SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2103.12292 · 2021

NDT-Transformer: Large-Scale 3D Point Cloud Localisation using the Normal Distribution Transform Representation

arXiv · PDF · Open in the Atlas

Code that ran

4 of 8 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; 0 failures of our instrument; 4 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/2103.12292.json · badge: /api/ran/2103.12292.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
dachengxiaocheng/NDT-Transformer canonical (classifier label)
classifier basis: census
4 ran · 4 no recorded run
FunctionStatusWhere it lives
check_in_test_set Ran
ran on a synthesized input
dachengxiaocheng/NDT-Transformer/generating_queries/generate_test_sets.py
code served (permissive licence) · get_code("3660847b6200e2d8")
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 bool, ndim 0, dtype family float, 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

torch.manual_seed(0)

x_width = 150
y_width = 150

# northing: a single numeric value representing a northing coordinate
northing = 42.5

# easting: a single numeric value representing an easting coordinate
easting = 73.2

# points: a list of tuples/lists where each point is [northing, easting]
points = [
    [100.0, 150.0],  # point 1
    [200.0, 250.0],  # point 2
    [50.0, 75.0],    # point 3
]

ARGS = {
    "northing": northing,
    "easting": easting,
    "points": points,
    "x_width": x_width,
    "y_width": y_width,
}
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 bool, ndim 0, dtype family float, 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
check_in_test_set Ran
ran on a synthesized input
dachengxiaocheng/NDT-Transformer/generating_queries/generate_training_tuples_baseline.py
code served (permissive licence) · get_code("798c8e34b491c1a9")
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 bool, ndim 0, dtype family float, 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

torch.manual_seed(0)

# Analyze the function:
# - northing: numeric value (float/int)
# - easting: numeric value (float/int)
# - points: iterable of items where each item has [0] and [1] indexing (list of tuples/lists)
# - x_width: numeric value (int/float)
# - y_width: numeric value (int/float)

# The function checks if a point (northing, easting) falls within a rectangular region
# defined by x_width and y_width, relative to any point in the points list.

northing = 100.0
easting = 200.0
points = [
    (50.0, 150.0),
    (120.0, 210.0),
    (300.0, 400.0)
]
x_width = 150
y_width = 150

ARGS = {
    "northing": northing,
    "easting": easting,
    "points": points,
    "x_width": x_width,
    "y_width": y_width
}
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 bool, ndim 0, dtype family float, 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
get_queries_dict Ran
ran on a synthesized input
dachengxiaocheng/NDT-Transformer/loading_pointclouds.py
code served (permissive licence) · get_code("7453ccbdbe5b42ed")
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 dict. 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 pickle
import tempfile
import os

# Create a temporary file with pickled queries data
temp_dir = tempfile.mkdtemp()
temp_filename = os.path.join(temp_dir, "queries.pkl")

# Create sample queries data
sample_queries = {
    "query_1": "What is machine learning?",
    "query_2": "How does deep learning work?",
    "query_3": "What are neural networks?"
}

# Pickle and save the queries
with open(temp_filename, 'wb') as handle:
    pickle.dump(sample_queries, handle)

ARGS = {
    "filename": temp_filename
}
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 dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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_sets_dict Ran
ran on a synthesized input
dachengxiaocheng/NDT-Transformer/loading_pointclouds.py
code served (permissive licence) · get_code("6d56a3fb2fac6db7")
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 dict. 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 pickle
import tempfile
import os

# Create a temporary pickle file with sample trajectory data
temp_dir = tempfile.mkdtemp()
temp_file = os.path.join(temp_dir, 'trajectories.pkl')

# Create sample trajectory data
sample_trajectories = {
    'trajectory_1': [1, 2, 3, 4],
    'trajectory_2': [5, 6, 7, 8],
    'metadata': {'count': 2}
}

# Write the pickle file
with open(temp_file, 'wb') as handle:
    pickle.dump(sample_trajectories, handle)

ARGS = {
    'filename': temp_file
}
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 dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
best_pos_distance Not yet run
unverified (harvested, no recorded run)
dachengxiaocheng/NDT-Transformer/loss/loss.py
code served (permissive licence) · get_code("68bb44663a240e2d")
How it ran

no invocation recorded.

get_recall Not yet run
unverified (harvested, no recorded run)
dachengxiaocheng/NDT-Transformer/evaluate.py
code served (permissive licence) · get_code("409cecd415eafba9")
How it ran

no invocation recorded.

triplet_loss Not yet run
unverified (harvested, no recorded run)
dachengxiaocheng/NDT-Transformer/loss/loss.py
code served (permissive licence) · get_code("c28d95d8592bb59e")
How it ran

no invocation recorded.

triplet_loss_wrapper Not yet run
unverified (harvested, no recorded run)
dachengxiaocheng/NDT-Transformer/loss/loss.py
code served (permissive licence) · get_code("9af7948327648729")
How it ran

no invocation recorded.

Also present in other papers' code

Of 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 8 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.

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

3D point cloud-based place recognition is highly demanded by autonomous driving in GPS-challenged environments and serves as an essential component (i.e. loop-closure detection) in lidar-based SLAM systems. This paper proposes a novel approach, named NDT-Transformer, for realtime and large-scale place recognition using 3D point clouds. Specifically, a 3D Normal Distribution Transform (NDT) representation is employed to condense the raw, dense 3D point cloud as probabilistic distributions (NDT cells) to provide the geometrical shape description. Then a novel NDT-Transformer network learns a global descriptor from a set of 3D NDT cell representations. Benefiting from the NDT representation and NDT-Transformer network, the learned global descriptors are enriched with both geometrical and contextual information. Finally, descriptor retrieval is achieved using a query-database for place recognition. Compared to the state-of-the-art methods, the proposed approach achieves an improvement of 7.52% on average top 1 recall and 2.73% on average top 1% recall on the Oxford Robotcar benchmark.

For agents

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

get_harvested_code_for_paper("2103.12292")
get_code_for_paper("2103.12292")
have("2103.12292")

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

curl https://syntology.ai/api/ran/2103.12292.json

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

[![Syntology run record](https://syntology.ai/api/ran/2103.12292.svg)](https://syntology.ai/paper/2103.12292)

Connect an agent — have() is free.