SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2003.07717 · 2020

Multimodal Shape Completion via Conditional Generative Adversarial Networks

arXiv · PDF · Open in the Atlas

Code that ran

7 of 7 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 6 have no contract verdict; 1 failure of our instrument; 0 no recorded run), measured 2026-11-21; 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/2003.07717.json · badge: /api/ran/2003.07717.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
ChrisWu1997/Multimodal-Shape-Completion canonical (classifier label)
classifier basis: census
7 ran · 0 no recorded run
FunctionStatusWhere it lives
collect_data_id Ran
ran on a synthesized input
ChrisWu1997/Multimodal-Shape-Completion/dataset/dataset_partnet.py
code served (permissive licence) · get_code("26ee5b528836c02d")
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 list, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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 os
import json
import tempfile
import shutil

# Create a temporary directory to hold our test data
temp_dir = tempfile.mkdtemp()

# Create a test split directory structure
split_dir = os.path.join(temp_dir, 'splits')
os.makedirs(split_dir, exist_ok=True)

# Create a test JSON file with the expected format
classname = 'test_class'
phase = 'train'
filename = os.path.join(split_dir, '{}.{}.json'.format(classname, phase))

test_data = [
    {'anno_id': 'id_001'},
    {'anno_id': 'id_002'},
    {'anno_id': 'id_003'},
]

with open(filename, 'w') as fp:
    json.dump(test_data, fp)

# Define arguments
ARGS = {
    'split_dir': split_dir,
    'classname': classname,
    'phase': phase,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
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 list, ndim 1, dtype family float — a list output has no array shape of its own; none is stated
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
collect_train_split_by_id Ran
ran on a synthesized input
ChrisWu1997/Multimodal-Shape-Completion/dataset/dataset_3depn.py
code served (permissive licence) · get_code("a350f50bcae6b3e4")
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 dict. 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 csv
import tempfile
import os

# Create a temporary CSV file with test data
temp_dir = tempfile.mkdtemp()
csv_path = os.path.join(temp_dir, 'test_data.csv')

# Write sample CSV data
csv_content = [
    ['id', 'category_id', 'sample_name', 'split'],
    ['1', 'cat_001', 'sample_001', 'train'],
    ['2', 'cat_001', 'sample_002', 'val'],
    ['3', 'cat_001', 'sample_003', 'test'],
    ['4', 'cat_002', 'sample_004', 'train'],
    ['5', 'cat_001', 'sample_005', 'train'],
]

with open(csv_path, 'w', newline='') as f:
    writer = csv.writer(f)
    writer.writerows(csv_content)

ARGS = {
    'path': csv_path,
    'cat_id': 'cat_001',
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
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 dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
completeness Ran
ran on a synthesized input
ChrisWu1997/Multimodal-Shape-Completion/evaluation/completeness.py
code served (permissive licence) · get_code("d9b81becc9f00a0c")
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 float64, ndim 0, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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 scipy.spatial import cKDTree as KDTree

# Set seed for reproducibility
np.random.seed(0)

# Create small point clouds
# query_points: N points in 3D space
query_points = np.random.rand(2, 3).astype(np.float64)

# ref_points: M points in 3D space (different size from query for clarity)
ref_points = np.random.rand(4, 3).astype(np.float64)

# threshold parameter
thres = 0.03

ARGS = {
    "query_points": query_points,
    "ref_points": ref_points,
    "thres": thres,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float64, ndim 0, dtype family float — no output shape is stated: observe_signature.py recorded float ndim 0, which disagrees with the fixture run
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
compute_trimesh_chamfer Ran
ran on a synthesized input
ChrisWu1997/Multimodal-Shape-Completion/evaluation/chamfer.py
code served (permissive licence) · get_code("b923a8167797f225")
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 float64, ndim 0, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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

# Generate small point clouds as numpy arrays
np.random.seed(0)

# Ground truth points: 5 points in 3D space
gt_points = np.random.randn(5, 3).astype(np.float32)

# Generated points: 6 points in 3D space
gen_points = np.random.randn(6, 3).astype(np.float32)

# Offset and scale parameters
offset = 0
scale = 1

ARGS = {
    'gt_points': gt_points,
    'gen_points': gen_points,
    'offset': offset,
    'scale': scale
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float64, ndim 0, dtype family float — no output shape is stated: observe_signature.py recorded float ndim 0, which disagrees with the fixture run
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
directed_hausdorff Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
ChrisWu1997/Multimodal-Shape-Completion/evaluation/completeness.py
code served (permissive licence) · get_code("ed17c51160302eeb")
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 Tensor, ndim 0, dtype family float, shape () 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 torch

torch.manual_seed(0)

# Create two point clouds with shape (B, 3, N) and (B, 3, M)
# B=2 (batch size), 3 (coordinates), N=4 (points in cloud 1), M=5 (points in cloud 2)
point_cloud1 = torch.randn(2, 3, 4)
point_cloud2 = torch.randn(2, 3, 5)

ARGS = {
    "point_cloud1": point_cloud1,
    "point_cloud2": point_cloud2,
    "reduce_mean": True,
}
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 Tensor, ndim 0, dtype family float, shape () — shape () 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
nn_distance Ran
ran on a synthesized input
ChrisWu1997/Multimodal-Shape-Completion/evaluation/completeness.py
code served (permissive licence) · get_code("245ed591a30e6a7b")
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 (2,) 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 torch
import numpy as np
from scipy.spatial import cKDTree as KDTree

torch.manual_seed(0)

# Create small sample point clouds
# query_points: points we want to find nearest neighbors for
query_points = np.array([
    [0.0, 0.0, 0.0, 0.0],
    [1.0, 1.0, 1.0, 1.0]
], dtype=np.float64)

# ref_points: reference point cloud to search in
ref_points = np.array([
    [0.1, 0.1, 0.1, 0.1],
    [1.1, 1.1, 1.1, 1.1],
    [2.0, 2.0, 2.0, 2.0],
    [3.0, 3.0, 3.0, 3.0]
], dtype=np.float64)

ARGS = {
    "query_points": query_points,
    "ref_points": ref_points
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy, torch — 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 (2,) — shape (2,) 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
scale_to_unit_sphere Ran
ran on a synthesized input
ChrisWu1997/Multimodal-Shape-Completion/evaluation/chamfer.py
code served (permissive licence) · get_code("d59e9144167a7e71")
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 (5, 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 point cloud: 5 points in 3D space
points = np.array([
    [1.0, 2.0, 3.0],
    [4.0, 5.0, 6.0],
    [7.0, 8.0, 9.0],
    [2.0, 3.0, 4.0],
    [5.0, 6.0, 7.0]
], dtype=np.float32)

ARGS = {
    "points": points
}
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 (5, 3) — shape (5, 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

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 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, 1 later) and 5 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
collect_data_id 1 other paper
1 dated earlier
1911.10949 (2019-11)
PQ-NET: A Generative Part Seq2Seq Network for 3D Shapes
directed_hausdorff 1 other paper
1 later
136620504 (2022 (year only))
Optimization over Disentangled Encoding: Unsupervised Cross-Domain Point Cloud Completion via Occlusion Factor Manipulation

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 2026-11-21.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Several deep learning methods have been proposed for completing partial data from shape acquisition setups, i.e., filling the regions that were missing in the shape. These methods, however, only complete the partial shape with a single output, ignoring the ambiguity when reasoning the missing geometry. Hence, we pose a multi-modal shape completion problem, in which we seek to complete the partial shape with multiple outputs by learning a one-to-many mapping. We develop the first multimodal shape completion method that completes the partial shape via conditional generative modeling, without requiring paired training data. Our approach distills the ambiguity by conditioning the completion on a learned multimodal distribution of possible results. We extensively evaluate the approach on several datasets that contain varying forms of shape incompleteness, and compare among several baseline methods and variants of our methods qualitatively and quantitatively, demonstrating the merit of our method in completing partial shapes with both diversity and quality.

For agents

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

get_harvested_code_for_paper("2003.07717")
get_code_for_paper("2003.07717")
have("2003.07717")

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

curl https://syntology.ai/api/ran/2003.07717.json

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

[![Syntology run record](https://syntology.ai/api/ran/2003.07717.svg)](https://syntology.ai/paper/2003.07717)

Connect an agent — have() is free.