SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2101.00591 · ICCV · 2021

Progressive Correspondence Pruning by Consensus Learning

Yixiao Ge, Hongsheng Li, Feng Zhu, Rui Zhao, Mathieu Salzmann, Chen Zhao

arXiv · PDF · Open in the Atlas

Code that ran

6 of 11 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (3 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 3 have no contract verdict; 3 failures of our instrument; 5 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/2101.00591.json · badge: /api/ran/2101.00591.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
weitong8591/ars_magsac community
Papers with Code archive
4 ran · 2 no recorded run
sailor-z/clnet community
Papers with Code archive
2 ran · 3 no recorded run
FunctionStatusWhere it lives
CLNet Ran
ran on a synthesized input · constructed an object; no result was computed
weitong8591/ars_magsac/networks/clnet.py
code served (permissive licence) · get_code("4a145d8c37c0d503")
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 an instance of its own class, CLNet: the run constructed the object and did not call it, so no result was computed. 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 torch.nn as nn

torch.manual_seed(0)

# The CLNet.__init__ takes no parameters, so ARGS should be empty
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 CLNet — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a CLNet 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
DGCNN_Block Ran
ran on a synthesized input · constructed an object; no result was computed
weitong8591/ars_magsac/networks/clnet.py
code served (permissive licence) · get_code("463923d13d63a36a")
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 an instance of its own class, DGCNN_Block: the run constructed the object and did not call it, so no result was computed. 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 torch.nn as nn

torch.manual_seed(0)

ARGS = {
    'knn_num': 9,
    'in_channel': 128,
}
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 DGCNN_Block — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a DGCNN_Block 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
ResNet_Block Ran
ran on a synthesized input · constructed an object; no result was computed
weitong8591/ars_magsac/networks/clnet.py
code served (permissive licence) · get_code("e57e5e70b4eb3eac")
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 an instance of its own class, ResNet_Block: the run constructed the object and did not call it, so no result was computed. 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 torch.nn as nn

torch.manual_seed(0)

class ResNet_Block(nn.Module):

    def __init__(self, inchannel, outchannel, pre=False):
        super(ResNet_Block, self).__init__()
        self.pre = pre
        self.right = nn.Sequential(nn.Conv2d(inchannel, outchannel, (1, 1)))
        self.left = nn.Sequential(nn.Conv2d(inchannel, outchannel, (1, 1)), nn.InstanceNorm2d(outchannel), nn.BatchNorm2d(outchannel), nn.ReLU(), nn.Conv2d(outchannel, outchannel, (1, 1)), nn.InstanceNorm2d(outchannel), nn.BatchNorm2d(outchannel))

    def forward(self, x):
        x1 = self.right(x) if self.pre is True else x
        out = self.left(x)
        out = out + x1
        return torch.relu(out)

ARGS = {
    "inchannel": 3,
    "outchannel": 4,
    "pre": 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 ResNet_Block — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a ResNet_Block 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
batch_episym Ran
ran; our contract draft was wrong, not the code
sailor-z/clnet/model.py
pointer only (licence: GPL-3.0) · get_code("7e6ccef29b8d6596")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, sailor-z/clnet, is not in the permissive set Syntology serves inline. 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.

knn Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
weitong8591/ars_magsac/networks/clnet.py
code served (permissive licence) · get_code("5f563da12002f5b8")
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 Tensor, ndim 3, dtype family int, shape (2, 3, 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)

# x is used with:
# - transpose(2, 1): needs 3 dimensions
# - sum(x ** 2, dim=1, keepdim=True): sum over dimension 1
# - matmul(x.transpose(2, 1), x): matrix multiplication
# Shape should be (batch, features, num_points) based on the operations
# Let's use (2, 4, 3) - batch=2, features=4, num_points=3

x = torch.randn(2, 4, 3)

# k is the number of nearest neighbors to find
k = 2

ARGS = {
    "x": x,
    "k": k,
}
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 Tensor, ndim 3, dtype family int, shape (2, 3, 2) — shape (2, 3, 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
weighted_8points Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
sailor-z/clnet/model.py
pointer only (licence: GPL-3.0) · get_code("bdf2881ce6634bf2")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, sailor-z/clnet, is not in the permissive set Syntology serves inline. 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.

CLNet Not yet run
unverified (harvested, no recorded run)
sailor-z/clnet/model.py
pointer only (licence: GPL-3.0) · get_code("7a593e756e0747b9")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, sailor-z/clnet, is not in the permissive set Syntology serves inline. 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. No invocation recorded.

DS_Block Not yet run
unverified (harvested, no recorded run)
sailor-z/clnet/model.py
pointer only (licence: GPL-3.0) · get_code("b0f2e92a4fe787a1")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, sailor-z/clnet, is not in the permissive set Syntology serves inline. 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. No invocation recorded.

GCN_Block Not yet run
unverified (harvested, no recorded run)
weitong8591/ars_magsac/networks/clnet.py
code served (permissive licence) · get_code("6ec2d760ebbf5880")
How it ran

no invocation recorded.

GCN_Block Not yet run
unverified (harvested, no recorded run)
sailor-z/clnet/model.py
pointer only (licence: GPL-3.0) · get_code("3aedbef83814f80e")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, sailor-z/clnet, is not in the permissive set Syntology serves inline. 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. No invocation recorded.

get_graph_feature Not yet run
unverified (harvested, no recorded run)
weitong8591/ars_magsac/networks/clnet.py
code served (permissive licence) · get_code("98c6b55c0f2b83c0")
How it ran

no invocation recorded.

Also present in other papers' code

Of 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 11 distinct functions with an identity, 5 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 5 later) and 6 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
batch_episym
brick of this paper's assembly: helper
4 other papers
3 later, 1 same year, order not determinable
Zhong_T-Net_Effective_Permutation-Equivariant_Network_for_Two-View_Correspondence_Learning_ICCV_2021_paper (2021 (year only))
T-Net: Effective Permutation-Equivariant Network for Two-View Correspondence Learning
aaai_25456 (2023 (year only))
ConvMatch: Rethinking Network Design for Two-View Correspondence Learning
Zhang_DeMatch_Deep_Decomposition_of_Motion_Field_for_Two-View_Correspondence_Learning_CVPR_2024_paper (2024 (year only))
DeMatch: Deep Decomposition of Motion Field for Two-View Correspondence Learning
and 1 more not named here
knn
brick of this paper's assembly: helper
2 other papers
2 later
2202.06688 (2022-02)
Geometric Transformer for Fast and Robust Point Cloud Registration
aaai_28123 (2024 (year only))
VSFormer: Visual-Spatial Fusion Transformer for Correspondence Pruning
DGCNN_Block
brick of this paper's assembly: helper, model
1 other paper
1 later
2202.06688 (2022-02)
Geometric Transformer for Fast and Robust Point Cloud Registration
ResNet_Block
brick of this paper's assembly: helper, model
1 other paper
1 later
2202.06688 (2022-02)
Geometric Transformer for Fast and Robust Point Cloud Registration
get_graph_feature
brick of this paper's assembly: helper
1 other paper
1 later
2202.06688 (2022-02)
Geometric Transformer for Fast and Robust Point Cloud Registration

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

Correspondence pruning aims to correctly remove false matches (outliers) from an initial set of putative correspondences. The pruning process is challenging since putative matches are typically extremely unbalanced, largely dominated by outliers, and the random distribution of such outliers further complicates the learning process for learningbased methods. To address this issue, we propose to progressively prune the correspondences via a local-to-global consensus learning procedure. We introduce a "pruning" block that lets us identify reliable candidates among the initial matches according to consensus scores estimated using local-to-global dynamic graphs. We then achieve progressive pruning by stacking multiple pruning blocks sequentially. Our method outperforms state-of-the-arts on robust line fitting, camera pose estimation and retrieval-based image localization benchmarks by significant margins and shows promising generalization ability to different datasets and detector/descriptor combinations.

For agents

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

get_harvested_code_for_paper("2101.00591")
get_code_for_paper("2101.00591")
have("2101.00591")

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

curl https://syntology.ai/api/ran/2101.00591.json

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

[![Syntology run record](https://syntology.ai/api/ran/2101.00591.svg)](https://syntology.ai/paper/2101.00591)

Connect an agent — have() is free.