SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1809.06267 · 2018

PointNetGPD: Detecting Grasp Configurations from Point Sets

arXiv · PDF · Open in the Atlas

Code that ran

4 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; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 4 failures of our instrument; 4 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/1809.06267.json · badge: /api/ran/1809.06267.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
hz-ants/PointNetGPD canonical (classifier label)
classifier basis: classifier_2025
2 ran · 2 no recorded run
lianghongzhuo/PointNetGPD canonical (classifier label)
classifier basis: classifier_2025
1 ran · 2 no recorded run
Hymwgk/PointNetGPD reimplementation (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
FunctionStatusWhere it lives
filterDiscontinuities Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
hz-ants/PointNetGPD/PointNetGPD/ycb_cloud_generate.py
code served (permissive licence) · get_code("b13c9c0960df9ee1")
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 (480, 640) 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 math

# Create a small depth map for testing
# The function expects a 2D or 3D array
depth_map = np.random.randint(0, 5000, size=(480, 640)).astype(np.float32)

# Add some discontinuities (large value changes) to test the filtering
depth_map[100:110, 100:110] = 6000  # Create a region with high values

ARGS = {
    "depthMap": depth_map
}
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 (480, 640) — shape (480, 640) 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_file_name Ran
ran; our contract draft was wrong, not the code
Hymwgk/PointNetGPD/apps/generate-dataset-canny.py
code served (permissive licence) · get_code("2009a9e0cd64682e")
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 os
import tempfile
import shutil

# Create a temporary directory structure for testing
temp_base = tempfile.mkdtemp()

# Create subdirectories at depth 1 (one level below temp_base)
subdir1 = os.path.join(temp_base, "subdir1")
subdir2 = os.path.join(temp_base, "subdir2")
subdir3 = os.path.join(temp_base, "subdir3")

os.makedirs(subdir1, exist_ok=True)
os.makedirs(subdir2, exist_ok=True)
os.makedirs(subdir3, exist_ok=True)

# Create a deeper subdirectory (depth 2, should not be included)
deep_subdir = os.path.join(subdir1, "deep")
os.makedirs(deep_subdir, exist_ok=True)

ARGS = {
    "file_dir_": temp_base
}
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
im2col Ran
ran; our contract draft was wrong, not the code
hz-ants/PointNetGPD/PointNetGPD/ycb_cloud_generate.py
code served (permissive licence) · get_code("eb096107619c2f49")
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 4, dtype family float, shape (7, 7, 2, 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 numpy as np
import math

# Create a simple 2D image (grayscale)
# Shape: (rows, cols)
im_2d = np.random.rand(8, 8).astype(np.float32)

# Create a 3D image (multi-channel)
# Shape: (channels, rows, cols)
im_3d = np.random.rand(3, 8, 8).astype(np.float32)

# Patch size parameter
psize = 2

# Test with 2D image
ARGS = {
    "im": im_2d,
    "psize": psize
}
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 4, dtype family float, shape (7, 7, 2, 2) — shape (7, 7, 2, 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
my_collate Ran
ran; our contract draft was wrong, not the code
lianghongzhuo/PointNetGPD/PointNetGPD/main_1v.py
code served (permissive licence) · get_code("5124350321202e42")
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 torch
import torch.utils.data

torch.manual_seed(0)

# my_collate takes a batch parameter
# The batch is a list that gets filtered for None values
# Then passed to default_collate which expects a list of samples
# Each sample should be a tuple or tensor that can be collated

# Create a simple batch with a few samples
# default_collate can handle lists of tensors or tuples of tensors
batch_samples = [
    (torch.randn(4, 3), torch.tensor(0)),
    (torch.randn(4, 3), torch.tensor(1)),
    None,  # This will be filtered out
    (torch.randn(4, 3), torch.tensor(2))
]

ARGS = {
    "batch": batch_samples
}
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 — 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
registerDepthMap Not yet run
unverified (harvested, no recorded run)
hz-ants/PointNetGPD/PointNetGPD/ycb_cloud_generate.py
code served (permissive licence) · get_code("0ea5fbc9913d70dd")
How it ran

no invocation recorded.

remove_table_points Not yet run
unverified (harvested, no recorded run)
lianghongzhuo/PointNetGPD/dex-net/apps/kinect2grasp.py
code served (permissive licence) · get_code("a2de5433924b3dfd")
How it ran

no invocation recorded.

remove_table_points Not yet run
unverified (harvested, no recorded run)
hz-ants/PointNetGPD/dex-net/apps/kinect2grasp_python2.py
code served (permissive licence) · get_code("9a9763f206f7237b")
How it ran

no invocation recorded.

test Not yet run
unverified (harvested, no recorded run)
lianghongzhuo/PointNetGPD/PointNetGPD/main_1v.py
code served (permissive licence) · get_code("51b8ec2235fca87b")
How it ran

no invocation recorded.

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, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 8 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.

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

In this paper, we propose an end-to-end grasp evaluation model to address the challenging problem of localizing robot grasp configurations directly from the point cloud. Compared to recent grasp evaluation metrics that are based on handcrafted depth features and a convolutional neural network (CNN), our proposed PointNetGPD is lightweight and can directly process the 3D point cloud that locates within the gripper for grasp evaluation. Taking the raw point cloud as input, our proposed grasp evaluation network can capture the complex geometric structure of the contact area between the gripper and the object even if the point cloud is very sparse. To further improve our proposed model, we generate a larger-scale grasp dataset with 350k real point cloud and grasps with the YCB object set for training. The performance of the proposed model is quantitatively measured both in simulation and on robotic hardware. Experiments on object grasping and clutter removal show that our proposed model generalizes well to novel objects and outperforms state-of-the-art methods. Code and video are available at \href{https://lianghongzhuo.github.io/PointNetGPD}{https://lianghongzhuo.github.io/PointNetGPD}

For agents

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

get_harvested_code_for_paper("1809.06267")
get_code_for_paper("1809.06267")
have("1809.06267")

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

curl https://syntology.ai/api/ran/1809.06267.json

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

[![Syntology run record](https://syntology.ai/api/ran/1809.06267.svg)](https://syntology.ai/paper/1809.06267)

Connect an agent — have() is free.