SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2106.04779 · CVPR · 2021

Point Cloud Upsampling via Disentangled Refinement

Ruihui Li, Chi-Wing Fu, Pheng-Ann Heng, Xianzhi Li

arXiv · PDF · Open in the Atlas

Code that ran

12 of 22 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; 1 honoured the contract we drafted, 0 violated it and 7 have no contract verdict; 4 failures of our instrument; 10 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/2106.04779.json · badge: /api/ran/2106.04779.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
liruihui/Dis-PU canonical (classifier label)
classifier basis: census
5 ran · 6 no recorded run
ryanphilly/DIS-PU-pytorch community
Papers with Code archive
7 ran · 4 no recorded run
FunctionStatusWhere it lives
Conv1d Ran
ran on a synthesized input
ryanphilly/DIS-PU-pytorch/dispu/generator.py
pointer only (licence: NONE) · get_code("6076850dcba081b0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ryanphilly/DIS-PU-pytorch when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

Conv2d Ran
ran on a synthesized input
ryanphilly/DIS-PU-pytorch/dispu/generator.py
pointer only (licence: NONE) · get_code("b0d00cfbeccb5778")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ryanphilly/DIS-PU-pytorch when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

CoordinateRegressor Ran
ran on a synthesized input
ryanphilly/DIS-PU-pytorch/dispu/generator.py
pointer only (licence: NONE) · get_code("fd692f96abf9f008")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ryanphilly/DIS-PU-pytorch when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

DuplicateUp Ran
ran on a synthesized input
ryanphilly/DIS-PU-pytorch/dispu/generator.py
pointer only (licence: NONE) · get_code("c190f988a7cfdf5e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ryanphilly/DIS-PU-pytorch when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

__batch_distance_matrix_general Ran
ran; our contract draft was wrong, not the code
ryanphilly/DIS-PU-pytorch/dispu/generator.py
pointer only (licence: NONE) · get_code("e86d5e6f0ad24ea6")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ryanphilly/DIS-PU-pytorch when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

cal_nearest_distance Ran
ran on a synthesized input
liruihui/Dis-PU/evaluate.py
code served (permissive licence) · get_code("1df94b9132c39b76")
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 sklearn.neighbors import NearestNeighbors

torch.manual_seed(0)

# Create small point cloud data
# pc: the reference point cloud (fit data)
pc = np.random.rand(5, 4).astype(np.float32)

# queries: the query points to find nearest neighbors for
queries = np.random.rand(2, 4).astype(np.float32)

# k: number of neighbors to find
k = 2

ARGS = {
    'queries': queries,
    'pc': pc,
    'k': k
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, sklearn, 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
classify_loss Ran
ran on a synthesized input
liruihui/Dis-PU/Common/loss_utils.py
code served (permissive licence) · get_code("7334175121d9a8de")
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 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 tensorflow as tf
import numpy as np

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

# Create small tensors for the function
# pre_label: logits tensor of shape (batch_size, num_classes)
batch_size = 2
num_classes = 4
pre_label = tf.constant(np.random.randn(batch_size, num_classes).astype(np.float32))

# label: integer labels tensor of shape (batch_size,) with values in [0, num_classes)
label = tf.constant(np.array([0, 2], dtype=np.int64))

ARGS = {
    "pre_label": pre_label,
    "label": label,
}
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 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
covariance_matrix Ran
ran on a synthesized input
liruihui/Dis-PU/Common/model_utils.py
code served (permissive licence) · get_code("981099922ccd7d21")
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 tensorflow as tf
import numpy as np

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

# Create a small point cloud tensor with shape [B, P, K, 3]
# B=2 (batch size)
# P=4 (number of points)
# K=3 (number of samples per point)
# 3 (coordinates: x, y, z)
pc = tf.constant(
    np.random.randn(2, 4, 3, 3).astype(np.float32),
    dtype=tf.float32
)

ARGS = {
    'pc': pc
}
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 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
euler2quat Ran
ran, honoured the contract we drafted
liruihui/Dis-PU/Common/eulerangles.py
code served (permissive licence) · get_code("2d9e8ce18f344f58")
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 (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 math
import numpy as np

# The function euler2quat takes three scalar parameters: z, y, x (Euler angles in radians)
# It performs mathematical operations on them and returns a quaternion array

ARGS = {
    'z': 0.5,
    'y': 0.3,
    'x': 0.2
}
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 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
gather_nd Ran
ran; our contract draft was wrong, not the code
ryanphilly/DIS-PU-pytorch/dispu/generator.py
pointer only (licence: NONE) · get_code("cca0f5613a67743b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ryanphilly/DIS-PU-pytorch when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

group_knn Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
ryanphilly/DIS-PU-pytorch/dispu/generator.py
pointer only (licence: NONE) · get_code("b5f6e333a67c11cf")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ryanphilly/DIS-PU-pytorch when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

mat2euler Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
liruihui/Dis-PU/Common/eulerangles.py
code served (permissive licence) · get_code("dd1f3e0945b180f2")
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, 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 math
import numpy as np

# Create a valid 3x3 rotation matrix
# Using a simple rotation matrix for testing
M = np.array([
    [0.9363, -0.3518, 0.0000],
    [0.3518, 0.9363, 0.0000],
    [0.0000, 0.0000, 1.0000]
], dtype=np.float64)

# cy_thresh can be None (will be auto-computed) or a scalar
cy_thresh = None

ARGS = {
    "M": M,
    "cy_thresh": cy_thresh
}
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, ndim 1, dtype family float — a tuple 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
DenseEdgeConv Not yet run
unverified (harvested, no recorded run)
ryanphilly/DIS-PU-pytorch/dispu/generator.py
pointer only (licence: NONE) · get_code("f618e313b23b3c52")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ryanphilly/DIS-PU-pytorch when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

FeatureExtractor Not yet run
unverified (harvested, no recorded run)
ryanphilly/DIS-PU-pytorch/dispu/generator.py
pointer only (licence: NONE) · get_code("f7a9740ea0fe2231")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ryanphilly/DIS-PU-pytorch when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

PointShuffle Not yet run
unverified (harvested, no recorded run)
ryanphilly/DIS-PU-pytorch/dispu/generator.py
pointer only (licence: NONE) · get_code("483d74fc0c6467b5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ryanphilly/DIS-PU-pytorch when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

RefinedGenerator Not yet run
unverified (harvested, no recorded run)
ryanphilly/DIS-PU-pytorch/dispu/generator.py
pointer only (licence: NONE) · get_code("82ae95410a4787b7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ryanphilly/DIS-PU-pytorch when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

dilated Not yet run
unverified (harvested, no recorded run)
liruihui/Dis-PU/gcn_lib/tf_edge.py
code served (permissive licence) · get_code("b7d5e1baa849c768")
How it ran

no invocation recorded.

euler2mat Not yet run
unverified (harvested, no recorded run)
liruihui/Dis-PU/Common/eulerangles.py
code served (permissive licence) · get_code("c895ee22fc847eed")
How it ran

no invocation recorded.

exponential_distance Not yet run
unverified (harvested, no recorded run)
liruihui/Dis-PU/Common/model_utils.py
code served (permissive licence) · get_code("1b6050f2e0623fab")
How it ran

no invocation recorded.

get_max_relat_feature Not yet run
unverified (harvested, no recorded run)
liruihui/Dis-PU/gcn_lib/tf_vertex.py
code served (permissive licence) · get_code("a413566796454bf7")
How it ran

no invocation recorded.

max_relat_conv_layer Not yet run
unverified (harvested, no recorded run)
liruihui/Dis-PU/gcn_lib/tf_vertex.py
code served (permissive licence) · get_code("5c13eeaa975af521")
How it ran

no invocation recorded.

sample_and_group_all Not yet run
unverified (harvested, no recorded run)
liruihui/Dis-PU/Common/pointnet_util.py
code served (permissive licence) · get_code("142a56400c483118")
How it ran

no invocation recorded.

Also present in other papers' code

Of 22 samples lifted from this paper's linked repositories, 22 carry a function identity and 0 do not. Of the 22 distinct functions with an identity, 7 are also present in other papers whose code we hold (7 with at least one paper dated earlier, 0 the same month, 3 later) and 15 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
sample_and_group_all 7 other papers
7 dated earlier
1803.05827 (2018-03)
Local Spectral Graph Convolution for Point Set Feature Learning
1811.07782 (2018-11)
Modeling Local Geometric Structure of 3D Point Clouds using Geo-CNN
1812.03320 (2018-12)
GSPN: Generative Shape Proposal Network for 3D Instance Segmentation in Point Cloud
and 4 more not named here
euler2mat 6 other papers
4 dated earlier, 2 later
1905.06292 (2019-05)
3D Point Cloud Generative Adversarial Network Based on Tree Structured Graph Convolutions
aaai_6994 (2020 (year only))
JSNet: Joint Instance and Semantic Segmentation of 3D Point Clouds
2001.05574 (2020-01)
Advbox: a toolbox to generate adversarial examples that fool neural networks
and 3 more not named here
euler2quat 6 other papers
4 dated earlier, 2 later
1905.06292 (2019-05)
3D Point Cloud Generative Adversarial Network Based on Tree Structured Graph Convolutions
aaai_6994 (2020 (year only))
JSNet: Joint Instance and Semantic Segmentation of 3D Point Clouds
2001.05574 (2020-01)
Advbox: a toolbox to generate adversarial examples that fool neural networks
and 3 more not named here
mat2euler 6 other papers
4 dated earlier, 2 later
1905.06292 (2019-05)
3D Point Cloud Generative Adversarial Network Based on Tree Structured Graph Convolutions
aaai_6994 (2020 (year only))
JSNet: Joint Instance and Semantic Segmentation of 3D Point Clouds
2001.05574 (2020-01)
Advbox: a toolbox to generate adversarial examples that fool neural networks
and 3 more not named here
dilated 1 other paper
1 dated earlier
1910.06849 (2019-10)
DeepGCNs: Making GCNs Go as Deep as CNNs
get_max_relat_feature 1 other paper
1 dated earlier
1910.06849 (2019-10)
DeepGCNs: Making GCNs Go as Deep as CNNs
max_relat_conv_layer 1 other paper
1 dated earlier
1910.06849 (2019-10)
DeepGCNs: Making GCNs Go as Deep as CNNs

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

Figure 1. In the top row, we show (a) a sparse real-scanned point set from [23], followed by upsampled results (16×) produced by (b) MPU [26], (c) PU-GAN [12], and (d) our method. In the bottom row, we show the associated reconstructed 3D meshes produced by the ball-pivoting algorithm [2]. Clearly, our method outperforms others on the local uniformity, contributing a better surface reconstruction.

For agents

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

get_harvested_code_for_paper("2106.04779")
get_code_for_paper("2106.04779")
have("2106.04779")

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

curl https://syntology.ai/api/ran/2106.04779.json

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

[![Syntology run record](https://syntology.ai/api/ran/2106.04779.svg)](https://syntology.ai/paper/2106.04779)

Connect an agent — have() is free.