SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1711.05971 · 2017

Learning to Find Good Correspondences

arXiv · PDF · Open in the Atlas

Code that ran

5 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; 0 honoured the contract we drafted, 1 violated it and 3 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/1711.05971.json · badge: /api/ran/1711.05971.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
ubc-vision/image-matching-benchmark community (classifier label)
classifier basis: plan_row
4 ran · 0 no recorded run
copy not recorded community
not in the paper's declared repositories
1 ran · 0 no recorded run
FunctionStatusWhere it lives
add_argument_group Ran
ran; our contract draft was wrong, not the code
this paper's copy was not recorded; identical code first harvested from carpedm20/ENAS-pytorch
pointer only · get_code("6d80592fd6d47b2d")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_hash_list Ran
ran on a synthesized input
ubc-vision/image-matching-benchmark/import_features.py
code served (permissive licence) · get_code("eeee36aa5159bd22")
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 HASH. 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 os
import tempfile
import hashlib

# Create a temporary directory structure with test files
temp_dir = tempfile.mkdtemp()

# Create some .h5 files
h5_file_1 = os.path.join(temp_dir, "data1.h5")
with open(h5_file_1, 'wb') as f:
    f.write(b"test h5 content 1")

h5_file_2 = os.path.join(temp_dir, "data2.h5")
with open(h5_file_2, 'wb') as f:
    f.write(b"test h5 content 2")

# Create a config.json file
config_file = os.path.join(temp_dir, "config.json")
with open(config_file, 'wb') as f:
    f.write(b'{"test": "config"}')

# Create a subdirectory with more files
subdir = os.path.join(temp_dir, "subdir")
os.makedirs(subdir, exist_ok=True)

h5_file_3 = os.path.join(subdir, "data3.h5")
with open(h5_file_3, 'wb') as f:
    f.write(b"test h5 content 3")

config_file_2 = os.path.join(subdir, "config.json")
with open(config_file_2, 'wb') as f:
    f.write(b'{"nested": "config"}')

# Create a file that should be ignored (not .h5 or config.json)
ignored_file = os.path.join(temp_dir, "ignored.txt")
with open(ignored_file, 'wb') as f:
    f.write(b"this should be ignored")

# Initialize hash object
hash_obj = hashlib.sha256()

ARGS = {
    "folder_path": temp_dir,
    "hash": hash_obj
}
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 HASH — a HASH output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a HASH 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
get_kp_category Ran
ran on a synthesized input
ubc-vision/image-matching-benchmark/import_features.py
code served (permissive licence) · get_code("7d57d64d5a3cb9fe")
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

def get_kp_category(num_kp):
    """Determine category by number of keypoints."""
    breakpoints = [2048, 8000]
    for b in breakpoints:
        if num_kp <= b:
            return b
    raise RuntimeError('Found more keypoints than allowed')

# Test with a valid number of keypoints
ARGS = {
    'num_kp': 1500
}
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
hash_folder Ran
ran on a synthesized input
ubc-vision/image-matching-benchmark/import_features.py
code served (permissive licence) · get_code("f923785d42f9cf82")
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 str. 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 os
import tempfile
import hashlib

# Create a temporary directory structure with test files
temp_dir = tempfile.mkdtemp()

# Create a subdirectory
subdir = os.path.join(temp_dir, "subdir")
os.makedirs(subdir)

# Create some dummy .h5 files
h5_file1 = os.path.join(temp_dir, "data.h5")
with open(h5_file1, 'wb') as f:
    f.write(b"dummy h5 content 1")

h5_file2 = os.path.join(subdir, "model.h5")
with open(h5_file2, 'wb') as f:
    f.write(b"dummy h5 content 2")

# Create a config.json file
config_file = os.path.join(temp_dir, "config.json")
with open(config_file, 'wb') as f:
    f.write(b'{"key": "value"}')

# Create a file that should be ignored
ignored_file = os.path.join(temp_dir, "ignore_me.txt")
with open(ignored_file, 'wb') as f:
    f.write(b"this should be ignored")

ARGS = {
    "folder_path": temp_dir
}
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 str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
str2bool Ran
ran, violated the contract we drafted
ubc-vision/image-matching-benchmark/config.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from haoran0301/amenunet, is pointer only (licence: NONE) · get_code("248284f69adfeaad")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from haoran0301/amenunet, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is 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, 3 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 3 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.

FunctionAlso present inEarliest-datedOthers named
str2bool 33 other papers
6 dated earlier, 27 later
1406.6247 (2014-06)
Recurrent Models of Visual Attention
1506.03134 (2015-06)
Pointer Networks
1611.09940 (2016-11)
Neural Combinatorial Optimization with Reinforcement Learning
and 30 more not named here
add_argument_group 27 other papers
6 dated earlier, 21 later
1406.6247 (2014-06)
Recurrent Models of Visual Attention
1506.03134 (2015-06)
Pointer Networks
1609.04802 (2016-09)
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network
and 24 more not named here
get_kp_category 1 other paper
1 later
2003.01587 (2020-03)
Image Matching across Wide Baselines: From Paper to Practice

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 develop a deep architecture to learn to find good correspondences for wide-baseline stereo. Given a set of putative sparse matches and the camera intrinsics, we train our network in an end-to-end fashion to label the correspondences as inliers or outliers, while simultaneously using them to recover the relative pose, as encoded by the essential matrix. Our architecture is based on a multi-layer perceptron operating on pixel coordinates rather than directly on the image, and is thus simple and small. We introduce a novel normalization technique, called Context Normalization, which allows us to process each data point separately while imbuing it with global information, and also makes the network invariant to the order of the correspondences. Our experiments on multiple challenging datasets demonstrate that our method is able to drastically improve the state of the art with little training data.

For agents

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

get_harvested_code_for_paper("1711.05971")
get_code_for_paper("1711.05971")
have("1711.05971")

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

curl https://syntology.ai/api/ran/1711.05971.json

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

[![Syntology run record](https://syntology.ai/api/ran/1711.05971.svg)](https://syntology.ai/paper/1711.05971)

Connect an agent — have() is free.