SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2007.11901 · 2020

Weakly Supervised 3D Object Detection from Lidar Point Cloud

arXiv · PDF · Open in the Atlas

Code that ran

4 of 4 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 2 have no contract verdict; 1 failure of our instrument; 0 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/2007.11901.json · badge: /api/ran/2007.11901.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
hlesmqh/WS3D canonical (classifier label)
classifier basis: census
4 ran · 0 no recorded run
FunctionStatusWhere it lives
cls_type_to_id Ran
ran, honoured the contract we drafted
hlesmqh/WS3D/Pointcloud_Annotation/object3d.py
code served (permissive licence) · get_code("68d59bd1b88d6e20")
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 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.

import torch

ARGS = {
    'cls_type': 'Car'
}
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 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
dist_to_plane Ran
ran on a synthesized input
hlesmqh/WS3D/Pointcloud_Annotation/kitti_utils.py
code served (permissive licence) · get_code("03cb460d47fb5a41")
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 numpy as np

# Create a plane represented as (a, b, c, d)
# Using normalized coefficients for a plane equation ax + by + cz + d = 0
plane = (1.0, 2.0, 3.0, -5.0)

# Create a set of 3D points with shape (N, 3)
# Using 4 points to have a non-trivial batch
points = np.array([
    [1.0, 2.0, 3.0],
    [0.0, 0.0, 0.0],
    [1.0, 1.0, 1.0],
    [2.0, 3.0, 4.0]
])

ARGS = {
    "plane": plane,
    "points": points
}
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
get_calib_from_file Ran
ran on a synthesized input
hlesmqh/WS3D/Pointcloud_Annotation/calibration.py
code served (permissive licence) · get_code("ebd8a3fc2a270133")
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 the expected format
temp_dir = tempfile.mkdtemp()
calib_file = os.path.join(temp_dir, "calib.txt")

with open(calib_file, 'w') as f:
    # Lines 0-1: dummy content
    f.write("P0: dummy\n")
    f.write("P1: dummy\n")
    # Line 2: P2 (3x4 = 12 values)
    f.write("P2: " + " ".join([str(i) for i in range(12)]) + "\n")
    # Line 3: P3 (3x4 = 12 values)
    f.write("P3: " + " ".join([str(i+12) for i in range(12)]) + "\n")
    # Line 4: R0 (3x3 = 9 values)
    f.write("R0: " + " ".join([str(i+24) for i in range(9)]) + "\n")
    # Line 5: Tr_velo_to_cam (3x4 = 12 values)
    f.write("Tr_velo_to_cam: " + " ".join([str(i+33) for i in range(12)]) + "\n")

ARGS = {
    "calib_file": calib_file
}
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
rotate_pc_along_y Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
hlesmqh/WS3D/Pointcloud_Annotation/kitti_utils.py
code served (permissive licence) · get_code("4b6801e509f37ef3")
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 (2, 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 numpy as np

# Create a point cloud with N=2 points, 3 spatial coordinates + 1 extra channel
# Shape: (2, 4) where first 3 columns are XYZ, last column is an extra feature
pc = np.array([
    [1.0, 2.0, 3.0, 0.5],
    [4.0, 5.0, 6.0, 0.7]
], dtype=np.float32)

# Rotation angle in radians (45 degrees)
rot_angle = np.pi / 4

ARGS = {
    "pc": pc,
    "rot_angle": rot_angle
}
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 (2, 4) — shape (2, 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

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 1 the same month, 2 later) and 1 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
cls_type_to_id 6 other papers
1 dated earlier, 5 later
2006.11275 (2020-06)
Center-based 3D Object Detection and Tracking
2203.11405 (2022-03)
Hindsight is 20/20: Leveraging Past Traversals to Aid 3D Perception
2203.15882 (2022-03)
Learning to Detect Mobile Objects from LiDAR Scans Without Labels
and 3 more not named here
get_calib_from_file 5 other papers
2 dated earlier, 1 the same month, 2 later
1812.04244 (2018-12)
PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud
2006.11275 (2020-06)
Center-based 3D Object Detection and Tracking
2007.08856 (2020-07)
EPNet: Enhancing Point Features with Image Semantics for 3D Object Detection
and 2 more not named here
rotate_pc_along_y 1 other paper
1 dated earlier
1812.04244 (2018-12)
PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud

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

It is laborious to manually label point cloud data for training high-quality 3D object detectors. This work proposes a weakly supervised approach for 3D object detection, only requiring a small set of weakly annotated scenes, associated with a few precisely labeled object instances. This is achieved by a two-stage architecture design. Stage-1 learns to generate cylindrical object proposals under weak supervision, i.e., only the horizontal centers of objects are click-annotated on bird's view scenes. Stage-2 learns to refine the cylindrical proposals to get cuboids and confidence scores, using a few well-labeled object instances. Using only 500 weakly annotated scenes and 534 precisely labeled vehicle instances, our method achieves 85-95% the performance of current top-leading, fully supervised detectors (which require 3, 712 exhaustively and precisely annotated scenes with 15, 654 instances). More importantly, with our elaborately designed network architecture, our trained model can be applied as a 3D object annotator, allowing both automatic and active working modes. The annotations generated by our model can be used to train 3D object detectors with over 94% of their original performance (under manually labeled data). Our experiments also show our model's potential in boosting performance given more training data. Above designs make our approach highly practical and introduce new opportunities for learning 3D object detection with reduced annotation burden.

For agents

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

get_harvested_code_for_paper("2007.11901")
get_code_for_paper("2007.11901")
have("2007.11901")

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

curl https://syntology.ai/api/ran/2007.11901.json

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

[![Syntology run record](https://syntology.ai/api/ran/2007.11901.svg)](https://syntology.ai/paper/2007.11901)

Connect an agent — have() is free.