SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2105.08229 · 2021

Single View Geocentric Pose in the Wild

arXiv · PDF · Open in the Atlas

Code that ran

4 of 5 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; 3 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/2105.08229.json · badge: /api/ran/2105.08229.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
pubgeo/monocular-geocentric-pose canonical (classifier label)
classifier basis: census
4 ran · 1 no recorded run
FunctionStatusWhere it lives
flip Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
pubgeo/monocular-geocentric-pose/utilities/augmentation_vflow.py
code served (permissive licence) · get_code("2baf6334e966e883")
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 torch
import numpy as np

torch.manual_seed(0)

# Construct arguments for the flip function
# The function expects:
# - image: a 3D array with shape (height, width, channels)
# - mag: a 2D array with shape (height, width)
# - agl: a 2D array with shape (height, width) or None
# - dim: a string either 'x' or 'y'

# Create a small image tensor (height=4, width=3, channels=2)
image = np.random.rand(4, 3, 2).astype(np.float32)

# Create a magnitude array (height=4, width=3)
mag = np.random.rand(4, 3).astype(np.float32)

# Create an angle array (height=4, width=3)
agl = np.random.rand(4, 3).astype(np.float32)

# Choose a dimension to flip
dim = 'x'

ARGS = {
    'image': image,
    'mag': mag,
    'agl': agl,
    'dim': dim
}
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 — 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_r2 Ran
ran, honoured the contract we drafted
pubgeo/monocular-geocentric-pose/utilities/misc_utils.py
code served (permissive licence) · get_code("6a34ed721080147b")
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 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
import numpy as np

torch.manual_seed(0)

# Analyzing the function:
# def get_r2(error_sum, gt_sq_sum, data_sum, count):
#     return 1 - error_sum / (gt_sq_sum - data_sum ** 2 / count)
#
# All parameters are used in arithmetic operations (subtraction, division, exponentiation)
# They should be numeric scalars or arrays that support these operations

# Creating small numeric values for each parameter
error_sum = torch.tensor(2.5)
gt_sq_sum = torch.tensor(15.0)
data_sum = torch.tensor(8.0)
count = torch.tensor(4.0)

ARGS = {
    "error_sum": error_sum,
    "gt_sq_sum": gt_sq_sum,
    "data_sum": data_sum,
    "count": count
}
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 Tensor, 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
load_vflow Ran
ran; our contract draft was wrong, not the code
pubgeo/monocular-geocentric-pose/utilities/misc_utils.py
code served (permissive licence) · get_code("de84dc201f81cf0b")
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. 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 numpy as np
import json
import tempfile
from pathlib import Path

# Create a temporary JSON file with valid vflow data
temp_dir = tempfile.mkdtemp()
vflow_path = Path(temp_dir) / "vflow.json"

vflow_data = {
    "scale": 0.5,
    "angle": np.pi / 4
}

with open(vflow_path, 'w') as f:
    json.dump(vflow_data, f)

# Create a simple args object with unit attribute
class Args:
    def __init__(self):
        self.unit = 'm'

args = Args()

# Create a small agl array (2x3)
agl = np.array([[1.0, 2.0, 3.0], [4.0, 5.0, 6.0]], dtype='float32')

ARGS = {
    'vflow_path': vflow_path,
    'agl': agl,
    'args': args,
    'dtype_out': 'float32',
    'units_per_meter_conversion_factors': {'cm': 100.0, 'm': 1.0},
    'return_vflow_pred_mat': False
}
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 — a list 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
rect_flow Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
pubgeo/monocular-geocentric-pose/utilities/evaluate.py
code served (permissive licence) · get_code("1c781d20158046de")
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 numpy as np
import cv2

# Create small test arrays
height, width = 8, 8

# rgb: uint8 array with shape (height, width, 3) for color image
rgb = np.random.randint(0, 256, (height, width, 3), dtype=np.uint8)

# mag: float32 array with shape (height, width) for magnitude
mag = np.random.rand(height, width).astype(np.float32) * 5.0

# angle: float32 array with shape (height, width) for angle in radians
angle = np.random.rand(height, width).astype(np.float32) * 2 * np.pi

# agl: float32 array with shape (height, width) for some angle data
agl = np.random.rand(height, width).astype(np.float32) * 2 * np.pi

ARGS = {
    "rgb": rgb,
    "mag": mag,
    "angle": angle,
    "agl": agl,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
cv2, numpy — 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_crop_region Not yet run
unverified (harvested, no recorded run)
pubgeo/monocular-geocentric-pose/utilities/augmentation_vflow.py
code served (permissive licence) · get_code("1dbe73d3d4fd8e91")
How it ran

no invocation recorded.

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 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 5 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

Current methods for Earth observation tasks such as semantic mapping, map alignment, and change detection rely on near-nadir images; however, often the first available images in response to dynamic world events such as natural disasters are oblique. These tasks are much more difficult for oblique images due to observed object parallax. There has been recent success in learning to regress geocentric pose, defined as height above ground and orientation with respect to gravity, by training with airborne lidar registered to satellite images. We present a model for this novel task that exploits affine invariance properties to outperform state of the art performance by a wide margin. We also address practical issues required to deploy this method in the wild for real-world applications. Our data and code are publicly available.

For agents

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

get_harvested_code_for_paper("2105.08229")
get_code_for_paper("2105.08229")
have("2105.08229")

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

curl https://syntology.ai/api/ran/2105.08229.json

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

[![Syntology run record](https://syntology.ai/api/ran/2105.08229.svg)](https://syntology.ai/paper/2105.08229)

Connect an agent — have() is free.