SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2003.02365 · 2020

Creating High Resolution Images with a Latent Adversarial Generator

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; 1 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/2003.02365.json · badge: /api/ran/2003.02365.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
google-research/lag canonical (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
FunctionStatusWhere it lives
get_candidates Ran
ran; our contract draft was wrong, not the code
google-research/lag/scripts/lag_generate_candidates.py
code served (permissive licence) · get_code("4d16cb8b4ebc6978")
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) and returned ndarray, ndim 5, dtype family float, shape (4, 5, 8, 6, 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
from absl import flags
import sys

# Set up FLAGS
FLAGS = flags.FLAGS
flags.DEFINE_integer('batch', 2, 'Batch size')
flags.DEFINE_integer('ncand', 3, 'Number of candidates')

# Mark flags as parsed to avoid issues
FLAGS.mark_as_parsed()

# Create a minimal ops object with the required methods
class MinimalOps:
    def lores(self, images):
        # Takes images, returns lower resolution version
        # Input shape: (N, H, W, C) -> output shape: (N, H//2, W//2, C)
        return images[:, ::2, ::2, :]
    
    def hires(self, lores_images):
        # Takes lores images, returns higher resolution version
        # Input shape: (N, H, W, C) -> output shape: (N, H*2, W*2, C)
        return np.repeat(np.repeat(lores_images, 2, axis=1), 2, axis=2)
    
    def sres(self, lores_images, scale_factor):
        # Takes lores images and a scale factor, returns super-resolved images
        # Input shape: (N, H, W, C) -> output shape: (N, H*2, W*2, C)
        return np.repeat(np.repeat(lores_images, 2, axis=1), 2, axis=2)

# Create sample images with shape (N, H, W, C)
# Using distinct dimensions: 4 samples, 8 height, 6 width, 3 channels
images = np.random.randn(4, 8, 6, 3).astype(np.float32)

ops = MinimalOps()

ARGS = {
    'ops': ops,
    'images': images,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
absl, numpy, tqdm — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 5, dtype family float, shape (4, 5, 8, 6, 3) — shape (4, 5, 8, 6, 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
get_samples_indexes Ran
ran, honoured the contract we drafted
google-research/lag/scripts/lag_generate_candidates.py
code served (permissive licence) · get_code("a9d9f59f5587169c")
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) and returned list, ndim 1, dtype family int; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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

ARGS = {
    'txt_list': ['1', '5', '10-15', '20', '25-27']
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, dtype family int — a list output has no array shape of its own; none is stated
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

Generating realistic images is difficult, and many formulations for this task have been proposed recently. If we restrict the task to that of generating a particular class of images, however, the task becomes more tractable. That is to say, instead of generating an arbitrary image as a sample from the manifold of natural images, we propose to sample images from a particular "subspace" of natural images, directed by a low-resolution image from the same subspace. The problem we address, while close to the formulation of the single-image super-resolution problem, is in fact rather different. Single image super-resolution is the task of predicting the image closest to the ground truth from a relatively low resolution image. We propose to produce samples of high resolution images given extremely small inputs with a new method called Latent Adversarial Generator (LAG). In our generative sampling framework, we only use the input (possibly of very low-resolution) to direct what class of samples the network should produce. As such, the output of our algorithm is not a unique image that relates to the input, but rather a possible se} of related images sampled from the manifold of natural images. Our method learns exclusively in the latent space of the adversary using perceptual loss -- it does not have a pixel loss.

For agents

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

get_harvested_code_for_paper("2003.02365")
get_code_for_paper("2003.02365")
have("2003.02365")

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

curl https://syntology.ai/api/ran/2003.02365.json

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

[![Syntology run record](https://syntology.ai/api/ran/2003.02365.svg)](https://syntology.ai/paper/2003.02365)

Connect an agent — have() is free.