SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2203.02104 · CVPR · 2022

Interactive Image Synthesis with Panoptic Layout Generation

Bo Wang, Tao Wu, Minfeng Zhu, Peng Du

arXiv · PDF · Open in the Atlas

Code that ran

5 of 11 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 5 have no contract verdict; 0 failures of our instrument; 6 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/2203.02104.json · badge: /api/ran/2203.02104.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
wb-finalking/PLGAN canonical (classifier label)
classifier basis not recorded on the link
5 ran · 6 no recorded run
FunctionStatusWhere it lives
clip_grad_value_ Ran
ran on a synthesized input
wb-finalking/PLGAN/train_cal2i.py
code served (permissive licence) · get_code("a119b0fda85b80cb")
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 torch

torch.manual_seed(0)

# Create a single parameter tensor with gradient
param1 = torch.randn(2, 4, requires_grad=True)
param1.grad = torch.randn(2, 4)

# Create another parameter tensor with gradient
param2 = torch.randn(3, 5, requires_grad=True)
param2.grad = torch.randn(3, 5)

# Create a parameter tensor with None gradient
param3 = torch.randn(2, 3, requires_grad=True)

# Test with iterable of parameters
parameters_list = [param1, param2, param3]

# Define clip_value
clip_value = 1.0

ARGS = {
    "parameters": parameters_list,
    "clip_value": clip_value
}
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 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
constrait Ran
ran on a synthesized input
wb-finalking/PLGAN/eval_cal2i.py
code served (permissive licence) · get_code("959a3c7666581486")
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 int, ndim 0, dtype family int, 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
import numpy as np

torch.manual_seed(0)

# The function constrait takes three parameters: x, start, and end
# It compares x with start and end, returning the constrained value
# All three parameters are used in comparison operations (< and >)
# They should be numeric types

x = 5
start = 1
end = 10

ARGS = {
    "x": x,
    "start": start,
    "end": end
}
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 int, ndim 0, dtype family int, 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
conv2d Ran
ran on a synthesized input
wb-finalking/PLGAN/model/plgan_128.py
code served (permissive licence) · get_code("e2cf4d4a9b257101")
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 Conv2d. 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

torch.manual_seed(0)

ARGS = {
    "in_feat": 3,
    "out_feat": 16,
    "kernel_size": 3,
    "stride": 1,
    "pad": 1,
    "spectral_norm": True,
}
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 Conv2d — a Conv2d output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Conv2d 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
one_hot_to_rgb Ran
ran on a synthesized input
wb-finalking/PLGAN/gui/load_model.py
code served (permissive licence) · get_code("34028c77d1dafa32")
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 4, dtype family float, shape (2, 3, 3, 5) 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 one_hot tensor
# Shape: (a, b, c, d) where a=batch, b=classes, c=height, d=width
one_hot = torch.randint(0, 2, (2, 4, 3, 5)).float()

# Construct colors tensor
# Shape: (b, e) where b=classes, e=RGB channels
# b must match the second dimension of one_hot
colors = torch.rand(4, 3)

ARGS = {
    'one_hot': one_hot,
    'colors': colors
}
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 4, dtype family float, shape (2, 3, 3, 5) — shape (2, 3, 3, 5) 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
truncted_random Ran
ran on a synthesized input
wb-finalking/PLGAN/gui/load_model.py
code served (permissive licence) · get_code("af499039ff61de50")
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 (2, 8, 128) 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

ARGS = {
    "num_o": 8,
    "thres": 1.0,
    "bs": 2
}
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 (2, 8, 128) — shape (2, 8, 128) 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
batched_index_select Not yet run
unverified (harvested, no recorded run)
wb-finalking/PLGAN/model/plgan_128.py
code served (permissive licence) · get_code("84c3d45fd84e4dca")
How it ran

no invocation recorded.

bbox_mask Not yet run
unverified (harvested, no recorded run)
wb-finalking/PLGAN/model/plgan_128.py
code served (permissive licence) · get_code("d4ff7d51e4555db3")
How it ran

no invocation recorded.

draw_img Not yet run
unverified (harvested, no recorded run)
wb-finalking/PLGAN/eval_cal2i.py
code served (permissive licence) · get_code("3f29ba463b73ec45")
How it ran

no invocation recorded.

get_color_table Not yet run
unverified (harvested, no recorded run)
wb-finalking/PLGAN/eval_cal2i.py
code served (permissive licence) · get_code("d9c6160dbe113a63")
How it ran

no invocation recorded.

get_dataset Not yet run
unverified (harvested, no recorded run)
wb-finalking/PLGAN/train_cal2i.py
code served (permissive licence) · get_code("c41b6e9f09907a9c")
How it ran

no invocation recorded.

json_to_img Not yet run
unverified (harvested, no recorded run)
wb-finalking/PLGAN/gui/load_model.py
code served (permissive licence) · get_code("a0c50eb23385c1b3")
How it ran

no invocation recorded.

Also present in other papers' code

Of 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 11 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 11 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

Interactive image synthesis from user-guided input is a challenging task when users wish to control the scene structure of a generated image with ease. Although remarkable progress has been made on layout-based image synthesis approaches, existing methods require high-precision inputs such as accurately placed bounding boxes, which might be constantly violated in an interactive setting. When placement of bounding boxes is subject to perturbation, layoutbased models suffer from "missing regions" in the constructed semantic layouts and hence undesirable artifacts in the generated images. In this work, we propose Panoptic Layout Generative Adversarial Network (PLGAN) to address this challenge. The PLGAN employs panoptic theory which distinguishes object categories between "stuff" with amorphous boundaries and "things" with well-defined shapes, such that stuff and instance layouts are constructed through separate branches and later fused into panoptic layouts. In particular, the stuff layouts can take amorphous shapes and fill up the missing regions left out by the instance layouts. We experimentally compare our PLGAN with state-of-the-art layout-based models on the COCO-Stuff, Visual Genome, and Landscape datasets. The advantages of PLGAN are not only visually demonstrated but quantitatively verified in terms of inception score, Fréchet inception distance, classification accuracy score, and coverage. The code is available at https://github.com/wbfinalking/PLGAN.

For agents

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

get_harvested_code_for_paper("2203.02104")
get_code_for_paper("2203.02104")
have("2203.02104")

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

curl https://syntology.ai/api/ran/2203.02104.json

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

[![Syntology run record](https://syntology.ai/api/ran/2203.02104.svg)](https://syntology.ai/paper/2203.02104)

Connect an agent — have() is free.