SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2203.14453 · CVPR · 2022

SC 2 -PCR: A Second Order Spatial Compatibility for Efficient and Robust Point Cloud Registration

Fan Yang, Zhi Chen, Wenbing Tao, Kun Sun

arXiv · PDF · Open in the Atlas

Code that ran

4 of 4 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; 0 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 3 failures of our instrument; 0 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/2203.14453.json · badge: /api/ran/2203.14453.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
zhichen902/sc2-pcr marked official in Papers with Code
Papers with Code archive
4 ran · 0 no recorded run
FunctionStatusWhere it lives
Matcher Ran
ran on a synthesized input · constructed an object; no result was computed
zhichen902/sc2-pcr/SC2_PCR.py
code served (permissive licence) · get_code("9832a38a9d496f54")
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, Matcher: the run constructed the object and did not call it, so no result was computed. 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
import numpy as np

torch.manual_seed(0)

ARGS = {
    'inlier_threshold': 0.1,
    'num_node': 'all',
    'use_mutual': True,
    'd_thre': 0.1,
    'num_iterations': 10,
    'ratio': 0.2,
    'nms_radius': 0.1,
    'max_points': 8000,
    'k1': 30,
    'k2': 20,
    'select_scene': None,
}
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 Matcher — 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 Matcher 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
integrate_trans Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
zhichen902/sc2-pcr/SC2_PCR.py
code served (permissive licence) · get_code("0fd1fa818a48bebf")
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, 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 torch
import numpy as np

torch.manual_seed(0)

# Test case 1: batched torch tensors
R_torch_batch = torch.randn(2, 3, 3)
t_torch_batch = torch.randn(2, 3, 1)

# Test case 2: single torch tensors
R_torch_single = torch.randn(3, 3)
t_torch_single = torch.randn(3, 1)

# Test case 3: batched numpy arrays
R_np_batch = np.random.randn(2, 3, 3)
t_np_batch = np.random.randn(2, 3, 1)

# Test case 4: single numpy arrays
R_np_single = np.random.randn(3, 3)
t_np_single = np.random.randn(3, 1)

# Use batched torch case as the primary test
ARGS = {
    "R": R_torch_batch,
    "t": t_torch_batch
}
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 Tensor, ndim 3, dtype family float, shape (2, 4, 4) — shape (2, 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
rigid_transform_3d Ran
ran; our contract draft was wrong, not the code
zhichen902/sc2-pcr/SC2_PCR.py
code served (permissive licence) · get_code("d0c17d6e728c7865")
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, 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 torch
import numpy as np

torch.manual_seed(0)

# Create small tensors for source and target point clouds
bs = 2  # batch size
num_corr = 4  # number of correspondences
A = torch.randn(bs, num_corr, 3)  # source point cloud
B = torch.randn(bs, num_corr, 3)  # target point cloud

# Create weights for correspondences
weights = torch.ones(bs, num_corr)

# Set weight_threshold
weight_threshold = 0.0

ARGS = {
    "A": A,
    "B": B,
    "weights": weights,
    "weight_threshold": weight_threshold
}
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 Tensor, ndim 3, dtype family float, shape (2, 4, 4) — shape (2, 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
transform Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
zhichen902/sc2-pcr/SC2_PCR.py
code served (permissive licence) · get_code("d60988746155a232")
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, 5, 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
import numpy as np

torch.manual_seed(0)

# Test case 1: 3D batched tensors (torch)
pts_batched_torch = torch.randn(2, 5, 3)  # [bs=2, num_pts=5, 3]
trans_batched_torch = torch.randn(2, 4, 4)  # [bs=2, 4, 4]
# Make it a valid SE3 matrix (rotation + translation)
trans_batched_torch[:, :3, :3] = torch.nn.functional.normalize(torch.randn(2, 3, 3), dim=-1)
trans_batched_torch[:, 3, :] = torch.tensor([0., 0., 0., 1.])

ARGS = {
    "pts": pts_batched_torch,
    "trans": trans_batched_torch,
}
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 Tensor, ndim 3, dtype family float, shape (2, 5, 3) — shape (2, 5, 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

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 3 later) and 1 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
rigid_transform_3d
brick of this paper's assembly: helper
4 other papers
1 dated earlier, 3 later · 1 only as an assembly brick
2103.05465 (2021-03)
PointDSC: Robust Point Cloud Registration using Deep Spatial Consistency
Ao_BUFFER_Balancing_Accuracy_Efficiency_and_Generalizability_in_Point_Cloud_Registration_CVPR_2023_paper (2023 (year only))
BUFFER: Balancing Accuracy, Efficiency, and Generalizability in Point Cloud Registration
2304.01514 (2023-04)
Robust Outlier Rejection for 3D Registration with Variational Bayes
and 1 more not named here
integrate_trans
brick of this paper's assembly: helper
3 other papers
1 dated earlier, 2 later · 1 only as an assembly brick
2103.05465 (2021-03)
PointDSC: Robust Point Cloud Registration using Deep Spatial Consistency
2305.10854 (2023-05)
3D Registration with Maximal Cliques
2310.17359 (2023-10)
SE(3) Diffusion Model-based Point Cloud Registration for Robust 6D Object Pose Estimation
transform
brick of this paper's assembly: helper
3 other papers
1 dated earlier, 1 later, 1 same year, order not determinable · 1 only as an assembly brick
2103.05465 (2021-03)
PointDSC: Robust Point Cloud Registration using Deep Spatial Consistency
aaai_19917 (2022 (year only))
DeTarNet: Decoupling Translation and Rotation by Siamese Network for Point Cloud Registration
2310.17359 (2023-10)
SE(3) Diffusion Model-based Point Cloud Registration for Robust 6D Object Pose Estimation

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

In this paper, we present a second order spatial compatibility (SC 2 ) measure based method for efficient and robust point cloud registration (PCR), called SC 2 -PCR 1 . Firstly, we propose a second order spatial compatibility (SC 2 ) measure to compute the similarity between correspondences. It considers the global compatibility instead of local consistency, allowing for more distinctive clustering between inliers and outliers at early stage. Based on this measure, our registration pipeline employs a global spectral technique to find some reliable seeds from the initial correspondences. Then we design a two-stage strategy to expand each seed to a consensus set based on the SC 2 measure matrix. Finally, we feed each consensus set to a weighted SVD algorithm to generate a candidate rigid transformation and select the best model as the final result. Our method can guarantee to find a certain number of outlier-free consensus sets using fewer samplings, making the model estimation more efficient and robust. In addition, the proposed SC 2 measure is general and can be easily plugged into deep learning based frameworks. Extensive experiments are carried out to investigate the performance of our method.

For agents

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

get_harvested_code_for_paper("2203.14453")
get_code_for_paper("2203.14453")
have("2203.14453")

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

curl https://syntology.ai/api/ran/2203.14453.json

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

[![Syntology run record](https://syntology.ai/api/ran/2203.14453.svg)](https://syntology.ai/paper/2203.14453)

Connect an agent — have() is free.