SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2308.04782 · ICCV · 2023

PointMBF: A Multi-scale Bidirectional Fusion Network for Unsupervised RGB-D Point Cloud Registration

Manning Wang, Kexue Fu, Zhihao Li, Yucong Meng, Mingzhi Yuan

arXiv · PDF · Open in the Atlas

Code that ran

13 of 18 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; 2 honoured the contract we drafted, 1 violated it and 0 have no contract verdict; 10 failures of our instrument; 5 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/2308.04782.json · badge: /api/ran/2308.04782.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
phdymz/pointmbf canonical (classifier label)
classifier basis: census
13 ran · 5 no recorded run
FunctionStatusWhere it lives
calculate_ratio_test Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
phdymz/pointmbf/models/correspondence.py
pointer only (licence: NONE) · get_code("9e0b951555ec102f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, phdymz/pointmbf 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.

closest_pool Ran
ran; our contract draft was wrong, not the code
phdymz/pointmbf/models/block.py
pointer only (licence: NONE) · get_code("728888ce9772c062")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, phdymz/pointmbf 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.

convert_layers Ran
ran; our contract draft was wrong, not the code
phdymz/pointmbf/models/model_util.py
pointer only (licence: NONE) · get_code("52b7e4d933b2bb18")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, phdymz/pointmbf 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.

dict_to_instances Ran
ran, honoured the contract we drafted
phdymz/pointmbf/make_dataset/process_scannet.py
pointer only (licence: NONE) · get_code("e821b86cfbfb4b82")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, phdymz/pointmbf 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.

exponential_alpha Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
phdymz/pointmbf/models/renderer.py
pointer only (licence: NONE) · get_code("9754408b012a7640")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, phdymz/pointmbf 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.

gather Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
phdymz/pointmbf/models/block.py
pointer only (licence: NONE) · get_code("06eb9b038422a6ef")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, phdymz/pointmbf 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.

get_grid Ran
ran, honoured the contract we drafted
phdymz/pointmbf/models/model_util.py
pointer only (licence: NONE) · get_code("a2ccaaf662ff614b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, phdymz/pointmbf 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.

get_topk_matches Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
phdymz/pointmbf/models/correspondence.py
pointer only (licence: NONE) · get_code("96a2c828833829e2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, phdymz/pointmbf 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.

linear_alpha Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
phdymz/pointmbf/models/renderer.py
pointer only (licence: NONE) · get_code("92c08730440b44bb")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, phdymz/pointmbf 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.

normalize_quaternion Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
phdymz/pointmbf/models/alignment.py
pointer only (licence: NONE) · get_code("b8ec9326edb1790e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, phdymz/pointmbf 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.

project_rgb Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
phdymz/pointmbf/models/model.py
pointer only (licence: NONE) · get_code("340f496a754d2a44")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, phdymz/pointmbf 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.

quaternion_distance Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
phdymz/pointmbf/models/alignment.py
pointer only (licence: NONE) · get_code("706ffefd857a2f5f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, phdymz/pointmbf 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.

radius_gaussian Ran
ran, violated the contract we drafted
phdymz/pointmbf/models/block.py
pointer only (licence: NONE) · get_code("42f2cd40ba483d3b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, phdymz/pointmbf 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.

build_model Not yet run
unverified (harvested, no recorded run)
phdymz/pointmbf/models/build_model.py
pointer only (licence: NONE) · get_code("1ee7182e52561f24")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, phdymz/pointmbf 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.

get_img Not yet run
unverified (harvested, no recorded run)
phdymz/pointmbf/make_dataset/process_scannet.py
pointer only (licence: NONE) · get_code("27eb4287b1e9c486")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, phdymz/pointmbf 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.

get_rgb_loss Not yet run
unverified (harvested, no recorded run)
phdymz/pointmbf/utils/losses.py
pointer only (licence: NONE) · get_code("61c0b810858047e9")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, phdymz/pointmbf 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.

grid_to_pointcloud Not yet run
unverified (harvested, no recorded run)
phdymz/pointmbf/models/model_util.py
pointer only (licence: NONE) · get_code("a65378a84e85c43b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, phdymz/pointmbf 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.

invert_quaternion Not yet run
unverified (harvested, no recorded run)
phdymz/pointmbf/models/alignment.py
pointer only (licence: NONE) · get_code("e9857f544a5c3471")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, phdymz/pointmbf 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 18 samples lifted from this paper's linked repositories, 18 carry a function identity and 0 do not. Of the 18 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 3 the same month, 3 later) and 15 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
gather 8 other papers
5 dated earlier, 1 the same month, 1 later, 1 same year, order not determinable
1904.08889 (2019-04)
KPConv: Flexible and Deformable Convolution for Point Clouds
2007.12668 (2020-07)
KPRNet: Improving projection-based LiDAR semantic segmentation
2111.12591 (2021-11)
Lepard: Learning partial point cloud matching in rigid and deformable scenes
and 5 more not named here
radius_gaussian 8 other papers
5 dated earlier, 1 the same month, 1 later, 1 same year, order not determinable
1904.08889 (2019-04)
KPConv: Flexible and Deformable Convolution for Point Clouds
2007.12668 (2020-07)
KPRNet: Improving projection-based LiDAR semantic segmentation
2111.12591 (2021-11)
Lepard: Learning partial point cloud matching in rigid and deformable scenes
and 5 more not named here
closest_pool 6 other papers
4 dated earlier, 1 the same month, 1 later
1904.08889 (2019-04)
KPConv: Flexible and Deformable Convolution for Point Clouds
2007.12668 (2020-07)
KPRNet: Improving projection-based LiDAR semantic segmentation
2111.12591 (2021-11)
Lepard: Learning partial point cloud matching in rigid and deformable scenes
and 3 more not named here

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

Point cloud registration is a task to estimate the rigid transformation between two unaligned scans, which plays an important role in many computer vision applications. Previous learning-based works commonly focus on supervised registration, which have limitations in practice. Recently, with the advance of inexpensive RGB-D sensors, several learning-based works utilize RGB-D data to achieve unsupervised registration. However, most of existing unsupervised methods follow a cascaded design or fuse RGB-D data in a unidirectional manner, which do not fully exploit the complementary information in the RGB-D data. To leverage the complementary information more effectively, we propose a network implementing multi-scale bidirectional fusion between RGB images and point clouds generated from depth images. By bidirectionally fusing visual and geometric features in multi-scales, more distinctive deep features for correspondence estimation can be obtained, making our registration more accurate. Extensive experiments on ScanNet and 3DMatch demonstrate that our method achieves new state-of-the-art performance. Code will be released at https://github.com/phdymz/ PointMBF.

For agents

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

get_harvested_code_for_paper("2308.04782")
get_code_for_paper("2308.04782")
have("2308.04782")

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

curl https://syntology.ai/api/ran/2308.04782.json

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

[![Syntology run record](https://syntology.ai/api/ran/2308.04782.svg)](https://syntology.ai/paper/2308.04782)

Connect an agent — have() is free.