SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2304.01529 · CVPR · 2023

IterativePFN: True Iterative Point Cloud Filtering

Gang Li, Ying He, Xuequan Lu, Zhiwen Shao, Dasith De Silva Edirimuni, Antonio Robles-Kelly

arXiv · PDF · Open in the Atlas

Code that ran

9 of 9 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, 1 violated it and 4 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/2304.01529.json · badge: /api/ran/2304.01529.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
ddsediri/IterativePFN canonical (classifier label)
classifier basis not recorded on the link
9 ran · 0 no recorded run
FunctionStatusWhere it lives
get_random_indices Ran
ran, honoured the contract we drafted
ddsediri/IterativePFN/models/denoise.py
code served (permissive licence) · get_code("41293a8736cbaded")
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 int, shape (5,) 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

np.random.seed(0)

# Read the function signature:
# def get_random_indices(n, m):
#   assert m < n
#   return np.random.permutation(n)[:m]
#
# Parameters:
# - n: an integer (size of permutation)
# - m: an integer (number of indices to select, must be < n)

ARGS = {
    "n": 10,
    "m": 5
}
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 int, shape (5,) — shape (5,) 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
int_list Ran
ran on a synthesized input
ddsediri/IterativePFN/utils/misc.py
code served (permissive licence) · get_code("acde8f49c7874fc4")
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 int; 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 torch

torch.manual_seed(0)

argstr = "1,2,3,4,5"

ARGS = {
    "argstr": argstr
}
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 list, ndim 1, dtype family int — 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
int_tuple Ran
ran on a synthesized input
ddsediri/IterativePFN/utils/misc.py
code served (permissive licence) · get_code("970334367a29c358")
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 int; 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 torch
import numpy as np

torch.manual_seed(0)

def int_tuple(argstr):
    return tuple(map(int, argstr.split(',')))

# The function takes a single parameter 'argstr' which should be a string
# containing comma-separated integers. It splits the string by commas and
# converts each element to an integer, returning a tuple.

argstr = "1,2,3,4,5"

ARGS = {
    'argstr': argstr
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — 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 int — 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
load_xyz Ran
ran on a synthesized input
ddsediri/IterativePFN/Evaluate.py
code served (permissive licence) · get_code("96f7a7726dfdfdc1")
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 os
import torch
import numpy as np
import tempfile
import shutil

torch.manual_seed(0)

# Create a temporary directory with sample .xyz files
temp_dir = tempfile.mkdtemp()

# Create sample xyz files with point cloud data
xyz_file_1 = os.path.join(temp_dir, "cloud_001.xyz")
xyz_file_2 = os.path.join(temp_dir, "cloud_002.xyz")

# Write sample point cloud data (3D points)
np.savetxt(xyz_file_1, np.random.rand(5, 3).astype(np.float32))
np.savetxt(xyz_file_2, np.random.rand(7, 3).astype(np.float32))

ARGS = {
    'xyz_dir': temp_dir
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch, tqdm — 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
normalize_pcl Ran
ran, violated the contract we drafted
ddsediri/IterativePFN/models/utils.py
pointer only (licence: MIT); the stored copy get_code serves, from tsingyuanchou/3dmambaipf, is pointer only (licence: NONE) · get_code("00b7c7b7d0d4baa6")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from tsingyuanchou/3dmambaipf, and GitHub detected no licence in that repository 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.

normalize_sphere Ran
ran; our contract draft was wrong, not the code
ddsediri/IterativePFN/models/utils.py
code served (permissive licence) · get_code("af412556c59dc503")
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 torch

torch.manual_seed(0)

# Create a batch of point clouds: (B, N, 3)
# B=2 (batch size), N=4 (number of points), 3 (x, y, z coordinates)
pc = torch.randn(2, 4, 3)

ARGS = {
    "pc": pc,
    "radius": 1.0,
}
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 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
normalize_std Ran
ran; our contract draft was wrong, not the code
ddsediri/IterativePFN/models/utils.py
pointer only (licence: MIT); the stored copy get_code serves, from tsingyuanchou/3dmambaipf, is pointer only (licence: NONE) · get_code("6424208301908b85")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from tsingyuanchou/3dmambaipf, and GitHub detected no licence in that repository 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.

standard_train_transforms Ran
ran; our contract draft was wrong, not the code
ddsediri/IterativePFN/utils/transforms.py
code served (permissive licence) · get_code("79881c479bc748bf")
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 Compose. 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 torch
import random
import math

torch.manual_seed(0)
random.seed(0)

ARGS = {
    'noise_std_min': 0.01,
    'noise_std_max': 0.05,
    'scale_d': 0.2,
    'rotate': True
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, torchvision — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Compose — a Compose output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Compose 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
str_tuple Ran
ran on a synthesized input
ddsediri/IterativePFN/utils/misc.py
code served (permissive licence) · get_code("57a483509c3a7357")
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 torch

def str_tuple(argstr):
    return tuple(argstr.split(','))

ARGS = {
    'argstr': 'apple,banana,cherry'
}
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 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

Also present in other papers' code

Of 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 distinct functions with an identity, 5 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 5 later) and 4 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
get_random_indices 2 other papers
2 later
2404.05522 (2024-04)
3DMambaIPF: A State Space Model for Iterative Point Cloud Filtering via Differentiable Rendering
2405.08322 (2024-05)
StraightPCF: Straight Point Cloud Filtering
normalize_sphere 2 other papers
2 later
2404.05522 (2024-04)
3DMambaIPF: A State Space Model for Iterative Point Cloud Filtering via Differentiable Rendering
2405.08322 (2024-05)
StraightPCF: Straight Point Cloud Filtering
standard_train_transforms 2 other papers
1 dated earlier, 1 later
2203.05940 (2022-03)
PD-Flow: A Point Cloud Denoising Framework with Normalizing Flows
Mao_Denoising_Point_Clouds_in_Latent_Space_via_Graph_Convolution_and_CVPR_2024_paper (2024 (year only))
Denoising Point Clouds in Latent Space via Graph Convolution and Invertible Neural Network
normalize_pcl 1 other paper
1 later
2404.05522 (2024-04)
3DMambaIPF: A State Space Model for Iterative Point Cloud Filtering via Differentiable Rendering
normalize_std 1 other paper
1 later
2404.05522 (2024-04)
3DMambaIPF: A State Space Model for Iterative Point Cloud Filtering via Differentiable Rendering

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

The quality of point clouds is often limited by noise introduced during their capture process. Consequently, a fundamental 3D vision task is the removal of noise, known as point cloud filtering or denoising. State-of-the-art learning based methods focus on training neural networks to infer filtered displacements and directly shift noisy points onto the underlying clean surfaces. In high noise conditions, they iterate the filtering process. However, this iterative filtering is only done at test time and is less effective at ensuring points converge quickly onto the clean surfaces. We propose It-erativePFN (iterative point cloud filtering network), which consists of multiple IterationModules that model the true iterative filtering process internally, within a single network. We train our IterativePFN network using a novel loss function that utilizes an adaptive ground truth target at each iteration to capture the relationship between intermediate filtering results during training. This ensures that the filtered results converge faster to the clean surfaces. Our method is able to obtain better performance compared to state-of-theart methods. The source code can be found at: https: //github.com/ddsediri/IterativePFN .

For agents

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

get_harvested_code_for_paper("2304.01529")
get_code_for_paper("2304.01529")
have("2304.01529")

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

curl https://syntology.ai/api/ran/2304.01529.json

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

[![Syntology run record](https://syntology.ai/api/ran/2304.01529.svg)](https://syntology.ai/paper/2304.01529)

Connect an agent — have() is free.