SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · aaai_20189 · AAAI · 2022

FINet: Dual Branches Feature Interaction for Partial-to-Partial Point Cloud Registration

Hao Xu, Shuaicheng Liu, Nianjin Ye, Guanghui Liu, Bing Zeng

Open in the Atlas

Code that ran

4 of 5 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; 1 no recorded run), measured 2026-11-22; 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/aaai_20189.json · badge: /api/ran/aaai_20189.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
megvii-research/FINet canonical (classifier label)
classifier basis: census
4 ran · 1 no recorded run
FunctionStatusWhere it lives
np_dcm2euler Ran
ran on a synthesized input
megvii-research/FINet/common/so3.py
code served (permissive licence) · get_code("0fa199d85229ec2e")
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 (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 numpy as np
from scipy.spatial.transform import Rotation

# Create a batch of 2 valid 3x3 rotation matrices
# Using scipy to generate valid rotation matrices
batch_size = 2

# Create two random rotation matrices using scipy
rot1 = Rotation.random(random_state=0).as_matrix()
rot2 = Rotation.random(random_state=1).as_matrix()

mats = np.stack([rot1, rot2], axis=0)

ARGS = {
    'mats': mats,
    'seq': 'zyx',
    'degrees': True
}
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 (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
np_inverse Ran
ran on a synthesized input
megvii-research/FINet/common/so3.py
code served (permissive licence) · get_code("880f38a2acc92366")
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 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 numpy as np

# Create a small SE3 transform matrix
# SE3 is typically (3, 4) or (4, 4) where the last row is [0, 0, 0, 1]
# The function extracts the rotation part (3x3) and transposes it

# Single transform case: (3, 4)
single_transform = np.array([
    [1.0, 0.0, 0.0, 1.0],
    [0.0, 1.0, 0.0, 2.0],
    [0.0, 0.0, 1.0, 3.0]
], dtype=np.float32)

# Batch of transforms: (B, 3, 4) where B=2
batch_transforms = np.array([
    [
        [1.0, 0.0, 0.0, 1.0],
        [0.0, 1.0, 0.0, 2.0],
        [0.0, 0.0, 1.0, 3.0]
    ],
    [
        [0.0, -1.0, 0.0, 4.0],
        [1.0, 0.0, 0.0, 5.0],
        [0.0, 0.0, 1.0, 6.0]
    ]
], dtype=np.float32)

ARGS = {
    "g": batch_transforms
}
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 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
np_transform Ran
ran on a synthesized input
megvii-research/FINet/common/so3.py
code served (permissive licence) · get_code("e20dada5a90fa38b")
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 3, dtype family float, shape (2, 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

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

# Create batch size and point cloud parameters
B = 2  # batch size
N = 4  # number of points
D = 3  # dimension

# Create SO3 transformation matrices (B, 3, 3)
# These are rotation matrices, so we'll create simple valid rotations
g = np.array([
    np.eye(3),  # identity rotation for batch 0
    np.array([  # 90-degree rotation around z-axis for batch 1
        [0, -1, 0],
        [1, 0, 0],
        [0, 0, 1]
    ], dtype=np.float64)
], dtype=np.float64)

# Create points to transform (B, N, 3)
pts = np.random.randn(B, N, 3).astype(np.float64)

ARGS = {
    "g": g,
    "pts": pts
}
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 3, dtype family float, shape (2, 4, 3) — shape (2, 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
uniform_2_sphere Ran
ran on a synthesized input
megvii-research/FINet/dataset/transformations.py
code served (permissive licence) · get_code("a020832e85dfd32f")
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 (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 numpy as np

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

# Define ARGS dict with all parameters
ARGS = {
    "num": 5
}
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 (5, 3) — shape (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
loss_meter_manager_intial Not yet run
unverified (harvested, no recorded run)
megvii-research/FINet/common/utils.py
code served (permissive licence) · get_code("6084c0eb4c908f20")
How it ran

no invocation recorded.

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 distinct functions with an identity, 2 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 0 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
uniform_2_sphere 2 other papers
1 dated earlier, 1 same year, order not determinable
2003.13479 (2020-03)
RPM-Net: Robust Point Matching using Learned Features
2203.14517 (2022-03)
REGTR: End-to-end Point Cloud Correspondences with Transformers
loss_meter_manager_intial 1 other paper
1 same year, order not determinable
2208.05114 (2022-08)
Ghost-free High Dynamic Range Imaging with Context-aware Transformer

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

Data association is important in the point cloud registration. In this work, we propose to solve the partial-to-partial registration from a new perspective, by introducing multi-level feature interactions between the source and the reference clouds at the feature extraction stage, such that the registration can be realized without the attentions or explicit mask estimation for the overlapping detection as adopted previously. Specifically, we present FINet, a feature interactionbased structure with the capability to enable and strengthen the information associating between the inputs at multiple stages. To achieve this, we first split the features into two components, one for rotation and one for translation, based on the fact that they belong to different solution spaces, yielding a dual branches structure. Second, we insert several interaction modules at the feature extractor for the data association. Third, we propose a transformation sensitivity loss to obtain rotation-attentive and translation-attentive features. Experiments demonstrate that our method performs higher precision and robustness compared to the state-of-the-art traditional and learning-based methods. Code is available at https://github.com/megvii-research/FINet.

For agents

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

get_harvested_code_for_paper("aaai_20189")
get_code_for_paper("aaai_20189")
have("aaai_20189")

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

curl https://syntology.ai/api/ran/aaai_20189.json

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

[![Syntology run record](https://syntology.ai/api/ran/aaai_20189.svg)](https://syntology.ai/paper/aaai_20189)

Connect an agent — have() is free.