SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · Lin_Meta_Architecture_for_Point_Cloud_Analysis_CVPR_2023_paper · CVPR · 2023

Meta Architecture for Point Cloud Analysis

Yan Wang, Yonghong Tian, Rongrong Ji, Fei Chao, Xiawu Zheng, Lijiang Li, Haojia Lin, Shanshan Wang

Code that ran

10 of 11 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; 4 honoured the contract we drafted, 1 violated it and 2 have no contract verdict; 3 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/Lin_Meta_Architecture_for_Point_Cloud_Analysis_CVPR_2023_paper.json · badge: /api/ran/Lin_Meta_Architecture_for_Point_Cloud_Analysis_CVPR_2023_paper.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
linhaojia13/PointMetaBase canonical (classifier label)
classifier basis: census
10 ran · 1 no recorded run
FunctionStatusWhere it lives
concat_collate_fn Ran
ran; our contract draft was wrong, not the code
linhaojia13/PointMetaBase/openpoints/dataset/build.py
pointer only (licence: MIT); the stored copy get_code serves, from Yuzhe-Fu/FlashFPS, is pointer only (licence: NOASSERTION) · get_code("65c970f35976128a")
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 Yuzhe-Fu/FlashFPS, and GitHub could not classify the licence of that repository (NOASSERTION). 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.

farthest_point_sample Ran
ran; our contract draft was wrong, not the code
linhaojia13/PointMetaBase/openpoints/dataset/modelnet/modelnet40_normal_resampled_loader.py
pointer only (licence: MIT); the stored copy get_code serves, from Yuzhe-Fu/FlashFPS, is pointer only (licence: NOASSERTION) · get_code("f80066a00e7156a2")
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 Yuzhe-Fu/FlashFPS, and GitHub could not classify the licence of that repository (NOASSERTION). 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.

fnv_hash_vec Ran
ran, honoured the contract we drafted
linhaojia13/PointMetaBase/openpoints/dataset/data_util.py
pointer only (licence: MIT); the stored copy get_code serves, from Yuzhe-Fu/FlashFPS, is pointer only (licence: NOASSERTION) · get_code("0086c892bd1df796")
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 Yuzhe-Fu/FlashFPS, and GitHub could not classify the licence of that repository (NOASSERTION). 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_aggregation_feautres Ran
ran on a synthesized input
linhaojia13/PointMetaBase/openpoints/models/backbone/pointmetabase.py
code served (permissive licence) · get_code("2e690674fe57851c")
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, 10, 5) 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 with distinct dimensions for each parameter
batch_size = 2
num_points = 3
feature_dim = 4
num_neighbors = 5

# p: used in 'pi_dp_fj_df' case with transpose(1, 2).unsqueeze(-1).expand
# Shape should be (batch, feature_dim, num_points)
p = torch.randn(batch_size, feature_dim, num_points)

# dp: concatenated in all cases
# Shape should be (batch, some_dim, num_neighbors)
dp = torch.randn(batch_size, 6, num_neighbors)

# f: used with unsqueeze(-1) to create (batch, feature_dim, 1)
# Shape should be (batch, feature_dim)
f = torch.randn(batch_size, feature_dim)

# fj: concatenated in all cases, subtracted from f.unsqueeze(-1)
# Shape should be (batch, feature_dim, num_neighbors)
fj = torch.randn(batch_size, feature_dim, num_neighbors)

ARGS = {
    'p': p,
    'dp': dp,
    'f': f,
    'fj': fj,
    'feature_type': 'dp_fj'
}
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, 10, 5) — shape (2, 10, 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
get_reduction_fn Ran
ran on a synthesized input
linhaojia13/PointMetaBase/openpoints/models/backbone/pointmetabase.py
code served (permissive licence) · get_code("6729ad5f41f9545e")
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 function. 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 torch

torch.manual_seed(0)

# The function get_reduction_fn takes a single parameter: reduction (a string)
# It normalizes 'avg' to 'mean' and asserts the reduction is one of ['sum', 'max', 'mean']
# It returns a pooling function that operates on tensors

ARGS = {
    'reduction': 'mean'
}
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 function — a function output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a function 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
is_model Ran
ran, violated the contract we drafted
linhaojia13/PointMetaBase/openpoints/models/registry.py
pointer only (licence: MIT); the stored copy get_code serves, from Yuzhe-Fu/FlashFPS, is pointer only (licence: NOASSERTION) · get_code("cd2a47ded9dd84cf")
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 Yuzhe-Fu/FlashFPS, and GitHub could not classify the licence of that repository (NOASSERTION). 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.

list_models Ran
ran, honoured the contract we drafted
linhaojia13/PointMetaBase/openpoints/models/registry.py
pointer only (licence: MIT); the stored copy get_code serves, from Yuzhe-Fu/FlashFPS, is pointer only (licence: NOASSERTION) · get_code("d14a6ca5ff9d530e")
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 Yuzhe-Fu/FlashFPS, and GitHub could not classify the licence of that repository (NOASSERTION). 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.

pc_normalize Ran
ran, honoured the contract we drafted
linhaojia13/PointMetaBase/openpoints/dataset/modelnet/modelnet40_normal_resampled_loader.py
pointer only (licence: MIT); the stored copy get_code serves, from ajhamdi/MVTN, is pointer only (licence: NONE) · get_code("4783fbece52f500e")
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 ajhamdi/MVTN, 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.

ravel_hash_vec Ran
ran, honoured the contract we drafted
linhaojia13/PointMetaBase/openpoints/dataset/data_util.py
pointer only (licence: MIT); the stored copy get_code serves, from Yuzhe-Fu/FlashFPS, is pointer only (licence: NOASSERTION) · get_code("afdc8ad15d9098b8")
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 Yuzhe-Fu/FlashFPS, and GitHub could not classify the licence of that repository (NOASSERTION). 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.

register_model Ran
ran; our contract draft was wrong, not the code
linhaojia13/PointMetaBase/openpoints/models/registry.py
pointer only (licence: MIT); the stored copy get_code serves, from Yuzhe-Fu/FlashFPS, is pointer only (licence: NOASSERTION) · get_code("e13039fb1c347452")
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 Yuzhe-Fu/FlashFPS, and GitHub could not classify the licence of that repository (NOASSERTION). 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.

download_url Not yet run
unverified (harvested, no recorded run)
linhaojia13/PointMetaBase/openpoints/dataset/data_util.py
pointer only (licence: MIT); the stored copy get_code serves, from Yuzhe-Fu/FlashFPS, is pointer only (licence: NOASSERTION) · get_code("556e417290a6e1fd")
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 Yuzhe-Fu/FlashFPS, and GitHub could not classify the licence of that repository (NOASSERTION). 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 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 11 distinct functions with an identity, 10 are also present in other papers whose code we hold (9 with at least one paper dated earlier, 0 the same month, 9 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
pc_normalize 47 other papers
17 dated earlier, 24 later, 6 same year, order not determinable
1811.07246 (2018-11)
PointConv: Deep Convolutional Networks on 3D Point Clouds
1912.12098 (2019-12)
Quaternion Equivariant Capsule Networks for 3D Point Clouds
2003.00492 (2020-03)
PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Sampling
and 44 more not named here
farthest_point_sample 43 other papers
14 dated earlier, 24 later, 5 same year, order not determinable
1811.07246 (2018-11)
PointConv: Deep Convolutional Networks on 3D Point Clouds
2003.00492 (2020-03)
PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Sampling
2010.05272 (2020-10)
IF-Defense: 3D Adversarial Point Cloud Defense via Implicit Function based Restoration
and 40 more not named here
is_model 22 other papers
11 dated earlier, 6 later, 5 same year, order not determinable
1409.4842 (2014-09)
Going deeper with convolutions
1512.00567 (2015-12)
Rethinking the Inception Architecture for Computer Vision
1608.06993 (2016-08)
Densely Connected Convolutional Networks
and 19 more not named here
fnv_hash_vec 12 other papers
2 dated earlier, 9 later, 1 same year, order not determinable
2211.15654 (2022-11)
OpenScene: 3D Scene Understanding with Open Vocabularies
2212.02011 (2022-12)
PointCaM: Cut-and-Mix for Open-Set Point Cloud Learning
2303.16450 (2023-03)
Self-positioning Point-based Transformer for Point Cloud Understanding
and 9 more not named here
list_models 12 other papers
3 dated earlier, 6 later, 3 same year, order not determinable
2105.01601 (2021-05)
MLP-Mixer: An all-MLP Architecture for Vision
2205.10528 (2022-05)
PointVector: A Vector Representation In Point Cloud Analysis
2206.03452 (2022-06)
Can CNNs Be More Robust Than Transformers?
and 9 more not named here
ravel_hash_vec 12 other papers
3 dated earlier, 8 later, 1 same year, order not determinable
2205.10528 (2022-05)
PointVector: A Vector Representation In Point Cloud Analysis
2211.15654 (2022-11)
OpenScene: 3D Scene Understanding with Open Vocabularies
2212.02011 (2022-12)
PointCaM: Cut-and-Mix for Open-Set Point Cloud Learning
and 9 more not named here
register_model 11 other papers
3 dated earlier, 5 later, 3 same year, order not determinable
2105.01601 (2021-05)
MLP-Mixer: An all-MLP Architecture for Vision
2205.10528 (2022-05)
PointVector: A Vector Representation In Point Cloud Analysis
2206.03452 (2022-06)
Can CNNs Be More Robust Than Transformers?
and 8 more not named here
concat_collate_fn 6 other papers
1 dated earlier, 3 later, 2 same year, order not determinable
2205.10528 (2022-05)
PointVector: A Vector Representation In Point Cloud Analysis
2303.16450 (2023-03)
Self-positioning Point-based Transformer for Point Cloud Understanding
2309.10431 (2023-09)
Sample-adaptive Augmentation for Point Cloud Recognition Against Real-world Corruptions
and 3 more not named here
download_url 6 other papers
1 dated earlier, 4 later, 1 same year, order not determinable
2205.10528 (2022-05)
PointVector: A Vector Representation In Point Cloud Analysis
2303.16450 (2023-03)
Self-positioning Point-based Transformer for Point Cloud Understanding
2403.00762 (2024-03)
Point Cloud Mamba: Point Cloud Learning via State Space Model
and 3 more not named here
get_reduction_fn 1 other paper
1 same year, order not determinable
2303.16450 (2023-03)
Self-positioning Point-based Transformer for Point Cloud Understanding

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

Recent advances in 3D point cloud analysis bring a diverse set of network architectures to the field. However, the lack of a unified framework to interpret those networks makes any systematic comparison, contrast, or analysis challenging, and practically limits healthy development of the field. In this paper, we take the initiative to explore and propose a unified framework called PointMeta, to which the popular 3D point cloud analysis approaches could fit. This brings three benefits. First, it allows us to compare different approaches in a fair manner, and use quick experiments to verify any empirical observations or assumptions summarized from the comparison. Second, the big picture brought by PointMeta enables us to think across different components, and revisit common beliefs and key design decisions made by the popular approaches. Third, based on the learnings from the previous two analyses, by doing simple tweaks on the existing approaches, we are able to derive a basic building block, termed PointMetaBase. It shows very strong performance in efficiency and effectiveness through extensive experiments on challenging benchmarks, and thus verifies the necessity and benefits of highlevel interpretation, contrast, and comparison like Point-Meta. In particular, PointMetaBase surpasses the previous state-of-the-art method by 0.7%/1.4/%2.1% mIoU with only 2%/11%/13% of the computation cost on the S3DIS datasets. The code and models are available at https: //github.com/linhaojia13/PointMetaBase.

For agents

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

get_harvested_code_for_paper("Lin_Meta_Architecture_for_Point_Cloud_Analysis_CVPR_2023_paper")
get_code_for_paper("Lin_Meta_Architecture_for_Point_Cloud_Analysis_CVPR_2023_paper")
have("Lin_Meta_Architecture_for_Point_Cloud_Analysis_CVPR_2023_paper")

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

curl https://syntology.ai/api/ran/Lin_Meta_Architecture_for_Point_Cloud_Analysis_CVPR_2023_paper.json

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

[![Syntology run record](https://syntology.ai/api/ran/Lin_Meta_Architecture_for_Point_Cloud_Analysis_CVPR_2023_paper.svg)](https://syntology.ai/paper/Lin_Meta_Architecture_for_Point_Cloud_Analysis_CVPR_2023_paper)

Connect an agent — have() is free.