SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2104.02246 · CVPR · 2021

One Thing One Click: A Self-Training Approach for Weakly Supervised 3D Semantic Segmentation

Xiaojuan Qi, Zhengzhe Liu, Chi-Wing Fu

arXiv · PDF · Open in the Atlas

Code that ran

3 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 0 have no contract verdict; 3 failures of our instrument; 3 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/2104.02246.json · badge: /api/ran/2104.02246.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
PointCloudYC/SQN_tensorflow community (classifier label)
classifier basis not recorded on the link
3 ran · 3 no recorded run
FunctionStatusWhere it lives
parse_header Ran
ran; our contract draft was wrong, not the code
PointCloudYC/SQN_tensorflow/helper_ply.py
pointer only (licence: MIT); the stored copy get_code serves, from valeoai/ttyd, is pointer only (licence: NONE) · get_code("27aa4c3bde697bf7")
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 valeoai/ttyd, 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.

parse_mesh_header Ran
ran; our contract draft was wrong, not the code
PointCloudYC/SQN_tensorflow/helper_ply.py
pointer only (licence: MIT); the stored copy get_code serves, from valeoai/ttyd, is pointer only (licence: NONE) · get_code("5f8cf95da4e4af73")
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 valeoai/ttyd, 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.

read_ply Ran
ran; our contract draft was wrong, not the code
PointCloudYC/SQN_tensorflow/helper_ply.py
code served (permissive licence) · get_code("1e26a8ee45f6722c")
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 1, dtype family float, shape (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 tempfile
import numpy as np
import os

# Create a temporary PLY file for testing
temp_dir = tempfile.mkdtemp()
ply_filename = os.path.join(temp_dir, 'test.ply')

# Create a simple binary little-endian PLY file
with open(ply_filename, 'wb') as f:
    # Header
    f.write(b'ply\n')
    f.write(b'format binary_little_endian 1.0\n')
    f.write(b'element vertex 3\n')
    f.write(b'property float x\n')
    f.write(b'property float y\n')
    f.write(b'property float z\n')
    f.write(b'end_header\n')
    
    # Vertex data (3 points with x, y, z coordinates)
    vertices = np.array([
        (0.1, 0.2, 0.3),
        (0.4, 0.5, 0.6),
        (0.7, 0.8, 0.9)
    ], dtype=[('x', '<f4'), ('y', '<f4'), ('z', '<f4')])
    
    f.write(vertices.tobytes())

ARGS = {
    'filename': ply_filename,
    'triangular_mesh': False
}
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 1, dtype family float, shape (3,) — shape (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
conv1d Not yet run
unverified (harvested, no recorded run)
PointCloudYC/SQN_tensorflow/helper_tf_util.py
code served (permissive licence) · get_code("9ed4be924ecef796")
How it ran

no invocation recorded.

conv2d Not yet run
unverified (harvested, no recorded run)
PointCloudYC/SQN_tensorflow/helper_tf_util.py
code served (permissive licence) · get_code("3ba7a15acc68a250")
How it ran

no invocation recorded.

conv2d_transpose Not yet run
unverified (harvested, no recorded run)
PointCloudYC/SQN_tensorflow/helper_tf_util.py
code served (permissive licence) · get_code("02f9433ac33f32b3")
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, 6 are also present in other papers whose code we hold (6 with at least one paper dated earlier, 0 the same month, 6 later) and 0 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
conv1d 8 other papers
3 dated earlier, 5 later
1803.05827 (2018-03)
Local Spectral Graph Convolution for Point Set Feature Learning
1809.07016 (2018-09)
Generating 3D Adversarial Point Clouds
2009.03137 (2020-09)
Towards Semantic Segmentation of Urban-Scale 3D Point Clouds: A Dataset, Benchmarks and Challenges
and 5 more not named here
parse_header 7 other papers
1 dated earlier, 5 later, 1 same year, order not determinable
2009.03137 (2020-09)
Towards Semantic Segmentation of Urban-Scale 3D Point Clouds: A Dataset, Benchmarks and Challenges
2105.10203 (2021-05)
Omni-supervised Point Cloud Segmentation via Gradual Receptive Field Component Reasoning
and 4 more not named here
parse_mesh_header 6 other papers
1 dated earlier, 5 later
2009.03137 (2020-09)
Towards Semantic Segmentation of Urban-Scale 3D Point Clouds: A Dataset, Benchmarks and Challenges
2105.10203 (2021-05)
Omni-supervised Point Cloud Segmentation via Gradual Receptive Field Component Reasoning
2109.13410 (2021-09)
KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3D
and 3 more not named here
read_ply 6 other papers
1 dated earlier, 5 later
2009.03137 (2020-09)
Towards Semantic Segmentation of Urban-Scale 3D Point Clouds: A Dataset, Benchmarks and Challenges
2105.10203 (2021-05)
Omni-supervised Point Cloud Segmentation via Gradual Receptive Field Component Reasoning
2109.13410 (2021-09)
KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3D
and 3 more not named here
conv2d 2 other papers
1 dated earlier, 1 later
2009.03137 (2020-09)
Towards Semantic Segmentation of Urban-Scale 3D Point Clouds: A Dataset, Benchmarks and Challenges
2105.10203 (2021-05)
Omni-supervised Point Cloud Segmentation via Gradual Receptive Field Component Reasoning
conv2d_transpose 2 other papers
1 dated earlier, 1 later
2009.03137 (2020-09)
Towards Semantic Segmentation of Urban-Scale 3D Point Clouds: A Dataset, Benchmarks and Challenges
2105.10203 (2021-05)
Omni-supervised Point Cloud Segmentation via Gradual Receptive Field Component Reasoning

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 semantic segmentation often requires largescale annotated training data, but clearly, point-wise labels are too tedious to prepare. While some recent methods propose to train a 3D network with small percentages of point labels, we take the approach to an extreme and propose "One Thing One Click," meaning that the annotator only needs to label one point per object. To leverage these extremely sparse labels in network training, we design a novel self-training approach, in which we iteratively conduct the training and label propagation, facilitated by a graph propagation module. Also, we adopt a relation network to generate the per-category prototype and explicitly model the similarity among graph nodes to generate pseudo labels to guide the iterative training. Experimental results on both ScanNet-v2 and S3DIS show that our self-training approach, with extremely-sparse annotations, outperforms all existing weakly supervised methods for 3D semantic segmentation by a large margin, and our results are also comparable to those of the fully supervised counterparts.

For agents

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

get_harvested_code_for_paper("2104.02246")
get_code_for_paper("2104.02246")
have("2104.02246")

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

curl https://syntology.ai/api/ran/2104.02246.json

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

[![Syntology run record](https://syntology.ai/api/ran/2104.02246.svg)](https://syntology.ai/paper/2104.02246)

Connect an agent — have() is free.