SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2602.02232 · 2026

LiFlow: Flow Matching for 3D LiDAR Scene Completion

Andrea Matteazzi, Dietmar Tutsch

arXiv · PDF · Open in the Atlas

Code that ran

8 of 8 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, 2 violated it and 0 have no contract verdict; 5 failures of our instrument; 0 no recorded run), measured 2026-11-21; 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/2602.02232.json · badge: /api/ran/2602.02232.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
matteandre/LiFlow canonical (classifier label)
classifier basis: census
8 ran · 0 no recorded run
FunctionStatusWhere it lives
default Ran
ran, violated the contract we drafted
matteandre/LiFlow/liflow/utils/helpers.py
code served (permissive licence) · get_code("424012cb37b31172")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned int, ndim 0, dtype family int, 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.

from inspect import isfunction

def exists(val):
    return val is not None

def default(val, d):
    if exists(val):
        return val
    return d() if isfunction(d) else d

# Test case 1: val exists (not None), d is a regular value
ARGS_1 = {
    'val': 42,
    'd': 100
}

# Test case 2: val is None, d is a regular value
ARGS_2 = {
    'val': None,
    'd': 100
}

# Test case 3: val is None, d is a function
def default_func():
    return 200

ARGS_3 = {
    'val': None,
    'd': default_func
}

# Test case 4: val exists, d is a function
ARGS_4 = {
    'val': "existing_value",
    'd': lambda: "default_value"
}

# Use one of the test cases as the final ARGS
ARGS = ARGS_3
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
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 int, ndim 0, dtype family int, 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
exists Ran
ran, violated the contract we drafted
matteandre/LiFlow/liflow/utils/helpers.py
pointer only (licence: MIT); the stored copy get_code serves, from ThomasMrY/VCT, is pointer only (licence: NONE) · get_code("aa5486a3650902d8")
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 ThomasMrY/VCT, 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.

get_state_dict Ran
ran; our contract draft was wrong, not the code
matteandre/LiFlow/liflow/models/ema_callback.py
code served (permissive licence) · get_code("b6c2e47cefdfee80")
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 OrderedDict. 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 torch.nn as nn

torch.manual_seed(0)

# Build a simple model
class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)
    
    def forward(self, x):
        return self.linear(x)

# Test case 1: Plain model
plain_model = SimpleModel()

# Test case 2: Model wrapped with 'module' attribute (e.g., DataParallel)
wrapped_model = SimpleModel()
wrapper = nn.Module()
wrapper.module = wrapped_model

# Test case 3: Model wrapped with '_orig_mod' attribute (e.g., torch.compile or torch._dynamo)
compiled_model = SimpleModel()
wrapper2 = nn.Module()
wrapper2._orig_mod = compiled_model

# Default unwrap function
def default_unwrap(model):
    if hasattr(model, 'module'):
        return default_unwrap(model.module)
    elif hasattr(model, '_orig_mod'):
        return default_unwrap(model._orig_mod)
    else:
        return model

ARGS = {
    'model': plain_model,
    'unwrap_fn': default_unwrap
}
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 OrderedDict — a OrderedDict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a OrderedDict 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
load_poses Ran
ran, honoured the contract we drafted
matteandre/LiFlow/liflow/utils/eval_path.py
code served (permissive licence) · get_code("21cd8e2f060ce50c")
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 3, 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 numpy as np
import tempfile

# Create temporary calibration file
calib_content = """Tr: 1.0 0.0 0.0 0.5 0.0 1.0 0.0 0.2 0.0 0.0 1.0 0.1"""
calib_file = tempfile.NamedTemporaryFile(mode='w', suffix='.txt', delete=False)
calib_file.write(calib_content)
calib_file.close()
calib_fname = calib_file.name

# Create temporary poses file
poses_content = """1.0 0.0 0.0 1.0 0.0 1.0 0.0 2.0 0.0 0.0 1.0 3.0
0.9 0.1 0.0 1.5 -0.1 0.9 0.0 2.5 0.0 0.0 1.0 3.5"""
poses_file = tempfile.NamedTemporaryFile(mode='w', suffix='.txt', delete=False)
poses_file.write(poses_content)
poses_file.close()
poses_fname = poses_file.name

ARGS = {
    'calib_fname': calib_fname,
    'poses_fname': poses_fname,
}
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 list, ndim 3, 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
parse_calibration Ran
ran; our contract draft was wrong, not the code
matteandre/LiFlow/liflow/utils/eval_path.py
code served (permissive licence) · get_code("b39e1616e4146e48")
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 tempfile
import os

# Create a temporary calibration file with valid content
temp_dir = tempfile.mkdtemp()
calib_filename = os.path.join(temp_dir, "calib.txt")

# Write a sample calibration file
with open(calib_filename, 'w') as f:
    f.write("P0: 1.0 2.0 3.0 4.0 5.0 6.0 7.0 8.0 9.0 10.0 11.0 12.0\n")
    f.write("P1: 0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.8 0.9 1.0 1.1 1.2\n")

ARGS = {
    "filename": calib_filename
}
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 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
point_set_to_sparse_refine Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
matteandre/LiFlow/liflow/utils/collations.py
code served (permissive licence) · get_code("bd5b67e3b147a989")
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. 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
import torch

torch.manual_seed(0)

# Create small numpy arrays for p_full and p_part
# p_full and p_part need to be numpy arrays that support indexing and repeat
p_full = np.random.randn(2, 4).astype(np.float32)  # shape (2, 4)
p_part = np.random.randn(3, 4).astype(np.float32)  # shape (3, 4)

# Set the target counts
n_full = 5
n_part = 7

# Set a dummy filename
filename = "test_output.txt"

ARGS = {
    "p_full": p_full,
    "p_part": p_part,
    "n_full": n_full,
    "n_part": n_part,
    "filename": filename
}
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 list — a list 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
un_normalize_ims Ran
ran; our contract draft was wrong, not the code
matteandre/LiFlow/liflow/utils/helpers.py
code served (permissive licence) · get_code("62851b601300e572")
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 4, dtype family int, shape (2, 3, 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 torch

torch.manual_seed(0)

# Create a small tensor in [-1, 1] range to test un_normalize_ims
# Shape: (2, 3, 4, 4) - batch of 2, 3 channels, 4x4 spatial dims
ims = torch.randn(2, 3, 4, 4) * 0.5  # scale to roughly [-0.5, 0.5] to stay in [-1, 1]
ims = ims.clamp(-1, 1)  # ensure it's in [-1, 1] range

ARGS = {
    "ims": ims
}
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 4, dtype family int, shape (2, 3, 4, 4) — shape (2, 3, 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
unwrap_model Ran
ran; our contract draft was wrong, not the code
matteandre/LiFlow/liflow/models/ema_callback.py
code served (permissive licence) · get_code("9603dea3759c2ec7")
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 SimpleModel. 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 torch.nn as nn

torch.manual_seed(0)

# Create a simple base model
class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)
    
    def forward(self, x):
        return self.linear(x)

# Test case 1: Model with 'module' attribute (DataParallel wrapped)
base_model = SimpleModel()
wrapped_with_module = nn.Module()
wrapped_with_module.module = base_model

# Test case 2: Model with '_orig_mod' attribute (torch.compile wrapped)
base_model2 = SimpleModel()
wrapped_with_orig_mod = nn.Module()
wrapped_with_orig_mod._orig_mod = base_model2

# Test case 3: Unwrapped model
unwrapped_model = SimpleModel()

# Use the wrapped_with_module as the test case
model = wrapped_with_module

ARGS = {
    'model': model
}
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 SimpleModel — a SimpleModel output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a SimpleModel 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

Also present in other papers' code

Of 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 distinct functions with an identity, 5 are also present in other papers whose code we hold (5 with at least one paper dated earlier, 2 the same month, 2 later) and 3 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
exists 486 other papers
468 dated earlier, 7 the same month, 9 later, 2 undated · 78 only as an assembly brick
1603.08155 (2016-03)
Perceptual Losses for Real-Time Style Transfer and Super-Resolution
1611.07004 (2016-11)
Image-to-Image Translation with Conditional Adversarial Networks
1804.04637 (2018-04)
EMBER: An Open Dataset for Training Static PE Malware Machine Learning Models
and 483 more not named here
default 207 other papers
202 dated earlier, 2 the same month, 3 later · 41 only as an assembly brick
1711.11585 (2017-11)
High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs
2006.11239 (2020-06)
Denoising Diffusion Probabilistic Models
2010.08162 (2020-10)
SidechainNet: An All-Atom Protein Structure Dataset for Machine Learning
and 204 more not named here
parse_calibration 6 other papers
6 dated earlier
1904.01416 (2019-04)
SemanticKITTI: A Dataset for Semantic Scene Understanding of LiDAR Sequences
2204.08084 (2022-04)
Learning 3D Semantics from Pose-Noisy 2D Images with Hierarchical Full Attention Network
2206.00927 (2022-06)
DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps
and 3 more not named here
get_state_dict 3 other papers
3 dated earlier
Tang_Progressive_Attention_on_Multi-Level_Dense_Difference_Maps_for_Generic_Event_CVPR_2022_paper (2022 (year only))
Progressive Attention on Multi-Level Dense Difference Maps for Generic Event Boundary Detection
2212.04129 (2022-12)
Deep Incubation: Training Large Models by Divide-and-Conquering
2309.17002 (2023-09)
Understanding and Mitigating the Label Noise in Pre-training on Downstream Tasks
load_poses 2 other papers
2 dated earlier
2403.13470 (2024-03)
Scaling Diffusion Models to Real-World 3D LiDAR Scene Completion
2503.21449 (2025-03)
Towards Generating Realistic 3D Semantic Training Data for Autonomous Driving

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

In autonomous driving scenarios, the collected LiDAR point clouds can be challenged by occlusion and long-range sparsity, limiting the perception of autonomous driving systems. Scene completion methods can infer the missing parts of incomplete 3D LiDAR scenes. Recent methods adopt local point-level denoising diffusion probabilistic models, which require predicting Gaussian noise, leading to a mismatch between training and inference initial distributions. This paper introduces the first flow matching framework for 3D LiDAR scene completion, improving upon diffusion-based methods by ensuring consistent initial distributions between training and inference. The model employs a nearest neighbor flow matching loss and a Chamfer distance loss to enhance both local structure and global coverage in the alignment of point clouds. LiFlow achieves state-of-the-art performance across multiple metrics. Code: https://github.com/matteandre/LiFlow.

For agents

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

get_harvested_code_for_paper("2602.02232")
get_code_for_paper("2602.02232")
have("2602.02232")

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

curl https://syntology.ai/api/ran/2602.02232.json

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

[![Syntology run record](https://syntology.ai/api/ran/2602.02232.svg)](https://syntology.ai/paper/2602.02232)

Connect an agent — have() is free.