SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2003.05855 · 2020

End-to-End Learning Local Multi-view Descriptors for 3D Point Clouds

arXiv · PDF · Open in the Atlas

Code that ran

12 of 13 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, 1 violated it and 10 have no contract verdict; 1 failure of our instrument; 1 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/2003.05855.json · badge: /api/ran/2003.05855.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
craigleili/3DLocalMultiViewDesc community (classifier label)
classifier basis not recorded on the link
12 ran · 1 no recorded run
FunctionStatusWhere it lives
batch_hard_mining Ran
ran on a synthesized input
craigleili/3DLocalMultiViewDesc/utils/loss.py
code served (permissive licence) · get_code("c3c83a875df07fc9")
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 2, 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

torch.manual_seed(0)

# Create a small distance matrix (4x4)
# This is a pairwise distance matrix between 4 samples
dist_mat = torch.tensor([
    [0.0, 1.5, 2.0, 3.5],
    [1.5, 0.0, 2.5, 3.0],
    [2.0, 2.5, 0.0, 1.2],
    [3.5, 3.0, 1.2, 0.0]
], dtype=torch.float32)

# Create labels for the 4 samples
# Labels indicate which class each sample belongs to
# We use at least 2 classes so we have both positive and negative pairs
labels = torch.tensor([0, 0, 1, 1], dtype=torch.long)

ARGS = {
    'dist_mat': dist_mat,
    'labels': labels
}
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 2, 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
batch_hard_negative_mining Ran
ran on a synthesized input
craigleili/3DLocalMultiViewDesc/utils/loss.py
code served (permissive licence) · get_code("f854ed3d229aea10")
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 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 torch

torch.manual_seed(0)

# The function expects dist_mat to be a square tensor (M x N where M == N)
# It computes pairwise distances and performs hard negative mining
# We need a square distance matrix
dist_mat = torch.rand(4, 4)

ARGS = {
    "dist_mat": dist_mat
}
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 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
get_norm2d Ran
ran on a synthesized input
craigleili/3DLocalMultiViewDesc/models/modules.py
code served (permissive licence) · get_code("80895a2fe2ffab06")
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 partial. 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
import functools

torch.manual_seed(0)

ARGS = {
    'norm_type': 'instance_norm',
    'trainable': False,
}
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 partial — a partial output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a partial 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
init_eye_xyz_coords Ran
ran on a synthesized input
craigleili/3DLocalMultiViewDesc/soft_renderer/transform.py
code served (permissive licence) · get_code("1b945506cf65c5f5")
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 math
import numpy as np

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

# Define ARGS dict with all parameters for init_eye_xyz_coords
ARGS = {
    "num_views": 5,
    "rho_min": 0.3,
    "rho_max": 1.0,
    "phi_min": 0.0,
    "phi_max": math.pi / 2.0,
    "theta_min": 0.0,
    "theta_max": 2.0 * math.pi,
}
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
is_batchnorm Ran
ran on a synthesized input
craigleili/3DLocalMultiViewDesc/models/modules.py
code served (permissive licence) · get_code("0298a16be4d1826f")
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 functools
import torch
import torch.nn as nn

torch.manual_seed(0)

# Test case 1: functools.partial wrapping BatchNorm2d
partial_bn = functools.partial(nn.BatchNorm2d)

# Test case 2: Direct BatchNorm2d class
direct_bn = nn.BatchNorm2d

# Test case 3: An instance of BatchNorm2d
bn_instance = nn.BatchNorm2d(num_features=3)

# Test case 4: A different norm layer (not BatchNorm2d)
other_norm = nn.LayerNorm

ARGS = {
    "norm_layer": partial_bn
}
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 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
is_number Ran
ran, violated the contract we drafted
craigleili/3DLocalMultiViewDesc/utils/io.py
pointer only (licence: MIT); the stored copy get_code serves, from RikVN/AMR, is pointer only (licence: NONE) · get_code("e18607dae38b30e2")
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 RikVN/AMR, 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.

may_create_folder Ran
ran on a synthesized input
craigleili/3DLocalMultiViewDesc/utils/io.py
code served (permissive licence) · get_code("648bf341417d98d7")
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 os
import os.path as osp
import tempfile

# Create a temporary directory path that doesn't exist yet
temp_base = tempfile.gettempdir()
test_folder = osp.join(temp_base, "test_folder_" + str(os.getpid()) + "_unique")

# Ensure the folder doesn't exist before testing
if osp.exists(test_folder):
    import shutil
    shutil.rmtree(test_folder)

ARGS = {
    "folder_path": test_folder
}
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 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
pairwise_distance_matrix Ran
ran on a synthesized input
craigleili/3DLocalMultiViewDesc/utils/loss.py
code served (permissive licence) · get_code("e56dac6b186a1209")
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 2, dtype family float, shape (2, 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 torch

torch.manual_seed(0)

# Create small tensors with distinct dimensions
# x: (2, 4) - 2 points in 4D space
# y: (3, 4) - 3 points in 4D space
x = torch.randn(2, 4)
y = torch.randn(3, 4)

ARGS = {
    "x": x,
    "y": y,
    "eps": 1e-06
}
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 2, dtype family float, shape (2, 3) — shape (2, 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
read_descriptors Ran
ran on a synthesized input
craigleili/3DLocalMultiViewDesc/evaluation/eval_geomreg_3dmatch.py
code served (permissive licence) · get_code("b5cfccb952c002e3")
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 (128, 256) 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
import os.path as osp
import tempfile
import os

# Create a temporary directory structure for testing
temp_dir = tempfile.mkdtemp()
scene_name = "test_scene"
seq_name = "test_seq"
pcd_name = "test_pcd"

# Create the necessary directory structure
scene_dir = osp.join(temp_dir, scene_name)
seq_dir = osp.join(scene_dir, seq_name)
os.makedirs(seq_dir, exist_ok=True)

# Create a dummy descriptor file
dummy_descs = np.random.rand(128, 256).astype(np.float32)
filepath = osp.join(seq_dir, pcd_name + '.desc.npy')
np.save(filepath, dummy_descs)

ARGS = {
    'desc_type': 'MVPoolNet',
    'root_dir': temp_dir,
    'scene_name': scene_name,
    'seq_name': seq_name,
    'pcd_name': pcd_name
}
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 (128, 256) — shape (128, 256) 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
read_keypoints Ran
ran on a synthesized input
craigleili/3DLocalMultiViewDesc/evaluation/eval_geomreg_3dmatch.py
code served (permissive licence) · get_code("2c276bf210860f63")
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 3, dtype family float, shape (2, 4, 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
import tempfile
import os

# Create a temporary directory and file
temp_dir = tempfile.mkdtemp()
temp_filepath = os.path.join(temp_dir, "keypoints.npy")

# Create sample keypoints data and save it
sample_keypoints = np.random.rand(2, 4, 3).astype(np.float32)
np.save(temp_filepath, sample_keypoints)

# Define arguments for read_keypoints
ARGS = {
    "filepath": temp_filepath
}
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 3, dtype family float, shape (2, 4, 3) — shape (2, 4, 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
sorted_alphanum Ran
ran; our contract draft was wrong, not the code
craigleili/3DLocalMultiViewDesc/utils/io.py
code served (permissive licence) · get_code("c9489b6bb295599d")
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 re

def sorted_alphanum(file_list_ordered):
    convert = lambda text: int(text) if text.isdigit() else text
    alphanum_key = lambda key: [convert(c) for c in re.split('([0-9]+)', key) if len(c) > 0]
    return sorted(file_list_ordered, key=alphanum_key)

ARGS = {
    "file_list_ordered": [
        "file10.txt",
        "file2.txt",
        "file1.txt",
        "image100.png",
        "image20.png",
        "image3.png",
        "doc_v5.pdf",
        "doc_v15.pdf",
        "doc_v2.pdf"
    ]
}
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
spherical_to_xyz_coords Ran
ran on a synthesized input
craigleili/3DLocalMultiViewDesc/soft_renderer/transform.py
code served (permissive licence) · get_code("e6c7e2af4aeb190c")
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 3, dtype family float, shape (2, 3, 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 small spherical coordinate tensors
# rho: radial distance (batch_size=2, features=4)
rho = torch.rand(2, 4)

# phi: polar angle (batch_size=2, features=4)
phi = torch.rand(2, 4) * torch.pi

# theta: azimuthal angle (batch_size=2, features=4)
theta = torch.rand(2, 4) * 2 * torch.pi

ARGS = {
    "rho": rho,
    "phi": phi,
    "theta": theta
}
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 3, dtype family float, shape (2, 3, 4) — shape (2, 3, 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
rotate_about Not yet run
unverified (harvested, no recorded run)
craigleili/3DLocalMultiViewDesc/soft_renderer/transform.py
code served (permissive licence) · get_code("5925dfa9f6475ed2")
How it ran

no invocation recorded.

Also present in other papers' code

Of 13 samples lifted from this paper's linked repositories, 13 carry a function identity and 0 do not. Of the 13 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, 2 later) and 11 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
is_number 13 other papers
2 dated earlier, 10 later, 1 undated
1202.3665 (2012-02)
emcee: The MCMC Hammer
1705.09980 (2017-05)
Neural Semantic Parsing by Character-based Translation: Experiments with Abstract Meaning Representations
2009.11407 (2020-09)
Steering a Historical Disease Forecasting Model Under a Pandemic: Case of Flu and COVID-19
and 10 more not named here
sorted_alphanum 1 other paper
1 later
Zhang_Point_Cloud_Upsampling_Using_Conditional_Diffusion_Module_with_Adaptive_Noise_CVPR_2025_paper (2025 (year only))
Point Cloud Upsampling Using Conditional Diffusion Module with Adaptive Noise Suppression

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 this work, we propose an end-to-end framework to learn local multi-view descriptors for 3D point clouds. To adopt a similar multi-view representation, existing studies use hand-crafted viewpoints for rendering in a preprocessing stage, which is detached from the subsequent descriptor learning stage. In our framework, we integrate the multi-view rendering into neural networks by using a differentiable renderer, which allows the viewpoints to be optimizable parameters for capturing more informative local context of interest points. To obtain discriminative descriptors, we also design a soft-view pooling module to attentively fuse convolutional features across views. Extensive experiments on existing 3D registration benchmarks show that our method outperforms existing local descriptors both quantitatively and qualitatively.

For agents

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

get_harvested_code_for_paper("2003.05855")
get_code_for_paper("2003.05855")
have("2003.05855")

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

curl https://syntology.ai/api/ran/2003.05855.json

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

[![Syntology run record](https://syntology.ai/api/ran/2003.05855.svg)](https://syntology.ai/paper/2003.05855)

Connect an agent — have() is free.