial 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_scheduler Ran
ran on a synthesized input
tengteng95/Pose-Transfer/models/networks.py
code served (permissive licence) · get_code("f4ecb472fd266452")
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 LambdaLR. 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
from torch.optim import Adam

torch.manual_seed(0)

# Create a simple model
model = nn.Linear(4, 3)

# Create an optimizer
optimizer = Adam(model.parameters(), lr=0.001)

# Create a config object with all required attributes
class OptConfig:
    def __init__(self):
        self.lr_policy = 'lambda'
        self.epoch_count = 0
        self.niter = 100
        self.niter_decay = 100
        self.lr_decay_iters = 10

opt = OptConfig()

ARGS = {
    'optimizer': optimizer,
    'opt': opt
}
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 LambdaLR — a LambdaLR output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a LambdaLR 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
load_pose_cords_from_strings Ran
ran, honoured the contract we drafted
tengteng95/Pose-Transfer/tool/generate_pose_map_fashion.py
code served (permissive licence) · get_code("1fb3b75115e8317e")
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 ndarray, ndim 2, dtype family float, shape (4, 2) 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
import json

# The function expects two string parameters that contain JSON-encoded lists
# y_str and x_str are JSON strings representing coordinate arrays

# Create sample coordinate data
y_coords = [10.5, 20.3, 15.2, 25.1]
x_coords = [5.1, 15.4, 8.9, 18.7]

# Convert to JSON strings as the function expects
y_str = json.dumps(y_coords)
x_str = json.dumps(x_coords)

ARGS = {
    "y_str": y_str,
    "x_str": x_str,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
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 (4, 2) — shape (4, 2) 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
map_to_cord Ran
ran on a synthesized input
tengteng95/Pose-Transfer/tool/pose_utils.py
code served (permissive licence) · get_code("0a24cbfa899d5c09")
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 ndarray, ndim 2, dtype family int, shape (18, 2) 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 pose_map with shape (height, width, 18)
# The function expects:
# - A 3D array where last dimension is 18 (pose keypoints)
# - Some values above threshold to be detected as peaks
# - Each channel (z dimension) can have multiple peaks

height, width = 10, 12
pose_map = np.zeros((height, width, 18), dtype=np.float32)

# Add some peaks in different channels
# Channel 0: peak at (3, 2)
pose_map[2, 3, 0] = 0.5

# Channel 1: peak at (5, 4)
pose_map[4, 5, 1] = 0.7

# Channel 2: peak at (7, 6)
pose_map[6, 7, 2] = 0.3

# Channel 3: peak at (8, 9) with high value
pose_map[9, 8, 3] = 0.95

# Remaining channels get no peaks (will use MISSING_VALUE)
# Add some noise below threshold
pose_map += np.random.RandomState(42).uniform(0, 0.05, pose_map.shape)

threshold = 0.1

ARGS = {
    "pose_map": pose_map,
    "threshold": threshold
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
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 int, shape (18, 2) — shape (18, 2) 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)
tengteng95/Pose-Transfer/models/models.py
code served (permissive licence) · get_code("53aa5b40d1658f67")
How it ran

no invocation recorded.

get_inception_score Not yet run
unverified (harvested, no recorded run)
tengteng95/Pose-Transfer/tool/inception_score.py
code served (permissive licence) · get_code("ca6c3975c982ec08")
How it ran

no invocation recorded.

Also present in other papers' code

Of 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 distinct functions with an identity, 2 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 1 the same month, 2 later) and 7 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
get_scheduler 4 other papers
2 dated earlier, 1 the same month, 1 later
1611.07004 (2016-11)
Image-to-Image Translation with Conditional Adversarial Networks
1807.09251 (2018-07)
GANimation: Anatomically-aware Facial Animation from a Single Image
1904.10620 (2019-04)
Bidirectional Learning for Domain Adaptation of Semantic Segmentation
and 1 more not named here
load_pose_cords_from_strings 1 other paper
1 later
2402.18078 (2024-02)
Coarse-to-Fine Latent Diffusion for Pose-Guided Person Image Synthesis

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

This paper proposes a new generative adversarial network for pose transfer, i.e., transferring the pose of a given person to a target pose. The generator of the network comprises a sequence of Pose-Attentional Transfer Blocks that each transfers certain regions it attends to, generating the person image progressively. Compared with those in previous works, our generated person images possess better appearance consistency and shape consistency with the input images, thus significantly more realistic-looking. The efficacy and efficiency of the proposed network are validated both qualitatively and quantitatively on Market-1501 and DeepFashion. Furthermore, the proposed architecture can generate training images for person re-identification, alleviating data insufficiency. Codes and models are available at: https://github.com/tengteng95/Pose-Transfer.git.

For agents

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

get_harvested_code_for_paper("1904.03349")
get_code_for_paper("1904.03349")
have("1904.03349")

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

curl https://syntology.ai/api/ran/1904.03349.json

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

[![Syntology run record](https://syntology.ai/api/ran/1904.03349.svg)](https://syntology.ai/paper/1904.03349)

Connect an agent — have() is free.