SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2407.11668 · 2024

Learning to Make Keypoints Sub-Pixel Accurate

arXiv · PDF · Open in the Atlas

Code that ran

14 of 14 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, 2 violated it and 0 have no contract verdict; 11 failures 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/2407.11668.json · badge: /api/ran/2407.11668.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
kimsinjeong/keypt2subpx canonical (classifier label)
classifier basis: census
14 ran · 0 no recorded run
FunctionStatusWhere it lives
add_argument_group Ran
ran; our contract draft was wrong, not the code
kimsinjeong/keypt2subpx/settings.py
code served (permissive licence) · get_code("8f8a9f02683a9743")
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 _ArgumentGroup. 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 argparse

arg_lists = []

parser = argparse.ArgumentParser(description='Sub-Pixel Accurate Keypoint Refinement.', formatter_class=argparse.ArgumentDefaultsHelpFormatter)

def add_argument_group(name):
    arg = parser.add_argument_group(name)
    arg_lists.append(arg)
    return arg

ARGS = {
    'name': 'Model Configuration'
}
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 _ArgumentGroup — a _ArgumentGroup output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a _ArgumentGroup 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
angle_error_mat Ran
ran, honoured the contract we drafted
kimsinjeong/keypt2subpx/utils.py
code served (permissive licence) · get_code("b878227b0bf45ec0")
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

# Create two rotation matrices
# R1 and R2 should be square matrices (rotation matrices are typically 3x3)
# The function accesses R1.T, R2, performs matrix multiplication, and traces

# Create a simple 3x3 rotation matrix for R1
angle1 = np.pi / 6  # 30 degrees
R1 = np.array([
    [np.cos(angle1), -np.sin(angle1), 0],
    [np.sin(angle1), np.cos(angle1), 0],
    [0, 0, 1]
])

# Create another 3x3 rotation matrix for R2
angle2 = np.pi / 4  # 45 degrees
R2 = np.array([
    [np.cos(angle2), -np.sin(angle2), 0],
    [np.sin(angle2), np.cos(angle2), 0],
    [0, 0, 1]
])

ARGS = {
    "R1": R1,
    "R2": R2,
}
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
angle_error_vec Ran
ran, violated the contract we drafted
kimsinjeong/keypt2subpx/utils.py
code served (permissive licence) · get_code("c0148cc150921b59")
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

# angle_error_vec takes two vector arguments (v1, v2)
# It computes norms, dot product, and arccos - these are standard numpy operations
# on 1D arrays or vectors

# Create two distinct vectors
v1 = np.array([1.0, 0.0, 0.0, 1.0])
v2 = np.array([0.0, 1.0, 1.0, 0.0])

ARGS = {
    "v1": v1,
    "v2": v2
}
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
create_meshgrid Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
kimsinjeong/keypt2subpx/model.py
code served (permissive licence) · get_code("8a04e00bdab17ab9")
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 3, 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)

# Create a 4D tensor with shape (batch, channels, height, width)
# Using distinct sizes: batch=2, channels=4, height=3, width=5
x = torch.randn(2, 4, 3, 5, dtype=torch.float32)

ARGS = {
    "x": x,
    "normalized_coordinates": 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 tuple, ndim 3, 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
dual_softmax_matcher Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
kimsinjeong/keypt2subpx/dataprocess/dedode.py
code served (permissive licence) · get_code("fd6d00be16baac22")
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 3, dtype family float, shape (2, 4, 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)

# Create small descriptor tensors
# desc_A: shape (B=2, N=4, C=3)
# desc_B: shape (B=2, M=5, C=3)
desc_A = torch.randn(2, 4, 3)
desc_B = torch.randn(2, 5, 3)

ARGS = {
    "desc_A": desc_A,
    "desc_B": desc_B,
    "inv_temperature": 1.0,
    "normalize": False,
}
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 3, dtype family float, shape (2, 4, 5) — shape (2, 4, 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
get_logger Ran
ran; our contract draft was wrong, not the code
kimsinjeong/keypt2subpx/settings.py
code served (permissive licence) · get_code("1850b68643e0cea6")
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 Logger. 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 logging

torch_available = False
try:
    import torch
    torch.manual_seed(0)
    torch_available = True
except ImportError:
    pass

ARGS = {
    'args': {}
}
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 Logger — a Logger output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Logger 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
last_checkpoint Ran
ran; our contract draft was wrong, not the code
kimsinjeong/keypt2subpx/utils.py
code served (permissive licence) · get_code("409032cbdc844dd7")
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 shutil

# Create a temporary directory and add some checkpoint files
temp_dir = tempfile.mkdtemp()

# Create sample checkpoint files
checkpoint_files = [
    'checkpoint_100.pth',
    'checkpoint_50.pth',
    'checkpoint_200.pth',
]

for checkpoint_file in checkpoint_files:
    filepath = os.path.join(temp_dir, checkpoint_file)
    with open(filepath, 'w') as f:
        f.write('dummy checkpoint')

ARGS = {
    'model_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
plot_overlap Ran
ran; our contract draft was wrong, not the code
kimsinjeong/keypt2subpx/logger.py
code served (permissive licence) · get_code("50afa2863ffd9fde")
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 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 matplotlib.pyplot as plt
import numpy as np

class MockLogger:
    def __init__(self):
        self.title = "TestPlot"
        self.names = ["loss", "accuracy", "f1_score"]
        self.numbers = {
            "loss": [0.5, 0.4, 0.3, 0.2],
            "accuracy": [0.7, 0.75, 0.8, 0.85],
            "f1_score": [0.65, 0.72, 0.78, 0.82]
        }

logger = MockLogger()

ARGS = {
    "logger": logger,
    "names": None
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
matplotlib, 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
sample_k_keypoints Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
kimsinjeong/keypt2subpx/dataprocess/superpoint_densescore.py
code served (permissive licence) · get_code("52149bdc1b043f19")
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

torch.manual_seed(0)

# Create small tensors for keypoints and scores
keypoints = torch.randn(5, 4)  # 5 keypoints, 4 dimensions each
scores = torch.rand(5)  # 5 scores, normalized to [0, 1]
scores = scores / scores.sum()  # normalize to make valid probability distribution

k = 3  # sample 3 keypoints

ARGS = {
    "keypoints": keypoints,
    "scores": scores,
    "k": k,
}
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 — 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
simple_nms Ran
ran; our contract draft was wrong, not the code
kimsinjeong/keypt2subpx/dataprocess/superpoint_densescore.py
code served (permissive licence) · get_code("f684bfe56f64af6f")
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 3, dtype family float, shape (2, 4, 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 torch

torch.manual_seed(0)

# Create a small heatmap tensor of shape (B, H, W) = (2, 4, 3)
# B=2 (batch size), H=4 (height), W=3 (width)
scores = torch.rand(2, 4, 3)

# Define radius as a small integer scalar
radius = 1

ARGS = {
    "scores": scores,
    "radius": radius,
}
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 3, dtype family float, shape (2, 4, 3) — shape (2, 4, 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
str2bool Ran
ran, violated the contract we drafted
kimsinjeong/keypt2subpx/settings.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.

to_normalized_coords Ran
ran; our contract draft was wrong, not the code
kimsinjeong/keypt2subpx/dataprocess/dedode.py
code served (permissive licence) · get_code("c10ee0f852bbdf33")
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 3, dtype family float, shape (2, 4, 2) 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)

# flow is a tensor with shape (..., 2) where the last dimension contains x and y components
flow = torch.randn(2, 4, 2)

# h1 is the height dimension (integer)
h1 = 3

# w1 is the width dimension (integer)
w1 = 5

ARGS = {
    "flow": flow,
    "h1": h1,
    "w1": w1,
}
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 3, dtype family float, shape (2, 4, 2) — shape (2, 4, 2) 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
to_pixel_coords Ran
ran; our contract draft was wrong, not the code
kimsinjeong/keypt2subpx/dataprocess/dedode.py
code served (permissive licence) · get_code("ce58f04f80fb3c1d")
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 3, dtype family float, shape (2, 4, 2) 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)

# flow: a tensor with shape (..., 2) containing normalized flow vectors
# The function expects flow values in range [-1, 1] and converts them to pixel coordinates
flow = torch.randn(2, 4, 2)  # batch_size=2, spatial_dim=4, channels=2

# h1: height of the output image
h1 = 480

# w1: width of the output image
w1 = 640

ARGS = {
    "flow": flow,
    "h1": h1,
    "w1": w1,
}
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 3, dtype family float, shape (2, 4, 2) — shape (2, 4, 2) 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
top_k_keypoints Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
kimsinjeong/keypt2subpx/dataprocess/superpoint_densescore.py
code served (permissive licence) · get_code("719478e41beaad68")
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

torch.manual_seed(0)

# Create small tensors for testing
# keypoints: shape (num_keypoints, num_features)
# scores: shape (num_keypoints,)
# k: integer for top-k selection

keypoints = torch.randn(5, 4)  # 5 keypoints, 4 features each
scores = torch.randn(5)  # 5 scores
k = 2  # select top 2

ARGS = {
    "keypoints": keypoints,
    "scores": scores,
    "k": k,
}
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 — 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

Also present in other papers' code

Of 14 samples lifted from this paper's linked repositories, 14 carry a function identity and 0 do not. Of the 14 distinct functions with an identity, 5 are also present in other papers whose code we hold (5 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
str2bool 33 other papers
31 dated earlier, 2 same year, order not determinable
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
plot_overlap 31 other papers
29 dated earlier, 1 later, 1 same year, order not determinable
1612.06321 (2016-12)
Large-Scale Image Retrieval with Attentive Deep Local Features
1805.07925 (2018-05)
Batch-Instance Normalization for Adaptively Style-Invariant Neural Networks
1806.04606 (2018-06)
Knowledge Distillation by On-the-Fly Native Ensemble
and 28 more not named here
add_argument_group 27 other papers
26 dated earlier, 1 same year, order not determinable
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
to_normalized_coords 1 other paper
1 dated earlier
2308.08479 (2023-08)
DeDoDe: Detect, Don't Describe -- Describe, Don't Detect for Local Feature Matching
top_k_keypoints 1 other paper
1 dated earlier
2306.13643 (2023-06)
LightGlue: Local Feature Matching at Light Speed

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

This work addresses the challenge of sub-pixel accuracy in detecting 2D local features, a cornerstone problem in computer vision. Despite the advancements brought by neural network-based methods like SuperPoint and ALIKED, these modern approaches lag behind classical ones such as SIFT in keypoint localization accuracy due to their lack of sub-pixel precision. We propose a novel network that enhances any detector with sub-pixel precision by learning an offset vector for detected features, thereby eliminating the need for designing specialized sub-pixel accurate detectors. This optimization directly minimizes test-time evaluation metrics like relative pose error. Through extensive testing with both nearest neighbors matching and the recent LightGlue matcher across various real-world datasets, our method consistently outperforms existing methods in accuracy. Moreover, it adds only around 7 ms to the time of a particular detector. The code is available at https://github.com/KimSinjeong/keypt2subpx .

For agents

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

get_harvested_code_for_paper("2407.11668")
get_code_for_paper("2407.11668")
have("2407.11668")

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

curl https://syntology.ai/api/ran/2407.11668.json

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

[![Syntology run record](https://syntology.ai/api/ran/2407.11668.svg)](https://syntology.ai/paper/2407.11668)

Connect an agent — have() is free.