SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1908.04616 · 2019

Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Data

arXiv · PDF · Open in the Atlas

Code that ran

4 of 6 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 2 have no contract verdict; 2 failures of our instrument; 2 no recorded run), measured 2026-11-21; 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/1908.04616.json · badge: /api/ran/1908.04616.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
hkust-vgd/scanobjectnn canonical (classifier label)
classifier basis: census
4 ran · 2 no recorded run
FunctionStatusWhere it lives
rotate_point_cloud Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
hkust-vgd/scanobjectnn/3DmFV-Net/provider.py
code served (permissive licence) · get_code("adb85367d5bf360a")
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

np.random.seed(0)

# Create a small batch of point clouds
# BxNx3 array where B=2 (batch size), N=4 (number of points), 3 (x,y,z coordinates)
batch_data = np.random.randn(2, 4, 3).astype(np.float32)

ARGS = {
    "batch_data": batch_data
}
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
shuffle_data Ran
ran; our contract draft was wrong, not the code
hkust-vgd/scanobjectnn/3DmFV-Net/provider.py
pointer only (licence: MIT); the stored copy get_code serves, from Levishery/Flywire-Neuron-Tracing, is pointer only (licence: NONE) · get_code("06353aadebc1724b")
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 Levishery/Flywire-Neuron-Tracing, 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.

shuffle_points Ran
ran on a synthesized input
hkust-vgd/scanobjectnn/data_utils.py
code served (permissive licence) · get_code("96e137097048037f")
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 list. 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 numpy as np

# Create a list of point clouds (pcs)
# Each point cloud is a numpy array that can be shuffled
pc1 = np.array([[1.0, 2.0, 3.0, 4.0],
                [5.0, 6.0, 7.0, 8.0],
                [9.0, 10.0, 11.0, 12.0]])

pc2 = np.array([[13.0, 14.0, 15.0, 16.0],
                [17.0, 18.0, 19.0, 20.0]])

pcs = [pc1, pc2]

ARGS = {
    "pcs": pcs
}
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 list — a list 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
translate_point_cloud Ran
ran on a synthesized input
hkust-vgd/scanobjectnn/3DmFV-Net/provider.py
code served (permissive licence) · get_code("32a8c1a55519d7a7")
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

np.random.seed(0)

# Create a small batch of point clouds
# Shape: BxNx3 where B=batch size, N=number of points, 3=coordinates
batch_data = np.random.randn(2, 4, 3).astype(np.float32)

ARGS = {
    'batch_data': batch_data,
    'tval': 0.2,
}
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
load_data Not yet run
unverified (harvested, no recorded run)
hkust-vgd/scanobjectnn/data_utils.py
code served (permissive licence) · get_code("beaa811fb5f2dca6")
How it ran

no invocation recorded.

load_pc_file Not yet run
unverified (harvested, no recorded run)
hkust-vgd/scanobjectnn/data_utils.py
code served (permissive licence) · get_code("c7fd6aee9e3017c9")
How it ran

no invocation recorded.

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 2 later) and 4 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
shuffle_data 17 other papers
5 dated earlier, 12 later
1803.05827 (2018-03)
Local Spectral Graph Convolution for Point Set Feature Learning
1803.11527 (2018-03)
SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filters
1811.07246 (2018-11)
PointConv: Deep Convolutional Networks on 3D Point Clouds
and 14 more not named here
rotate_point_cloud 7 other papers
2 dated earlier, 5 later
1803.11527 (2018-03)
SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filters
1904.10014 (2019-04)
Linked Dynamic Graph CNN: Learning on Point Cloud via Linking Hierarchical Features
2006.14865 (2020-06)
RPM-Net: Recurrent Prediction of Motion and Parts from Point Cloud
and 4 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 2026-11-21.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Deep learning techniques for point cloud data have demonstrated great potentials in solving classical problems in 3D computer vision such as 3D object classification and segmentation. Several recent 3D object classification methods have reported state-of-the-art performance on CAD model datasets such as ModelNet40 with high accuracy (~92%). Despite such impressive results, in this paper, we argue that object classification is still a challenging task when objects are framed with real-world settings. To prove this, we introduce ScanObjectNN, a new real-world point cloud object dataset based on scanned indoor scene data. From our comprehensive benchmark, we show that our dataset poses great challenges to existing point cloud classification techniques as objects from real-world scans are often cluttered with background and/or are partial due to occlusions. We identify three key open problems for point cloud object classification, and propose new point cloud classification neural networks that achieve state-of-the-art performance on classifying objects with cluttered background. Our dataset and code are publicly available in our project page https://hkust-vgd.github.io/scanobjectnn/.

For agents

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

get_harvested_code_for_paper("1908.04616")
get_code_for_paper("1908.04616")
have("1908.04616")

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

curl https://syntology.ai/api/ran/1908.04616.json

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

[![Syntology run record](https://syntology.ai/api/ran/1908.04616.svg)](https://syntology.ai/paper/1908.04616)

Connect an agent — have() is free.