SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2004.11540 · 2020

Deep Global Registration

arXiv · PDF · Open in the Atlas

Code that ran

8 of 9 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, 1 violated it and 2 have no contract verdict; 5 failures of our instrument; 1 no recorded run), measured 2026-11-21; 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/2004.11540.json · badge: /api/ran/2004.11540.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
chrischoy/FCGF community (classifier label)
classifier basis not recorded on the link
8 ran · 1 no recorded run
FunctionStatusWhere it lives
M Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
chrischoy/FCGF/lib/data_loaders.py
code served (permissive licence) · get_code("3095f89bf0fc823d")
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 ndarray, ndim 2, dtype family float, shape (3, 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 numpy as np
from scipy.linalg import expm, norm

def M(axis, theta):
    return expm(np.cross(np.eye(3), axis / norm(axis) * theta))

# Setup code
axis = np.array([1.0, 0.0, 0.0])  # Unit direction vector
theta = 0.5  # Rotation angle in radians

ARGS = {
    "axis": axis,
    "theta": theta
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 2, dtype family float, shape (3, 3) — shape (3, 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
add_argument_group Ran
ran; our contract draft was wrong, not the code
chrischoy/FCGF/config.py
code served (permissive licence) · get_code("6d80592fd6d47b2d")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) 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()

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

ARGS = {
    'name': 'test_group'
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
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
corr_dist Ran
ran; our contract draft was wrong, not the code
chrischoy/FCGF/lib/metrics.py
code served (permissive licence) · get_code("3fab7fa4f99491ee")
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 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

torch.manual_seed(0)

# est and gth are 4x4 transformation matrices (3x3 rotation + 3x1 translation)
est = torch.randn(4, 4)
gth = torch.randn(4, 4)

# xyz0 is a batch of 3D points (batch_size=2, coords=3)
xyz0 = torch.randn(2, 3)

# xyz1 is a batch of 3D points (batch_size=2, coords=3)
# Note: xyz1 is not used in the function body, but it's a parameter
xyz1 = torch.randn(2, 3)

# weight is optional, shape (2,) to match batch size
weight = torch.randn(2)

# max_dist parameter
max_dist = 1.0

ARGS = {
    "est": est,
    "gth": gth,
    "xyz0": xyz0,
    "xyz1": xyz1,
    "weight": weight,
    "max_dist": max_dist,
}
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 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
hardest_contrastive_loss Ran
ran on a synthesized input
chrischoy/FCGF/wcn/loss.py
code served (permissive licence) · get_code("b42b83c08ac8041e")
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 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 torch
import numpy as np

torch.manual_seed(0)
np.random.seed(0)

# Create small feature tensors
# F0: [N0, C] - features from first set
N0 = 5
C = 4
F0 = torch.randn(N0, C)

# F1: [N1, C] - features from second set
N1 = 6
F1 = torch.randn(N1, C)

# positive_pairs: [P, 2] - long tensor of (idx-in-F0, idx-in-F1)
# Create some valid positive pair indices
positive_pairs = torch.tensor([
    [0, 1],
    [1, 2],
    [2, 3],
    [3, 4],
    [4, 5]
], dtype=torch.long)

ARGS = {
    'F0': F0,
    'F1': F1,
    'positive_pairs': positive_pairs,
    'num_pos': 4096,
    'num_hn_samples': 1024,
    'pos_thresh': 0.1,
    'neg_thresh': 1.4
}
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 tuple, ndim 1, 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
pdist Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
chrischoy/FCGF/lib/metrics.py
code served (permissive licence) · get_code("4dd813cc2789294d")
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 2, dtype family float, shape (2, 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 small tensors for A and B
# A: shape (2, 4) - 2 points in 4D space
# B: shape (3, 4) - 3 points in 4D space
A = torch.randn(2, 4)
B = torch.randn(3, 4)

# Test with L2 distance type
dist_type = 'L2'

ARGS = {
    'A': A,
    'B': B,
    'dist_type': dist_type
}
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 2, dtype family float, shape (2, 3) — shape (2, 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
pdist Ran
ran on a synthesized input
chrischoy/FCGF/wcn/loss.py
code served (permissive licence) · get_code("0554943fb787aa5f")
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 2, dtype family float, shape (2, 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 two small tensors with distinct dimensions
# A: shape [2, 4] - 2 points in 4D space
# B: shape [3, 4] - 3 points in 4D space
A = torch.randn(2, 4)
B = torch.randn(3, 4)

# dist_type can be 'L2' or 'SquareL2'
dist_type = 'L2'

ARGS = {
    'A': A,
    'B': B,
    'dist_type': dist_type,
}
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 2, dtype family float, shape (2, 3) — shape (2, 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
sample_random_trans Ran
ran; our contract draft was wrong, not the code
chrischoy/FCGF/lib/data_loaders.py
code served (permissive licence) · get_code("695bce6ba3e7d453")
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 ndarray, ndim 2, dtype family float, shape (4, 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 numpy as np
from scipy.linalg import expm, norm

# Create a small point cloud (N points in 3D)
pcd = np.random.randn(5, 3).astype(np.float32)

# Create a random number generator with a seed for reproducibility
randg = np.random.RandomState(42)

# rotation_range in degrees
rotation_range = 360

ARGS = {
    "pcd": pcd,
    "randg": randg,
    "rotation_range": rotation_range,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 2, dtype family float, shape (4, 4) — shape (4, 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
str2bool Ran
ran, violated the contract we drafted
chrischoy/FCGF/config.py
pointer only (licence: MIT); 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 (MIT), 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.

eval_metrics Not yet run
unverified (harvested, no recorded run)
chrischoy/FCGF/lib/metrics.py
code served (permissive licence) · get_code("876a2cfd6cb4e088")
How it ran

no invocation recorded.

Also present in other papers' code

Of 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 distinct functions with an identity, 7 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 7 later) and 2 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
18 dated earlier, 15 later
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
add_argument_group 27 other papers
14 dated earlier, 13 later
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
M 6 other papers
6 later
2211.15654 (2022-11)
OpenScene: 3D Scene Understanding with Open Vocabularies
2305.02893 (2023-05)
APR: Online Distant Point Cloud Registration through Aggregated Point Cloud Reconstruction
2403.03532 (2024-03)
Extend Your Own Correspondences: Unsupervised Distant Point Cloud Registration by Progressive Distance Extension
and 3 more not named here
corr_dist 2 other papers
2 later
2305.02893 (2023-05)
APR: Online Distant Point Cloud Registration through Aggregated Point Cloud Reconstruction
2403.03532 (2024-03)
Extend Your Own Correspondences: Unsupervised Distant Point Cloud Registration by Progressive Distance Extension
eval_metrics 2 other papers
2 later
2305.02893 (2023-05)
APR: Online Distant Point Cloud Registration through Aggregated Point Cloud Reconstruction
2403.03532 (2024-03)
Extend Your Own Correspondences: Unsupervised Distant Point Cloud Registration by Progressive Distance Extension
pdist 2 other papers
2 later
2305.02893 (2023-05)
APR: Online Distant Point Cloud Registration through Aggregated Point Cloud Reconstruction
2403.03532 (2024-03)
Extend Your Own Correspondences: Unsupervised Distant Point Cloud Registration by Progressive Distance Extension
sample_random_trans 2 other papers
2 later
2305.02893 (2023-05)
APR: Online Distant Point Cloud Registration through Aggregated Point Cloud Reconstruction
2403.03532 (2024-03)
Extend Your Own Correspondences: Unsupervised Distant Point Cloud Registration by Progressive Distance Extension

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 2026-11-21.

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 present Deep Global Registration, a differentiable framework for pairwise registration of real-world 3D scans. Deep global registration is based on three modules: a 6-dimensional convolutional network for correspondence confidence prediction, a differentiable Weighted Procrustes algorithm for closed-form pose estimation, and a robust gradient-based SE(3) optimizer for pose refinement. Experiments demonstrate that our approach outperforms state-of-the-art methods, both learning-based and classical, on real-world data.

For agents

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

get_harvested_code_for_paper("2004.11540")
get_code_for_paper("2004.11540")
have("2004.11540")

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

curl https://syntology.ai/api/ran/2004.11540.json

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

[![Syntology run record](https://syntology.ai/api/ran/2004.11540.svg)](https://syntology.ai/paper/2004.11540)

Connect an agent — have() is free.