SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2202.11292 · AAAI · 2022

Reliable Inlier Evaluation for Unsupervised Point Cloud Registration

Le Hui, Jin Xie, Jian Yang, Haobo Jiang, Yaqi Shen

arXiv · PDF · Open in the Atlas

Code that ran

8 of 12 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 5 have no contract verdict; 3 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/2202.11292.json · badge: /api/ran/2202.11292.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
supersyq/rienet canonical (classifier label)
classifier basis not recorded on the link
8 ran · 4 no recorded run
FunctionStatusWhere it lives
farthest_subsample_points Ran
ran on a synthesized input
supersyq/rienet/data_modelnet40.py
code served (permissive licence) · get_code("3f15da07b66d960e")
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 3, 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 numpy as np

# Set random seed for reproducibility
np.random.seed(0)

# Create two small point clouds
# pointcloud1: shape (3, 10) - 3 coordinates, 10 points
pointcloud1 = np.random.randn(3, 10).astype(np.float32)

# pointcloud2: shape (3, 10) - 3 coordinates, 10 points
pointcloud2 = np.random.randn(3, 10).astype(np.float32)

# num_subsampled_points should be less than or equal to the number of points
num_subsampled_points = 5

ARGS = {
    "pointcloud1": pointcloud1,
    "pointcloud2": pointcloud2,
    "num_subsampled_points": num_subsampled_points
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy, sklearn — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 3, 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
get_graph_feature Ran
ran on a synthesized input
supersyq/rienet/utils.py
code served (permissive licence) · get_code("11f1fc28e78be11c")
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. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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

torch.manual_seed(0)

# The function expects:
# x: Input point clouds. Size [B, 3, N]
# k: Number of nearest neighbors.

batch_size = 2
num_points = 4
num_dims = 3
k = 2

# Create a small point cloud tensor with shape [B, 3, N]
x = torch.randn(batch_size, num_dims, num_points)

ARGS = {
    "x": x,
    "k": k,
}
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 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
jitter_pcd Ran
ran on a synthesized input
supersyq/rienet/data_icl.py
code served (permissive licence) · get_code("4db7368a77694af8")
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, 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

# Create a small point cloud array
# Shape: (num_points, 3) for a 3D point cloud
pcd = np.random.randn(4, 3).astype(np.float32)

ARGS = {
    "pcd": pcd,
    "sigma": 0.01,
    "clip": 0.05,
}
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 ndarray, ndim 2, dtype family float, shape (4, 3) — shape (4, 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
jitter_pointcloud Ran
ran on a synthesized input
supersyq/rienet/data_modelnet40.py
code served (permissive licence) · get_code("50f07ba76d757466")
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 (205, 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

# Create a small pointcloud
# Shape: (num_points, num_channels)
# Using distinct dimensions: 5 points, 3 channels
pointcloud = np.random.randn(5, 3).astype(np.float32)

ARGS = {
    "pointcloud": pointcloud,
    "sigma": 0.5,
    "clip": 1
}
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 ndarray, ndim 2, dtype family float, shape (205, 3) — shape (205, 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
knn Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
supersyq/rienet/utils.py
code served (permissive licence) · get_code("35d6887261f3e988")
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) and contiguous() -> needs 3D tensor
# - sum(x ** 2, dim=1, keepdim=True) -> needs dim 1 to exist
# - matmul operations
# Shape: (batch, features, num_points) based on the transpose operations
x = torch.randn(2, 4, 3)

# k is used with topk(k=k, dim=-1)
# Should be a positive integer less than the last dimension size
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
pairwise_distance_batch Ran
ran; our contract draft was wrong, not the code
supersyq/rienet/utils.py
code served (permissive licence) · get_code("26187fdb33d4f6ed")
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 3, dtype family float, shape (2, 3, 5) as a later run recorded it. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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: Input features of source point clouds. Size [B, c, N]
# y: Input features of source point clouds. Size [B, c, M]
# B = batch size = 2
# c = channels/features = 4
# N = number of points in x = 3
# M = number of points in y = 5

x = torch.randn(2, 4, 3)
y = torch.randn(2, 4, 5)

ARGS = {
    "x": x,
    "y": y,
}
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 3, dtype family float, shape (2, 3, 5) — shape (2, 3, 5) 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
quat2mat Ran
ran; our contract draft was wrong, not the code
supersyq/rienet/util.py
code served (permissive licence) · get_code("838e2078ad9224da")
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 3, dtype family float, shape (2, 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 torch

torch.manual_seed(0)

# Create a batch of quaternions in [x, y, z, w] format
# Shape: (batch_size, 4)
quat = torch.randn(2, 4)

ARGS = {
    "quat": quat
}
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 3, dtype family float, shape (2, 3, 3) — shape (2, 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
transform_point_cloud Ran
ran on a synthesized input
supersyq/rienet/util.py
code served (permissive licence) · get_code("421c2d3aa126a3e8")
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 3, dtype family float, shape (2, 3, 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 batch of 2 point clouds, each with 3 points in 3D space
# Shape: (batch_size=2, channels=3, num_points=4)
point_cloud = torch.randn(2, 3, 4)

# Create quaternion rotations for batch of 2
# Shape: (batch_size=2, 4) where 4 is [x, y, z, w]
# Normalize to make valid quaternions
quat_rotation = torch.randn(2, 4)
quat_rotation = quat_rotation / torch.norm(quat_rotation, dim=1, keepdim=True)

# Create translation vectors for batch of 2
# Shape: (batch_size=2, 3)
translation = torch.randn(2, 3)

ARGS = {
    "point_cloud": point_cloud,
    "rotation": quat_rotation,
    "translation": translation,
}
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 3, dtype family float, shape (2, 3, 4) — shape (2, 3, 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
load_data Not yet run
unverified (harvested, no recorded run)
supersyq/rienet/data_modelnet40.py
code served (permissive licence) · get_code("166cfaf582a0252e")
How it ran

no invocation recorded.

npmat2euler Not yet run
unverified (harvested, no recorded run)
supersyq/rienet/util.py
code served (permissive licence) · get_code("955ebc1518a36aa7")
How it ran

no invocation recorded.

random_pose Not yet run
unverified (harvested, no recorded run)
supersyq/rienet/data_icl.py
pointer only (licence: MIT); the stored copy get_code serves, from xmu-qcj/e2pnet, is pointer only (licence: NONE) · get_code("b3efafb434123af6")
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 xmu-qcj/e2pnet, 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. No invocation recorded.

random_rotation Not yet run
unverified (harvested, no recorded run)
supersyq/rienet/data_icl.py
pointer only (licence: MIT); the stored copy get_code serves, from xmu-qcj/e2pnet, is pointer only (licence: NONE) · get_code("d50438ea5f0c80b2")
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 xmu-qcj/e2pnet, 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. No invocation recorded.

Also present in other papers' code

Of 12 samples lifted from this paper's linked repositories, 12 carry a function identity and 0 do not. Of the 12 distinct functions with an identity, 9 are also present in other papers whose code we hold (9 with at least one paper dated earlier, 0 the same month, 5 later) and 3 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
knn 5 other papers
3 dated earlier, 2 later · 1 only as an assembly brick
2103.04256 (2021-03)
Robust Point Cloud Registration Framework Based on Deep Graph Matching
2109.06619 (2021-09)
Sampling Network Guided Cross-Entropy Method for Unsupervised Point Cloud Registration
2112.12053 (2021-12)
Multi-View Partial (MVP) Point Cloud Challenge 2021 on Completion and Registration: Methods and Results
and 2 more not named here
quat2mat 3 other papers
2 dated earlier, 1 later
1806.01411 (2018-06)
FlowNet3D: Learning Scene Flow in 3D Point Clouds
2110.02210 (2021-10)
Mix3D: Out-of-Context Data Augmentation for 3D Scenes
2310.17359 (2023-10)
SE(3) Diffusion Model-based Point Cloud Registration for Robust 6D Object Pose Estimation
load_data 2 other papers
1 dated earlier, 1 later
2110.02210 (2021-10)
Mix3D: Out-of-Context Data Augmentation for 3D Scenes
2305.07805 (2023-05)
Mesh2SSM: From Surface Meshes to Statistical Shape Models of Anatomy
random_pose 2 other papers
1 dated earlier, 1 later
2112.12053 (2021-12)
Multi-View Partial (MVP) Point Cloud Challenge 2021 on Completion and Registration: Methods and Results
2311.18433 (2023-11)
E2PNet: Event to Point Cloud Registration with Spatio-Temporal Representation Learning
random_rotation 2 other papers
1 dated earlier, 1 later
2112.12053 (2021-12)
Multi-View Partial (MVP) Point Cloud Challenge 2021 on Completion and Registration: Methods and Results
2311.18433 (2023-11)
E2PNet: Event to Point Cloud Registration with Spatio-Temporal Representation Learning
jitter_pcd 1 other paper
1 dated earlier
2112.12053 (2021-12)
Multi-View Partial (MVP) Point Cloud Challenge 2021 on Completion and Registration: Methods and Results
npmat2euler 1 other paper
1 dated earlier
1806.01411 (2018-06)
FlowNet3D: Learning Scene Flow in 3D Point Clouds
pairwise_distance_batch 1 other paper
1 dated earlier
2109.06619 (2021-09)
Sampling Network Guided Cross-Entropy Method for Unsupervised Point Cloud Registration
transform_point_cloud 1 other paper
1 dated earlier
1806.01411 (2018-06)
FlowNet3D: Learning Scene Flow in 3D Point Clouds

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

Unsupervised point cloud registration algorithm usually suffers from the unsatisfied registration precision in the partially overlapping problem due to the lack of effective inlier evaluation. In this paper, we propose a neighborhood consensus based reliable inlier evaluation method for robust unsupervised point cloud registration. It is expected to capture the discriminative geometric difference between the source neighborhood and the corresponding pseudo target neighborhood for effective inlier distinction. Specifically, our model consists of a matching map refinement module and an inlier evaluation module. In our matching map refinement module, we improve the point-wise matching map estimation by integrating the matching scores of neighbors into it. The aggregated neighborhood information potentially facilitates the discriminative map construction so that high-quality correspondences can be provided for generating the pseudo target point cloud. Based on the observation that the outlier has the significant structure-wise difference between its source neighborhood and corresponding pseudo target neighborhood while this difference for inlier is small, the inlier evaluation module exploits this difference to score the inlier confidence for each estimated correspondence. In particular, we construct an effective graph representation for capturing this geometric difference between the neighborhoods. Finally, with the learned correspondences and the corresponding inlier confidence, we use the weighted SVD algorithm for transformation estimation. Under the unsupervised setting, we exploit the Huber function based global alignment loss, the local neighborhood consensus loss, and spatial consistency loss for model optimization. The experimental results on extensive datasets demonstrate that our unsupervised point cloud registration method can yield comparable performance.

For agents

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

get_harvested_code_for_paper("2202.11292")
get_code_for_paper("2202.11292")
have("2202.11292")

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

curl https://syntology.ai/api/ran/2202.11292.json

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

[![Syntology run record](https://syntology.ai/api/ran/2202.11292.svg)](https://syntology.ai/paper/2202.11292)

Connect an agent — have() is free.