SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2006.08844 · NeurIPS · 2020

Dual-Resolution Correspondence Networks

Kai Han, Xinghui Li, Shuda Li, Victor Prisacariu

arXiv · PDF · Open in the Atlas

Code that ran

3 of 11 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 1 failure of our instrument; 8 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/2006.08844.json · badge: /api/ran/2006.08844.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
ActiveVisionLab/DualRC-Net canonical (classifier label)
classifier basis: classifier_2025
3 ran · 8 no recorded run
FunctionStatusWhere it lives
FeatureCorrelation Ran
ran on a synthesized input · constructed an object; no result was computed
ActiveVisionLab/DualRC-Net/lib/model_v2.py
code served (permissive licence) · get_code("7807e7b29b2f6d3a")
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, FeatureCorrelation: 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)

# Create small feature tensors for testing
# Using distinct sizes: batch=2, channels=4, height=3, width=5
feature_A = torch.randn(2, 4, 3, 5)
feature_B = torch.randn(2, 4, 3, 5)

ARGS = {
    'shape': '3D',
    'normalization': True,
    'device': 0
}
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 FeatureCorrelation — 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 FeatureCorrelation 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
MutualMatching Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
ActiveVisionLab/DualRC-Net/lib/model_v2.py
code served (permissive licence) · get_code("6143bd380b5003fc")
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 6, dtype family float, shape (2, 1, 3, 4, 5, 6) 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)

# The function expects a 6D tensor with shape (batch_size, ch, fs1, fs2, fs3, fs4)
# Let's create a small tensor with distinct dimensions for clarity
batch_size = 2
ch = 1
fs1 = 3
fs2 = 4
fs3 = 5
fs4 = 6

corr4d = torch.randn(batch_size, ch, fs1, fs2, fs3, fs4)

ARGS = {
    "corr4d": corr4d
}
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 6, dtype family float, shape (2, 1, 3, 4, 5, 6) — shape (2, 1, 3, 4, 5, 6) 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
featureL2Norm Ran
ran, honoured the contract we drafted
ActiveVisionLab/DualRC-Net/lib/model_v2.py
code served (permissive licence) · get_code("cf9656ffec66503c")
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 2, dtype family float, shape (2, 4) 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 feature tensor with shape (batch_size=2, feature_dim=4)
# The function expects a 2D tensor where dimension 1 is summed over
feature = torch.randn(2, 4)

ARGS = {
    "feature": feature
}
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 2, dtype family float, shape (2, 4) — shape (2, 4) 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
Conv4d Not yet run
unverified (harvested, no recorded run)
ActiveVisionLab/DualRC-Net/lib/model_v2.py
code served (permissive licence) · get_code("c8d946595f870824")
How it ran

no invocation recorded.

Conv4d Not yet run
unverified (harvested, no recorded run)
ActiveVisionLab/DualRC-Net/lib/model_v2.py
code served (permissive licence) · get_code("0dc49061adf4b7f0")
How it ran

no invocation recorded.

FeatureExtraction Not yet run
unverified (harvested, no recorded run)
ActiveVisionLab/DualRC-Net/lib/model_v2.py
code served (permissive licence) · get_code("70060753740460e3")
How it ran

no invocation recorded.

ImMatchNet Not yet run
unverified (harvested, no recorded run)
ActiveVisionLab/DualRC-Net/lib/model_v2.py
code served (permissive licence) · get_code("a0d0188fd972c3f6")
How it ran

no invocation recorded.

ImMatchNet Not yet run
unverified (harvested, no recorded run)
ActiveVisionLab/DualRC-Net/lib/model_v2.py
code served (permissive licence) · get_code("117118b8bed6eec8")
How it ran

no invocation recorded.

NeighConsensus Not yet run
unverified (harvested, no recorded run)
ActiveVisionLab/DualRC-Net/lib/model_v2.py
code served (permissive licence) · get_code("0b91fae41a6075d7")
How it ran

no invocation recorded.

NeighConsensus Not yet run
unverified (harvested, no recorded run)
ActiveVisionLab/DualRC-Net/lib/model_v2.py
code served (permissive licence) · get_code("04c2433ce7b4fb9d")
How it ran

no invocation recorded.

conv4d Not yet run
unverified (harvested, no recorded run)
ActiveVisionLab/DualRC-Net/lib/model_v2.py
code served (permissive licence) · get_code("b34a6df14efe752e")
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 8 distinct functions with an identity, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 2 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
featureL2Norm
brick of this paper's assembly: helper
7 other papers
5 dated earlier, 2 later · 2 only as an assembly brick
1703.05593 (2017-03)
Convolutional neural network architecture for geometric matching
1810.10510 (2018-10)
Neighbourhood Consensus Networks
1909.11895 (2019-09)
Joint-task Self-supervised Learning for Temporal Correspondence
and 4 more not named here
MutualMatching
brick of this paper's assembly: helper
4 other papers
3 dated earlier, 1 later · 1 only as an assembly brick
1810.10510 (2018-10)
Neighbourhood Consensus Networks
2003.12059 (2020-03)
Correspondence Networks with Adaptive Neighbourhood Consensus
2004.10566 (2020-04)
Efficient Neighbourhood Consensus Networks via Submanifold Sparse Convolutions
and 1 more not named here

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 tackle the problem of establishing dense pixel-wise correspondences between a pair of images. In this work, we introduce Dual-Resolution Correspondence Networks (DualRC-Net), to obtain pixel-wise correspondences in a coarse-to-fine manner. DualRC-Net extracts both coarse-and fine-resolution feature maps. The coarse maps are used to produce a full but coarse 4D correlation tensor, which is then refined by a learnable neighbourhood consensus module. The fine-resolution feature maps are used to obtain the final dense correspondences guided by the refined coarse 4D correlation tensor. The selected coarse-resolution matching scores allow the fine-resolution features to focus only on a limited number of possible matches with high confidence. In this way, DualRC-Net dramatically increases matching reliability and localisation accuracy, while avoiding to apply the expensive 4D convolution kernels on fine-resolution feature maps. We comprehensively evaluate our method on large-scale public benchmarks including HPatches, InLoc, and Aachen Day-Night. It achieves the state-of-the-art results on all of them. Recently, several approaches [18,19,5] aim to avoid the detection stage by considering every point from a regular grid for matching. As a result, dense matches can be obtained by retrieving the confident ones from all possible candidate matches. Hence, the missing detection problem can be alleviated. Among these approaches, the Neighbourhood Consensus Networks (NCNet) [5] and its variants [20,21,6] have shown encouraging results. These methods employ a CNN to extract features 34th Conference on Neural Information Processing Systems (NeurIPS 2020),

For agents

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

get_harvested_code_for_paper("2006.08844")
get_code_for_paper("2006.08844")
have("2006.08844")

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

curl https://syntology.ai/api/ran/2006.08844.json

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

[![Syntology run record](https://syntology.ai/api/ran/2006.08844.svg)](https://syntology.ai/paper/2006.08844)

Connect an agent — have() is free.