SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2312.11269 · 2023

Spherical Mask: Coarse-to-Fine 3D Point Cloud Instance Segmentation with Spherical Representation

arXiv · PDF · Open in the Atlas

Code that ran

1 of 4 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; 1 failure 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/2312.11269.json · badge: /api/ran/2312.11269.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
yunshin/SphericalMask canonical (classifier label)
classifier basis: census
1 ran · 3 no recorded run
FunctionStatusWhere it lives
point_indices_from_group Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
yunshin/SphericalMask/dataset/scannet200/utils.py
code served (permissive licence) · get_code("58907f232b19eed3")
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 tuple. 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
import pandas as pd

# Create sample points array (N points with 3D coordinates)
points = np.random.randn(10, 3).astype(np.float32)

# Create seg_indices array mapping points to segments
seg_indices = np.array([0, 0, 1, 1, 2, 2, 3, 3, 4, 4])

# Create a group dict with segments and label
group = {
    'segments': [0, 1, 2],
    'label': 'chair'
}

# Create a labels dataframe with raw_category and id columns
labels_pd = pd.DataFrame({
    'raw_category': ['chair', 'table', 'desk'],
    'id': [1, 2, 3]
})

# Define CLASS_IDs that are valid
CLASS_IDs = [1, 2, 3]

ARGS = {
    'points': points,
    'seg_indices': seg_indices,
    'group': group,
    'labels_pd': labels_pd,
    'CLASS_IDs': CLASS_IDs
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, pandas — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple 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
get_pred_color Not yet run
unverified (harvested, no recorded run)
yunshin/SphericalMask/visualization/vis_scannet200.py
code served (permissive licence) · get_code("51fa2dc6deb89f01")
How it ran

no invocation recorded.

get_pred_color Not yet run
unverified (harvested, no recorded run)
yunshin/SphericalMask/visualization/vis_scannetv2.py
code served (permissive licence) · get_code("547702b319e8ae89")
How it ran

no invocation recorded.

read_plymesh Not yet run
unverified (harvested, no recorded run)
yunshin/SphericalMask/dataset/scannet200/utils.py
code served (permissive licence) · get_code("f02cb8a890d52050")
How it ran

no invocation recorded.

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 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, 2 later) and 2 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
get_pred_color 2 other papers
1 dated earlier, 1 later
2307.13251 (2023-07)
GaPro: Box-Supervised 3D Point Cloud Instance Segmentation Using Gaussian Processes as Pseudo Labelers
2403.15019 (2024-03)
BSNet: Box-Supervised Simulation-assisted Mean Teacher for 3D Instance Segmentation
read_plymesh 1 other paper
1 later
2412.02402 (2024-12)
RG-SAN: Rule-Guided Spatial Awareness Network for End-to-End 3D Referring Expression Segmentation

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

Coarse-to-fine 3D instance segmentation methods show weak performances compared to recent Grouping-based, Kernel-based and Transformer-based methods. We argue that this is due to two limitations: 1) Instance size overestimation by axis-aligned bounding box(AABB) 2) False negative error accumulation from inaccurate box to the refinement phase. In this work, we introduce Spherical Mask, a novel coarse-to-fine approach based on spherical representation, overcoming those two limitations with several benefits. Specifically, our coarse detection estimates each instance with a 3D polygon using a center and radial distance predictions, which avoids excessive size estimation of AABB. To cut the error propagation in the existing coarse-to-fine approaches, we virtually migrate points based on the polygon, allowing all foreground points, including false negatives, to be refined. During inference, the proposal and point migration modules run in parallel and are assembled to form binary masks of instances. We also introduce two margin-based losses for the point migration to enforce corrections for the false positives/negatives and cohesion of foreground points, significantly improving the performance. Experimental results from three datasets, such as ScanNetV2, S3DIS, and STPLS3D, show that our proposed method outperforms existing works, demonstrating the effectiveness of the new instance representation with spherical coordinates. The code is available at: https://github.com/yunshin/SphericalMask

For agents

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

get_harvested_code_for_paper("2312.11269")
get_code_for_paper("2312.11269")
have("2312.11269")

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

curl https://syntology.ai/api/ran/2312.11269.json

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

[![Syntology run record](https://syntology.ai/api/ran/2312.11269.svg)](https://syntology.ai/paper/2312.11269)

Connect an agent — have() is free.