SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2106.11272 · 2021

Neural Marching Cubes

arXiv · PDF · Open in the Atlas

Code that ran

3 of 3 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; 0 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/2106.11272.json · badge: /api/ran/2106.11272.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
czq142857/NMC canonical (classifier label)
classifier basis: classifier_2025
3 ran · 0 no recorded run
FunctionStatusWhere it lives
read_as_3d_array Ran
ran; our contract draft was wrong, not the code
czq142857/NMC/data_preprocessing/get_groundtruth_NMC/binvox_rw.py
code served (permissive licence) · get_code("7dc0ccf56d156abb")
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) and returned Voxels. 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 io

# Create a minimal binvox file in memory
def create_binvox_bytes():
    """Create a minimal valid binvox file as bytes"""
    output = io.BytesIO()
    
    # Write header
    output.write(b'#binvox 1\n')
    output.write(b'dim 4 4 4\n')
    output.write(b'translate 0.0 0.0 0.0\n')
    output.write(b'scale 1.0\n')
    output.write(b'data\n')
    
    # Write minimal voxel data (4x4x4 = 64 voxels)
    # Use run-length encoding: alternating (value, count) bytes
    # Start with 0 (empty) for 32 voxels, then 1 (filled) for 32 voxels
    output.write(bytes([0, 32]))  # 32 empty voxels
    output.write(bytes([1, 32]))  # 32 filled voxels
    
    output.seek(0)
    return output

# Create file pointer with binvox data
fp = create_binvox_bytes()

ARGS = {
    'fp': fp,
    'fix_coords': True
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Voxels — a Voxels output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Voxels 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
read_as_coord_array Ran
ran; our contract draft was wrong, not the code
czq142857/NMC/data_preprocessing/get_groundtruth_NMC/binvox_rw.py
code served (permissive licence) · get_code("d3b3bb299e8acb92")
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) and returned Voxels. 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
from io import BytesIO

# Create a minimal binvox file in memory
def create_binvox_bytes():
    """Create a minimal valid binvox file as bytes."""
    output = BytesIO()
    
    # Write header
    output.write(b'#binvox 1\n')
    output.write(b'dim 4 4 4\n')
    output.write(b'translate 0.0 0.0 0.0\n')
    output.write(b'scale 1.0\n')
    output.write(b'data\n')
    
    # Write minimal voxel data (run-length encoded)
    # 64 voxels total (4x4x4), mostly empty with a few filled
    # Format: [state (0 or 1), count] pairs
    output.write(bytes([0, 60]))  # 60 empty voxels
    output.write(bytes([1, 4]))   # 4 filled voxels
    
    output.seek(0)
    return output

# Create file pointer with binvox data
fp = create_binvox_bytes()

ARGS = {
    'fp': fp,
    'fix_coords': True,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Voxels — a Voxels output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Voxels 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
read_header Ran
ran; our contract draft was wrong, not the code
czq142857/NMC/data_preprocessing/get_groundtruth_NMC/binvox_rw.py
code served (permissive licence) · get_code("ba966c4838f2c939")
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) 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 io

# Create a mock binvox file content in memory
binvox_content = b"""#binvox 1
dim 64 64 64
translate 0.0 0.0 0.0
scale 1.0
data
"""

# Create a BytesIO object that acts like a file pointer
fp = io.BytesIO(binvox_content)

ARGS = {
    'fp': fp
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
none outside the standard library — 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

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 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, 1 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
read_header 6 other papers
4 dated earlier, 1 later, 1 same year, order not determinable
1607.07539 (2016-07)
Semantic Image Inpainting with Deep Generative Models
1808.00758 (2018-08)
Robust Attentional Aggregation of Deep Feature Sets for Multi-view 3D Reconstruction
1901.11153 (2019-01)
Pix2Vox: Context-aware 3D Reconstruction from Single and Multi-view Images
and 3 more not named here
read_as_3d_array 5 other papers
4 dated earlier, 1 same year, order not determinable
1607.07539 (2016-07)
Semantic Image Inpainting with Deep Generative Models
1808.00758 (2018-08)
Robust Attentional Aggregation of Deep Feature Sets for Multi-view 3D Reconstruction
1901.11153 (2019-01)
Pix2Vox: Context-aware 3D Reconstruction from Single and Multi-view Images
and 2 more not named here
read_as_coord_array 5 other papers
4 dated earlier, 1 same year, order not determinable
1607.07539 (2016-07)
Semantic Image Inpainting with Deep Generative Models
1808.00758 (2018-08)
Robust Attentional Aggregation of Deep Feature Sets for Multi-view 3D Reconstruction
1901.11153 (2019-01)
Pix2Vox: Context-aware 3D Reconstruction from Single and Multi-view Images
and 2 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

We introduce Neural Marching Cubes (NMC), a data-driven approach for extracting a triangle mesh from a discretized implicit field. Classical MC is defined by coarse tessellation templates isolated to individual cubes. While more refined tessellations have been proposed, they all make heuristic assumptions, such as trilinearity, when determining the vertex positions and local mesh topologies in each cube. In principle, none of these approaches can reconstruct geometric features that reveal coherence or dependencies between nearby cubes (e.g., a sharp edge), as such information is unaccounted for, resulting in poor estimates of the true underlying implicit field. To tackle these challenges, we re-cast MC from a deep learning perspective, by designing tessellation templates more apt at preserving geometric features, and learning the vertex positions and mesh topologies from training meshes, to account for contextual information from nearby cubes. We develop a compact per-cube parameterization to represent the output triangle mesh, while being compatible with neural processing, so that a simple 3D convolutional network can be employed for the training. We show that all topological cases in each cube that are applicable to our design can be easily derived using our representation, and the resulting tessellations can also be obtained naturally and efficiently by following a few design guidelines. In addition, our network learns local features with limited receptive fields, hence it generalizes well to new shapes and new datasets. We evaluate our neural MC approach by quantitative and qualitative comparisons to all well-known MC variants. In particular, we demonstrate the ability of our network to recover sharp features such as edges and corners, a long-standing issue of MC and its variants. Our network also reconstructs local mesh topologies more accurately than previous approaches.

For agents

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

get_harvested_code_for_paper("2106.11272")
get_code_for_paper("2106.11272")
have("2106.11272")

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

curl https://syntology.ai/api/ran/2106.11272.json

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

[![Syntology run record](https://syntology.ai/api/ran/2106.11272.svg)](https://syntology.ai/paper/2106.11272)

Connect an agent — have() is free.