SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2409.16925 · 2024

Game4Loc: A UAV Geo-Localization Benchmark from Game Data

arXiv · PDF · Open in the Atlas

Code that ran

9 of 10 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; 3 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 6 failures of our instrument; 1 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/2409.16925.json · badge: /api/ran/2409.16925.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
Yux1angJi/GTA-UAV canonical (classifier label)
classifier basis: census
9 ran · 1 no recorded run
FunctionStatusWhere it lives
get_dis Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
Yux1angJi/GTA-UAV/Game4Loc/game4loc/evaluate/gta.py
code served (permissive licence) · get_code("c43925523daefde1")
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 list, ndim 1, dtype family float; 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 numpy as np

# Set up seed for reproducibility
np.random.seed(0)

# query_loc: tuple of (x, y) coordinates
query_loc = (5.0, 3.0)

# index: list of indices into gallery_loc_xy_list
index = [0, 1, 2, 3]

# gallery_loc_xy_list: list of (x, y) coordinate tuples
gallery_loc_xy_list = [
    (1.0, 1.0),
    (2.0, 2.0),
    (3.0, 3.0),
    (4.0, 4.0),
    (6.0, 5.0),
]

# disk_list: list of k values (number of neighbors to consider)
disk_list = [1, 2, 3]

# match_loc: optional tuple of (x, y) coordinates for matching location
match_loc = (5.5, 3.5)

ARGS = {
    "query_loc": query_loc,
    "index": index,
    "gallery_loc_xy_list": gallery_loc_xy_list,
    "disk_list": disk_list,
    "match_loc": match_loc,
}
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 list, ndim 1, dtype family float — 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
get_dis_target Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
Yux1angJi/GTA-UAV/Game4Loc/game4loc/evaluate/gta.py
code served (permissive licence) · get_code("c4dbcb6fd7ecc7af")
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 float64, ndim 0, dtype family float; 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 numpy as np

# The function get_dis_target expects:
# - query_loc: a tuple of two numbers (query_x, query_y)
# - target_loc: a tuple of two numbers (target_x, target_y)
# It computes the Euclidean distance between the two points

query_loc = (3.0, 4.0)
target_loc = (0.0, 0.0)

ARGS = {
    "query_loc": query_loc,
    "target_loc": target_loc,
}
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 float64, ndim 0, dtype family float — no output shape is stated: observe_signature.py recorded float ndim 0, which disagrees with the fixture run
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_sate_data Ran
ran; our contract draft was wrong, not the code
Yux1angJi/GTA-UAV/Game4Loc/game4loc/dataset/gta.py
code served (permissive licence) · get_code("71dc1830ad1384ea")
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 tuple, ndim 2, dtype family float; 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 os
import tempfile
import shutil

# Create a temporary directory structure for testing
temp_dir = tempfile.mkdtemp()
try:
    # Create subdirectories and files
    subdir1 = os.path.join(temp_dir, "subdir1")
    subdir2 = os.path.join(temp_dir, "subdir2")
    os.makedirs(subdir1)
    os.makedirs(subdir2)
    
    # Create some dummy files
    open(os.path.join(subdir1, "image1.jpg"), 'w').close()
    open(os.path.join(subdir1, "image2.jpg"), 'w').close()
    open(os.path.join(subdir2, "image3.jpg"), 'w').close()
    open(os.path.join(temp_dir, "image4.jpg"), 'w').close()
    
    # Define ARGS with the temporary directory
    ARGS = {
        "root_dir": temp_dir
    }
finally:
    # Note: In actual execution, cleanup would happen after function call
    pass
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 tuple, ndim 2, dtype family float — a tuple 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
get_transforms Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
Yux1angJi/GTA-UAV/Game4Loc/game4loc/dataset/gta.py
code served (permissive licence) · get_code("f50ce26b4f651f09")
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 tuple. 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 cv2
import albumentations as A
from albumentations.pytorch import ToTensorV2

ARGS = {
    'img_size': (224, 224),
    'mean': [0.485, 0.456, 0.406],
    'std': [0.229, 0.224, 0.225],
    'sat_rot': False
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
albumentations, cv2 — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is 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_transforms Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
Yux1angJi/GTA-UAV/Game4Loc/game4loc/dataset/gta_rgbd.py
code served (permissive licence) · get_code("b68371e8ced39ca5")
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 tuple. 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 cv2
import albumentations as A
from albumentations.pytorch import ToTensorV2

ARGS = {
    "img_size": (224, 224),
    "mean": [0.485, 0.456, 0.406],
    "std": [0.229, 0.224, 0.225],
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
albumentations, cv2 — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is 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
parse_tuple Ran
ran, honoured the contract we drafted
Yux1angJi/GTA-UAV/Game4Loc/eval_gta.py
code served (permissive licence) · get_code("b58429d8eed76ff7")
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 tuple, 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 argparse

def parse_tuple(s):
    try:
        return tuple(map(int, s.split(',')))
    except ValueError:
        raise argparse.ArgumentTypeError('Tuple must be integers separated by commas')

# The function takes one parameter: s (a string)
# It parses the string as comma-separated integers and returns a tuple

ARGS = {
    's': '1,2,3,4,5'
}
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 tuple, ndim 1, dtype family int — a tuple 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
sate2loc Ran
ran, honoured the contract we drafted
Yux1angJi/GTA-UAV/Game4Loc/game4loc/dataset/gta.py
code served (permissive licence) · get_code("04a66b8a5630f9e9")
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 tuple, ndim 1, dtype family float; 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

torch.manual_seed(0)

ARGS = {
    "tile_zoom": 10,
    "offset": 128,
    "tile_x": 5,
    "tile_y": 7
}
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 tuple, ndim 1, dtype family float — a tuple 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
sate2loc Ran
ran, honoured the contract we drafted
Yux1angJi/GTA-UAV/Game4Loc/game4loc/dataset/gta_mm.py
code served (permissive licence) · get_code("7981aa72d8dd283d")
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 tuple, ndim 1, dtype family float; 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
import numpy as np

SATE_LENGTH = 24576
TILE_LENGTH = 256

def sate2loc(tile_zoom, offset, tile_x, tile_y):
    tile_pix = SATE_LENGTH / 2 ** tile_zoom
    loc_x = tile_pix * (tile_x + 1 / 2 + offset / TILE_LENGTH) * 0.45
    loc_y = tile_pix * (tile_y + 1 / 2 + offset / TILE_LENGTH) * 0.45
    return (loc_x, loc_y)

ARGS = {
    "tile_zoom": 10,
    "offset": 128,
    "tile_x": 5,
    "tile_y": 7,
}
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 tuple, ndim 1, dtype family float — a tuple 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
sdm Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
Yux1angJi/GTA-UAV/Game4Loc/game4loc/evaluate/gta.py
code served (permissive licence) · get_code("b9a22fc2b74a3143")
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 list, ndim 1, dtype family float; 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 numpy as np

# Set random seed for reproducibility
np.random.seed(0)

# Define the arguments for the sdm function
query_loc = (1.5, 2.3)

sdmk_list = [3, 5]

index = np.array([0, 1, 2, 3, 4])

gallery_loc_xy_list = [
    (0.1, 0.2),
    (1.2, 2.1),
    (3.4, 1.5),
    (2.1, 3.2),
    (0.5, 1.8),
]

s = 0.001

ARGS = {
    "query_loc": query_loc,
    "sdmk_list": sdmk_list,
    "index": index,
    "gallery_loc_xy_list": gallery_loc_xy_list,
    "s": s,
}
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 list, ndim 1, dtype family float — 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
get_transforms Not yet run
unverified (harvested, no recorded run)
Yux1angJi/GTA-UAV/Game4Loc/game4loc/dataset/gta_mm.py
code served (permissive licence) · get_code("4b4a7eacffe29507")
How it ran

no invocation recorded.

Also present in other papers' code

Of 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 10 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 9 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
parse_tuple 1 other paper
1 later
Ji_MMGeo_Multimodal_Compositional_Geo-Localization_for_UAVs_ICCV_2025_paper (2025 (year only))
MMGEO: Multimodal Compositional Geo-Localization for UAVs

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

The vision-based geo-localization technology for UAV, serving as a secondary source of GPS information in addition to the global navigation satellite systems (GNSS), can still operate independently in the GPS-denied environment. Recent deep learning based methods attribute this as the task of image matching and retrieval. By retrieving drone-view images in geo-tagged satellite image database, approximate localization information can be obtained. However, due to high costs and privacy concerns, it is usually difficult to obtain large quantities of drone-view images from a continuous area. Existing drone-view datasets are mostly composed of small-scale aerial photography with a strong assumption that there exists a perfect one-to-one aligned reference image for any query, leaving a significant gap from the practical localization scenario. In this work, we construct a large-range contiguous area UAV geo-localization dataset named GTA-UAV, featuring multiple flight altitudes, attitudes, scenes, and targets using modern computer games. Based on this dataset, we introduce a more practical UAV geo-localization task including partial matches of cross-view paired data, and expand the image-level retrieval to the actual localization in terms of distance (meters). For the construction of drone-view and satellite-view pairs, we adopt a weight-based contrastive learning approach, which allows for effective learning while avoiding additional post-processing matching steps. Experiments demonstrate the effectiveness of our data and training method for UAV geo-localization, as well as the generalization capabilities to real-world scenarios.

For agents

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

get_harvested_code_for_paper("2409.16925")
get_code_for_paper("2409.16925")
have("2409.16925")

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

curl https://syntology.ai/api/ran/2409.16925.json

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

[![Syntology run record](https://syntology.ai/api/ran/2409.16925.svg)](https://syntology.ai/paper/2409.16925)

Connect an agent — have() is free.