SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1808.00671 · 2018

PCN: Point Completion Network

arXiv · PDF · Open in the Atlas

Code that ran

5 of 10 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 4 have no contract verdict; 1 failure of our instrument; 5 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/1808.00671.json · badge: /api/ran/1808.00671.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
wentaoyuan/pcn canonical (classifier label)
classifier basis: census
5 ran · 5 no recorded run
FunctionStatusWhere it lives
bbox2rt Ran
ran on a synthesized input
wentaoyuan/pcn/kitti_registration.py
code served (permissive licence) · get_code("28f4acff9940aff5")
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

# bbox2rt expects a numpy array with shape (4, 2) or similar
# It calls .min(0), .max(0), and indexes with [3, 1], [0, 1], [3, 0], [0, 0]
# So it needs at least 4 rows and 2 columns

# Create a simple bounding box: 4 corner points in 2D
bbox = np.array([
    [0.0, 0.0],   # bottom-left
    [2.0, 0.0],   # bottom-right
    [2.0, 1.0],   # top-right
    [0.0, 1.0]    # top-left
], dtype=np.float32)

ARGS = {
    "bbox": bbox
}
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
point_maxpool Ran
ran on a synthesized input
wentaoyuan/pcn/tf_util.py
code served (permissive licence) · get_code("adedca45af78a404")
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 2, dtype family float, shape (4, 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

# Create a small input tensor
# The function splits inputs along axis=1 based on npts, then reduces each split along axis=1
# Shape: (batch_size, total_points, features)
batch_size = 2
total_points = 6
features = 4

inputs = tf.constant(np.random.randn(batch_size, total_points, features), dtype=tf.float32)

# npts defines how to split the inputs along axis=1
# It should be a list/array of integers that sum to total_points
npts = [2, 4]  # Split into two groups: 2 points and 4 points

# keepdims parameter controls whether reduced dimension is kept
keepdims = False

ARGS = {
    "inputs": inputs,
    "npts": npts,
    "keepdims": keepdims
}
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 2, dtype family float, shape (4, 4) — shape (4, 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
resample_pcd Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
wentaoyuan/pcn/data_util.py
code served (permissive licence) · get_code("bf448dc3fba4f7fc")
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 point cloud array with shape (num_points, num_dimensions)
# Using 7 points with 3 spatial dimensions
pcd = np.random.randn(7, 3).astype(np.float32)

# Target number of points to resample to
n = 5

ARGS = {
    "pcd": pcd,
    "n": n,
}
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
rotation_error Ran
ran on a synthesized input
wentaoyuan/pcn/kitti_registration.py
code served (permissive licence) · get_code("a05abe42947793d6")
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

# Create two valid rotation matrices
# A rotation matrix is 3x3 and orthogonal
def create_rotation_matrix(angle):
    """Create a simple 3x3 rotation matrix around z-axis"""
    c = np.cos(angle)
    s = np.sin(angle)
    return np.array([
        [c, -s, 0],
        [s, c, 0],
        [0, 0, 1]
    ], dtype=np.float64)

R1 = create_rotation_matrix(0.1)
R2 = create_rotation_matrix(0.2)

ARGS = {
    "R1": R1,
    "R2": R2
}
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 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
within_bbox Ran
ran on a synthesized input
wentaoyuan/pcn/kitti_util/process_kitti_raw.py
code served (permissive licence) · get_code("84d9397ae4c43c26")
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 bool, 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 numpy as np

# Construct arguments for within_bbox function
# The function takes a point and a bbox (bounding box)
# point should be a 1D array that can be compared via dot products
# bbox should be a 2D array with at least 5 rows (indexed at 0, 1, 3, 4)

# Create a simple bounding box as a 5x3 array
# Each row represents a corner or edge definition of the bbox
bbox = np.array([
    [0.0, 0.0, 0.0],      # bbox[0, :] - reference point
    [1.0, 1.0, 1.0],      # bbox[1, :]
    [2.0, 2.0, 2.0],      # bbox[2, :]
    [3.0, 3.0, 3.0],      # bbox[3, :] - opposite corner
    [0.0, 0.0, 3.0],      # bbox[4, :]
], dtype=np.float64)

# Create a point that is inside the bounding box
# This point should satisfy all the conditions in the function
point = np.array([1.5, 0.5, 1.5], dtype=np.float64)

ARGS = {
    "point": point,
    "bbox": bbox,
}
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 bool, 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
get_queued_data Not yet run
unverified (harvested, no recorded run)
wentaoyuan/pcn/data_util.py
code served (permissive licence) · get_code("999d044322f6d060")
How it ran

no invocation recorded.

mlp Not yet run
unverified (harvested, no recorded run)
wentaoyuan/pcn/tf_util.py
code served (permissive licence) · get_code("873d33260cb6137a")
How it ran

no invocation recorded.

mlp_conv Not yet run
unverified (harvested, no recorded run)
wentaoyuan/pcn/tf_util.py
code served (permissive licence) · get_code("c4e230ca9f043a59")
How it ran

no invocation recorded.

parseXML Not yet run
unverified (harvested, no recorded run)
wentaoyuan/pcn/kitti_util/parse_tracklet_xml.py
code served (permissive licence) · get_code("ea7b718cfbcf21ac")
How it ran

no invocation recorded.

register Not yet run
unverified (harvested, no recorded run)
wentaoyuan/pcn/kitti_registration.py
code served (permissive licence) · get_code("079447ff7ae596e5")
How it ran

no invocation recorded.

Also present in other papers' code

Of 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 10 distinct functions with an identity, 1 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 1 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
resample_pcd 4 other papers
4 later
1912.00280 (2019-12)
Morphing and Sampling Network for Dense Point Cloud Completion
2112.05324 (2021-12)
Attention-based Transformation from Latent Features to Point Clouds
2212.00564 (2022-12)
Leveraging Single-View Images for Unsupervised 3D Point Cloud Completion
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

Shape completion, the problem of estimating the complete geometry of objects from partial observations, lies at the core of many vision and robotics applications. In this work, we propose Point Completion Network (PCN), a novel learning-based approach for shape completion. Unlike existing shape completion methods, PCN directly operates on raw point clouds without any structural assumption (e.g. symmetry) or annotation (e.g. semantic class) about the underlying shape. It features a decoder design that enables the generation of fine-grained completions while maintaining a small number of parameters. Our experiments show that PCN produces dense, complete point clouds with realistic structures in the missing regions on inputs with various levels of incompleteness and noise, including cars from LiDAR scans in the KITTI dataset.

For agents

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

get_harvested_code_for_paper("1808.00671")
get_code_for_paper("1808.00671")
have("1808.00671")

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

curl https://syntology.ai/api/ran/1808.00671.json

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

[![Syntology run record](https://syntology.ai/api/ran/1808.00671.svg)](https://syntology.ai/paper/1808.00671)

Connect an agent — have() is free.