SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2005.08135 · 2020

VPR-Bench: An Open-Source Visual Place Recognition Evaluation Framework with Quantifiable Viewpoint and Appearance Change

arXiv · PDF · Open in the Atlas

Code that ran

5 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; 0 honoured the contract we drafted, 0 violated it and 4 have no contract verdict; 1 failure of our instrument; 9 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/2005.08135.json · badge: /api/ran/2005.08135.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
MubarizZaffar/VPR-Bench canonical (classifier label)
classifier basis: census
5 ran · 9 no recorded run
FunctionStatusWhere it lives
largest_indices Ran
ran on a synthesized input
MubarizZaffar/VPR-Bench/VPR_Techniques/CoHOG_Python/CoHOG.py
code served (permissive licence) · get_code("83d4caaa8181f385")
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 2, dtype family int; 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 a small 2D numpy array with distinct integer values
array = np.array([
    [3, 7, 2, 9],
    [1, 8, 4, 5],
    [6, 0, 10, 3]
], dtype=np.float32)

# Number of largest indices to find
n = 5

ARGS = {
    "ary": array,
    "n": n
}
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 tuple, ndim 2, dtype family int — 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
largest_indices_thresholded Ran
ran on a synthesized input
MubarizZaffar/VPR-Bench/VPR_Techniques/CoHOG_Python/CoHOG.py
code served (permissive licence) · get_code("8b78d79ced8875cd")
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 2, dtype family int; 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

# The function takes a single parameter 'ary' which is used with:
# - np.where() to filter values >= ET (0.4)
# - len() is called on the result
# So we need a numpy array with some values >= 0.4 and some < 0.4

ary = np.array([0.1, 0.5, 0.3, 0.8, 0.2, 0.6])

ARGS = {
    "ary": ary
}
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 tuple, ndim 2, dtype family int — 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
matconvnetNormalize Ran
ran; our contract draft was wrong, not the code
MubarizZaffar/VPR-Bench/VPR_Techniques/NetVLAD/netvlad_tf/layers.py
code served (permissive licence) · get_code("0d6c91d22f5c4a69")
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 SymbolicTensor. 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 tensorflow.compat.v1 as tf
import numpy as np

tf.disable_v2_behavior()

# Create a small input tensor with shape (2, 4) - batch size 2, feature dim 4
inputs = tf.constant([[1.0, 2.0, 3.0, 4.0], [5.0, 6.0, 7.0, 8.0]], dtype=tf.float32)

# Small epsilon value to avoid division by zero
epsilon = 1e-6

ARGS = {
    "inputs": inputs,
    "epsilon": epsilon
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type SymbolicTensor — a SymbolicTensor 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
perform_VPR Ran
ran on a synthesized input
MubarizZaffar/VPR-Bench/VPR_Techniques/AMOSNet.py
code served (permissive licence) · get_code("e99fdde9ae989c7a")
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

# Analyze the function:
# - features_query_local: used in np.subtract, so needs to be array-like with shape (256, 256)
# - ref_map_features: needs to be a list/sequence where each element is array-like with shape (256, 256)
# - The function iterates through ref_map_features and computes match scores

# Create small stand-in data
# Using 256x256 as expected by the function's normalization factor
query_features = np.random.rand(256, 256).astype(np.float32)

# Create a list of reference features (using 3 reference images for variety)
ref_features = [
    np.random.rand(256, 256).astype(np.float32),
    np.random.rand(256, 256).astype(np.float32),
    np.random.rand(256, 256).astype(np.float32),
]

ARGS = {
    "features_query_local": query_features,
    "ref_map_features": ref_features,
}
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 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
perform_VPR Ran
ran on a synthesized input
MubarizZaffar/VPR-Bench/VPR_Techniques/HOG_VPR.py
code served (permissive licence) · get_code("e328ebfdf6b678a4")
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 time

# Analyze the function:
# - query_desc: needs to be array-like, converted to float64, used in dot product and norm
# - ref_map_features: iterable of array-like objects, each converted to float64, used in dot product and norm
# Both are vectors that get dot product and norm operations, so they should be 1D arrays

# Create query descriptor: 1D array of shape (5,)
query_desc = np.random.randn(5).astype('float32')

# Create reference map features: list of 1D arrays, each shape (5,)
# Using 3 reference descriptors for testing
ref_map_features = [
    np.random.randn(5).astype('float32'),
    np.random.randn(5).astype('float32'),
    np.random.randn(5).astype('float32'),
]

ARGS = {
    'query_desc': query_desc,
    'ref_map_features': ref_map_features,
}
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 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
compute_image_descriptors Not yet run
unverified (harvested, no recorded run)
MubarizZaffar/VPR-Bench/vpr_system.py
code served (permissive licence) · get_code("a151656cd963dc20")
How it ran

no invocation recorded.

compute_map_features Not yet run
unverified (harvested, no recorded run)
MubarizZaffar/VPR-Bench/VPR_Techniques/HOG_VPR.py
code served (permissive licence) · get_code("a7b10c35e372f663")
How it ran

no invocation recorded.

compute_query_desc Not yet run
unverified (harvested, no recorded run)
MubarizZaffar/VPR-Bench/VPR_Techniques/HOG_VPR.py
code served (permissive licence) · get_code("05ae286e3683b9d0")
How it ran

no invocation recorded.

conv_match_dotproduct Not yet run
unverified (harvested, no recorded run)
MubarizZaffar/VPR-Bench/VPR_Techniques/CoHOG_Python/CoHOG.py
code served (permissive licence) · get_code("94c947e93b83502a")
How it ran

no invocation recorded.

match_two_images Not yet run
unverified (harvested, no recorded run)
MubarizZaffar/VPR-Bench/vpr_system.py
code served (permissive licence) · get_code("083ea85f59fb72a6")
How it ran

no invocation recorded.

netVLAD Not yet run
unverified (harvested, no recorded run)
MubarizZaffar/VPR-Bench/VPR_Techniques/NetVLAD/netvlad_tf/layers.py
code served (permissive licence) · get_code("89c0f6b0ed442c5a")
How it ran

no invocation recorded.

perform_VPR Not yet run
unverified (harvested, no recorded run)
MubarizZaffar/VPR-Bench/VPR_Techniques/AlexNet_VPR/AlexNet_VPR.py
code served (permissive licence) · get_code("69113ca50906e841")
How it ran

no invocation recorded.

perform_VPR Not yet run
unverified (harvested, no recorded run)
MubarizZaffar/VPR-Bench/VPR_Techniques/NetVLAD/NetVLAD.py
code served (permissive licence) · get_code("6ba48fc73bf040c4")
How it ran

no invocation recorded.

selective_import Not yet run
unverified (harvested, no recorded run)
MubarizZaffar/VPR-Bench/vpr_system.py
code served (permissive licence) · get_code("1b06a8fb67a5908b")
How it ran

no invocation recorded.

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, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 0 later) and 12 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
matconvnetNormalize 1 other paper
1 dated earlier
1511.07247 (2015-11)
NetVLAD: CNN architecture for weakly supervised place recognition
netVLAD 1 other paper
1 dated earlier
1511.07247 (2015-11)
NetVLAD: CNN architecture for weakly supervised place recognition

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

Visual Place Recognition (VPR) is the process of recognising a previously visited place using visual information, often under varying appearance conditions and viewpoint changes and with computational constraints. VPR is related to the concepts of localisation, loop closure, image retrieval and is a critical component of many autonomous navigation systems ranging from autonomous vehicles to drones and computer vision systems. While the concept of place recognition has been around for many years, VPR research has grown rapidly as a field over the past decade due to improving camera hardware and its potential for deep learning-based techniques, and has become a widely studied topic in both the computer vision and robotics communities. This growth however has led to fragmentation and a lack of standardisation in the field, especially concerning performance evaluation. Moreover, the notion of viewpoint and illumination invariance of VPR techniques has largely been assessed qualitatively and hence ambiguously in the past. In this paper, we address these gaps through a new comprehensive open-source framework for assessing the performance of VPR techniques, dubbed "VPR-Bench". VPR-Bench (Open-sourced at: https://github.com/MubarizZaffar/VPR-Bench) introduces two much-needed capabilities for VPR researchers: firstly, it contains a benchmark of 12 fully-integrated datasets and 10 VPR techniques, and secondly, it integrates a comprehensive variation-quantified dataset for quantifying viewpoint and illumination invariance. We apply and analyse popular evaluation metrics for VPR from both the computer vision and robotics communities, and discuss how these different metrics complement and/or replace each other, depending upon the underlying applications and system requirements.

For agents

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

get_harvested_code_for_paper("2005.08135")
get_code_for_paper("2005.08135")
have("2005.08135")

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

curl https://syntology.ai/api/ran/2005.08135.json

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

[![Syntology run record](https://syntology.ai/api/ran/2005.08135.svg)](https://syntology.ai/paper/2005.08135)

Connect an agent — have() is free.