SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2107.07437 · 2021

StyleFusion: A Generative Model for Disentangling Spatial Segments

arXiv · PDF · Open in the Atlas

Code that ran

1 of 1 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; 1 failure 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/2107.07437.json · badge: /api/ran/2107.07437.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
OmerKafri/StyleFusion canonical (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
FunctionStatusWhere it lives
tensor2im Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
OmerKafri/StyleFusion/style_fusion_simple.py
code served (permissive licence) · get_code("4fdffb935fa35cee")
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 Image. 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
from PIL import Image

torch.manual_seed(0)

# The function expects a tensor with shape (C, H, W) after the transposes
# It performs: transpose(0, 2) then transpose(0, 1)
# If input is (batch, H, W, C), after transpose(0, 2) it becomes (C, H, W, batch)
# After transpose(0, 1) it becomes (H, W, C, batch) - this doesn't match
# 
# More likely input is (batch, C, H, W):
# After transpose(0, 2) it becomes (H, C, W, batch)
# After transpose(0, 1) it becomes (C, H, W, batch) - still not right
#
# Actually, let's think of it as needing to end up with (H, W, C) for Image.fromarray
# Starting with shape that after two transposes gives (H, W, C)
# If we have (C, H, W) and do transpose(0, 2) -> (W, H, C)
# Then transpose(0, 1) -> (H, W, C) ✓
# 
# So the input tensor should be (C, H, W) format, or more generally
# a 3D tensor where after those ops we get (H, W, C)

# Create a small 3D tensor: (C=3, H=4, W=5)
# Values in range [-1, 1] to match the (var + 1) / 2 normalization
var = torch.randn(3, 4, 5) * 0.5  # values roughly in [-1, 1]

ARGS = {
    "var": var
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Image — a Image output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Image output the recorded ndim 3 and dtype family int 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

Also present in other papers' code

Of 1 samples lifted from this paper's linked repositories, 1 carry a function identity and 0 do not. Of the 1 distinct functions with an identity, 1 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 1 later) and 0 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
tensor2im 1 other paper
1 later
2502.13987 (2025-02)
SelfAge: Personalized Facial Age Transformation Using Self-reference Images

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

We present StyleFusion, a new mapping architecture for StyleGAN, which takes as input a number of latent codes and fuses them into a single style code. Inserting the resulting style code into a pre-trained StyleGAN generator results in a single harmonized image in which each semantic region is controlled by one of the input latent codes. Effectively, StyleFusion yields a disentangled representation of the image, providing fine-grained control over each region of the generated image. Moreover, to help facilitate global control over the generated image, a special input latent code is incorporated into the fused representation. StyleFusion operates in a hierarchical manner, where each level is tasked with learning to disentangle a pair of image regions (e.g., the car body and wheels). The resulting learned disentanglement allows one to modify both local, fine-grained semantics (e.g., facial features) as well as more global features (e.g., pose and background), providing improved flexibility in the synthesis process. As a natural extension, StyleFusion enables one to perform semantically-aware cross-image mixing of regions that are not necessarily aligned. Finally, we demonstrate how StyleFusion can be paired with existing editing techniques to more faithfully constrain the edit to the user's region of interest.

For agents

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

get_harvested_code_for_paper("2107.07437")
get_code_for_paper("2107.07437")
have("2107.07437")

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

curl https://syntology.ai/api/ran/2107.07437.json

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

[![Syntology run record](https://syntology.ai/api/ran/2107.07437.svg)](https://syntology.ai/paper/2107.07437)

Connect an agent — have() is free.