SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2007.06888 · 2020

JSENet: Joint Semantic Segmentation and Edge Detection Network for 3D Point Clouds

arXiv · PDF · Open in the Atlas

Code that ran

8 of 12 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 7 have no contract verdict; 1 failure of our instrument; 4 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/2007.06888.json · badge: /api/ran/2007.06888.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
hzykent/JSENet canonical (classifier label)
classifier basis: census
8 ran · 4 no recorded run
FunctionStatusWhere it lives
IoU_from_confusions Ran
ran on a synthesized input
hzykent/JSENet/JSENet_code/utils/metrics.py
code served (permissive licence) · get_code("d17cdcb847279eea")
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 2, dtype family float, shape (2, 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

# Create a small confusion matrix for testing
# Shape: (2, 3, 3) - 2 samples, 3 classes
# Each confusion matrix is 3x3
confusions = np.array([
    [[10, 2, 1],
     [1, 8, 2],
     [0, 1, 9]],
    [[12, 1, 0],
     [2, 7, 1],
     [0, 2, 11]]
], dtype=np.int32)

ARGS = {
    "confusions": confusions
}
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 2, dtype family float, shape (2, 3) — shape (2, 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
bias_variable Ran
ran; our contract draft was wrong, not the code
hzykent/JSENet/JSENet_code/models/network_blocks.py
code served (permissive licence) · get_code("6a88f1ae24fa26b2")
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 ResourceVariable, ndim 1, dtype family float, shape (4,) 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 tensorflow as tf

def bias_variable(shape):
    initial = tf.constant(0.0, shape=shape)
    return tf.Variable(initial, name='bias')

# The function takes a single parameter 'shape' which should be a tuple or list
# defining the shape of the bias variable. We'll create a small shape tuple.

ARGS = {
    'shape': (4,)
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ResourceVariable, ndim 1, dtype family float, shape (4,) — shape (4,) 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
cylinder_mesh Ran
ran on a synthesized input
hzykent/JSENet/JSENet_code/utils/mesh.py
code served (permissive licence) · get_code("331436bb7f42d917")
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

# The function takes a cylinder parameter which is an array-like with 5 elements:
# [center_x, center_y, center_z, height, radius]
# and an optional precision parameter (default 24)

cylinder = np.array([1.0, 2.0, 3.0, 5.0, 2.5])

precision = 24

ARGS = {
    "cylinder": cylinder,
    "precision": precision
}
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 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
kernel_point_optimization_debug Ran
ran on a synthesized input
hzykent/JSENet/JSENet_code/kernels/kernel_points.py
code served (permissive licence) · get_code("277002c8cf0a416e")
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

ARGS = {
    'radius': 0.5,
    'num_points': 8,
    'num_kernels': 2,
    'dimension': 3,
    'fixed': 'center',
    'ratio': 1.0,
    'verbose': 0
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
matplotlib, numpy — 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
metrics Ran
ran on a synthesized input
hzykent/JSENet/JSENet_code/utils/metrics.py
code served (permissive licence) · get_code("5ffd29343f3e8e0d")
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

# Create a small confusion matrix for testing
# Shape: (2, 4, 4) - batch of 2 confusion matrices, 4 classes
confusions = np.array([
    [[10, 2, 1, 0],
     [1, 15, 2, 1],
     [0, 1, 12, 2],
     [1, 0, 1, 8]],
    [[8, 1, 0, 1],
     [2, 14, 1, 0],
     [1, 2, 11, 1],
     [0, 1, 2, 7]]
], dtype=np.int32)

ARGS = {
    "confusions": confusions,
    "ignore_unclassified": 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 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
radius_gaussian Ran
ran on a synthesized input
hzykent/JSENet/JSENet_code/kernels/convolution_ops.py
code served (permissive licence) · get_code("b211e6b58ff40f29")
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 EagerTensor, ndim 3, dtype family float, shape (2, 3, 4) 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 tensorflow as tf
import numpy as np

# Set seed for reproducibility
tf.random.set_seed(0)

# Create small tensors with distinct sizes for different dimensions
# sq_r should be radiuses with shape [dn, ..., d1, d0]
# Using shape [2, 3, 4] to have distinct dimensions
sq_r = tf.constant([
    [[1.0, 2.0, 3.0, 4.0],
     [0.5, 1.5, 2.5, 3.5],
     [0.1, 0.2, 0.3, 0.4]],
    [[2.0, 3.0, 4.0, 5.0],
     [1.0, 2.0, 3.0, 4.0],
     [0.2, 0.4, 0.6, 0.8]]
], dtype=tf.float32)

# sig should be extents of gaussians with shape [d1, d0] or [d0] or float
# Using shape [3, 4] to match the last two dimensions of sq_r
sig = tf.constant([
    [1.0, 1.5, 2.0, 2.5],
    [0.8, 1.2, 1.6, 2.0],
    [0.5, 1.0, 1.5, 2.0]
], dtype=tf.float32)

# eps parameter with default value
eps = 1e-09

ARGS = {
    "sq_r": sq_r,
    "sig": sig,
    "eps": eps
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type EagerTensor, ndim 3, dtype family float, shape (2, 3, 4) — shape (2, 3, 4) 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
rasterize_mesh Ran
ran on a synthesized input
hzykent/JSENet/JSENet_code/utils/mesh.py
code served (permissive licence) · get_code("ed30417628486a92")
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

# Create a simple triangular mesh
# 4 vertices forming a tetrahedron-like structure
vertices = np.array([
    [0.0, 0.0, 0.0],
    [1.0, 0.0, 0.0],
    [0.5, 1.0, 0.0],
    [0.5, 0.5, 1.0]
], dtype=np.float32)

# 4 faces (triangles), each face defined by 3 vertex indices
faces = np.array([
    [0, 1, 2],
    [0, 1, 3],
    [1, 2, 3],
    [0, 2, 3]
], dtype=np.int32)

# Distance parameter controlling point density
dl = 0.3

# Verbose flag
verbose = False

ARGS = {
    'vertices': vertices,
    'faces': faces,
    'dl': dl,
    'verbose': verbose
}
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 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
smooth_metrics Ran
ran on a synthesized input
hzykent/JSENet/JSENet_code/utils/metrics.py
code served (permissive licence) · get_code("9a05516350145ef4")
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

# Create a small confusion matrix for testing
# Shape: (n_epochs, n_classes, n_classes)
# Let's use 3 epochs and 4 classes
np.random.seed(0)
confusions = np.random.randint(1, 10, size=(3, 4, 4)).astype(np.int32)

ARGS = {
    "confusions": confusions,
    "smooth_n": 1,
    "ignore_unclassified": 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 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
broadcast_matmul Not yet run
unverified (harvested, no recorded run)
hzykent/JSENet/JSENet_code/kernels/convolution_ops.py
code served (permissive licence) · get_code("2793f292a326cf88")
How it ran

no invocation recorded.

general_gaussian Not yet run
unverified (harvested, no recorded run)
hzykent/JSENet/JSENet_code/kernels/convolution_ops.py
code served (permissive licence) · get_code("7a2d8943181815ac")
How it ran

no invocation recorded.

ind_max_pool Not yet run
unverified (harvested, no recorded run)
hzykent/JSENet/JSENet_code/models/network_blocks.py
code served (permissive licence) · get_code("4383ecd8cc0719fa")
How it ran

no invocation recorded.

weight_variable Not yet run
unverified (harvested, no recorded run)
hzykent/JSENet/JSENet_code/models/network_blocks.py
code served (permissive licence) · get_code("5a6188c7d118c3fc")
How it ran

no invocation recorded.

Also present in other papers' code

Of 12 samples lifted from this paper's linked repositories, 12 carry a function identity and 0 do not. Of the 12 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 3 later) and 9 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
bias_variable 4 other papers
3 dated earlier, 1 later
1904.08889 (2019-04)
KPConv: Flexible and Deformable Convolution for Point Clouds
2003.03164 (2020-03)
D3Feat: Joint Learning of Dense Detection and Description of 3D Local Features
2003.13035 (2020-03)
Multi-Path Region Mining For Weakly Supervised 3D Semantic Segmentation on Point Clouds
and 1 more not named here
ind_max_pool 4 other papers
3 dated earlier, 1 later
1904.08889 (2019-04)
KPConv: Flexible and Deformable Convolution for Point Clouds
2003.03164 (2020-03)
D3Feat: Joint Learning of Dense Detection and Description of 3D Local Features
2003.13035 (2020-03)
Multi-Path Region Mining For Weakly Supervised 3D Semantic Segmentation on Point Clouds
and 1 more not named here
weight_variable 4 other papers
3 dated earlier, 1 later
1904.08889 (2019-04)
KPConv: Flexible and Deformable Convolution for Point Clouds
2003.03164 (2020-03)
D3Feat: Joint Learning of Dense Detection and Description of 3D Local Features
2003.13035 (2020-03)
Multi-Path Region Mining For Weakly Supervised 3D Semantic Segmentation on Point Clouds
and 1 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

Semantic segmentation and semantic edge detection can be seen as two dual problems with close relationships in computer vision. Despite the fast evolution of learning-based 3D semantic segmentation methods, little attention has been drawn to the learning of 3D semantic edge detectors, even less to a joint learning method for the two tasks. In this paper, we tackle the 3D semantic edge detection task for the first time and present a new two-stream fully-convolutional network that jointly performs the two tasks. In particular, we design a joint refinement module that explicitly wires region information and edge information to improve the performances of both tasks. Further, we propose a novel loss function that encourages the network to produce semantic segmentation results with better boundaries. Extensive evaluations on S3DIS and ScanNet datasets show that our method achieves on par or better performance than the state-of-the-art methods for semantic segmentation and outperforms the baseline methods for semantic edge detection. Code release: https://github.com/hzykent/JSENet

For agents

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

get_harvested_code_for_paper("2007.06888")
get_code_for_paper("2007.06888")
have("2007.06888")

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

curl https://syntology.ai/api/ran/2007.06888.json

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

[![Syntology run record](https://syntology.ai/api/ran/2007.06888.svg)](https://syntology.ai/paper/2007.06888)

Connect an agent — have() is free.