SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2203.01703 · 2022

Capturing Shape Information with Multi-Scale Topological Loss Terms for 3D Reconstruction

arXiv · PDF · Open in the Atlas

Code that ran

2 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 2 have no contract verdict; 0 failures of our instrument; 2 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/2203.01703.json · badge: /api/ran/2203.01703.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
marrlab/shapr_torch canonical (classifier label)
classifier basis not recorded on the link
2 ran · 2 no recorded run
FunctionStatusWhere it lives
auto_property Ran
ran on a synthesized input
marrlab/shapr_torch/shapr/_settings.py
code served (permissive licence) · get_code("e1cd310a804b6dd7")
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 property. It ran in syntology-harvest-sandbox:v5-deps (sha256:6a292aa1aed1) at 2026-09-26T22:17:51Z. 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 torch

class SimpleClass:
    pass

def test_auto_property():
    # Create an instance to test the decorator
    instance = SimpleClass()
    
    # The function auto_property takes a string parameter: attr_storage_name
    # This is the name of the attribute to store in __dict__
    attr_storage_name = "my_value"
    
    # Create the property using auto_property
    prop = auto_property(attr_storage_name)
    
    # Attach it to the class
    SimpleClass.my_value = prop
    
    # Test that it works
    instance.my_value = 42
    assert instance.my_value == 42
    assert instance.__dict__[attr_storage_name] == 42
    
    # Another test with a tensor
    tensor_val = torch.tensor([1.0, 2.0, 3.0])
    instance.my_value = tensor_val
    assert torch.equal(instance.my_value, tensor_val)

# Define ARGS dict with the parameter
ARGS = {
    "attr_storage_name": "test_attribute"
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type property — a property output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a property output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image syntology-harvest-sandbox:v5-deps (sha256:6a292aa1aed1); 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
import_image Ran
ran on a synthesized input
marrlab/shapr_torch/shapr/utils.py
code served (permissive licence) · get_code("bdc2d395cd0ad8b6")
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 int, shape (3, 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
import tempfile
import os
from PIL import Image

# Create a temporary image file for testing
temp_dir = tempfile.mkdtemp()
temp_image_path = os.path.join(temp_dir, "test_image.png")

# Create a simple RGB image and save it
rgb_image = Image.new('RGB', (4, 3), color=(255, 0, 0))
rgb_image.save(temp_image_path)

# Define ARGS
ARGS = {
    "path_name": temp_image_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, numpy, skimage — 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 int, shape (3, 4, 3) — shape (3, 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
augmentation Not yet run
unverified (harvested, no recorded run)
marrlab/shapr_torch/shapr/data_generator.py
code served (permissive licence) · get_code("8e50af8dd2a65977")
How it ran

no invocation recorded.

get_test_image Not yet run
unverified (harvested, no recorded run)
marrlab/shapr_torch/shapr/data_generator.py
code served (permissive licence) · get_code("c1f885bc16f810ac")
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, 4 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 0 the same month, 0 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
augmentation 1 other paper
1 dated earlier
2201.00058 (2022-01)
Representation Topology Divergence: A Method for Comparing Neural Network Representations
auto_property 1 other paper
1 dated earlier
2201.00058 (2022-01)
Representation Topology Divergence: A Method for Comparing Neural Network Representations
get_test_image 1 other paper
1 dated earlier
2201.00058 (2022-01)
Representation Topology Divergence: A Method for Comparing Neural Network Representations
import_image 1 other paper
1 dated earlier
2201.00058 (2022-01)
Representation Topology Divergence: A Method for Comparing Neural Network Representations

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

Reconstructing 3D objects from 2D images is both challenging for our brains and machine learning algorithms. To support this spatial reasoning task, contextual information about the overall shape of an object is critical. However, such information is not captured by established loss terms (e.g. Dice loss). We propose to complement geometrical shape information by including multi-scale topological features, such as connected components, cycles, and voids, in the reconstruction loss. Our method uses cubical complexes to calculate topological features of 3D volume data and employs an optimal transport distance to guide the reconstruction process. This topology-aware loss is fully differentiable, computationally efficient, and can be added to any neural network. We demonstrate the utility of our loss by incorporating it into SHAPR, a model for predicting the 3D cell shape of individual cells based on 2D microscopy images. Using a hybrid loss that leverages both geometrical and topological information of single objects to assess their shape, we find that topological information substantially improves the quality of reconstructions, thus highlighting its ability to extract more relevant features from image datasets.

For agents

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

get_harvested_code_for_paper("2203.01703")
get_code_for_paper("2203.01703")
have("2203.01703")

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

curl https://syntology.ai/api/ran/2203.01703.json

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

[![Syntology run record](https://syntology.ai/api/ran/2203.01703.svg)](https://syntology.ai/paper/2203.01703)

Connect an agent — have() is free.