SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2407.08366 · ECCV · 2024

An Economic Framework for 6-DoF Grasp Detection

Xiao-Ming Wu, Wei-Shi Zheng, Jia-Feng Cai, Jian-Jian Jiang, Dian Zheng, Yi-Lin Wei

arXiv · PDF · Open in the Atlas

Code that ran

7 of 7 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 0 have no contract verdict; 6 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/2407.08366.json · badge: /api/ran/2407.08366.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
iSEE-Laboratory/EconomicGrasp canonical (classifier label)
classifier basis: census
7 ran · 0 no recorded run
FunctionStatusWhere it lives
batch_viewpoint_params_to_matrix Ran
ran; our contract draft was wrong, not the code
iSEE-Laboratory/EconomicGrasp/utils/loss_utils.py
code served (permissive licence) · get_code("84c2545d9172caa0")
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, 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)

# batch_towards: [torch.FloatTensor, (N,3)] - approach vectors in batch
# batch_angle: [torch.FloatTensor, (N,)] - in-plane rotation angles in batch

batch_size = 2
batch_towards = torch.randn(batch_size, 3, dtype=torch.float32)
batch_angle = torch.randn(batch_size, dtype=torch.float32)

ARGS = {
    "batch_towards": batch_towards,
    "batch_angle": batch_angle,
}
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, 3) — shape (2, 3, 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
collate_fn Ran
ran, honoured the contract we drafted
iSEE-Laboratory/EconomicGrasp/dataset/graspnet_dataset.py
code served (permissive licence) · get_code("78e44f3729f4608a")
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, 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
import numpy as np
import collections.abc as container_abcs

torch.manual_seed(0)

# Test case 1: batch of numpy arrays
numpy_batch = [np.array([1, 2, 3, 4], dtype=np.float32), 
               np.array([5, 6, 7, 8], dtype=np.float32)]

ARGS = {
    'batch': numpy_batch
}
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 Tensor, 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
compute_graspness_loss Ran
ran; our contract draft was wrong, not the code
iSEE-Laboratory/EconomicGrasp/models/loss_economicgrasp.py
code served (permissive licence) · get_code("702c7af5bf12d39e")
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
import torch.nn as nn

torch.manual_seed(0)

# Construct end_points dict with required keys
batch_size = 2
num_points = 4

end_points = {
    'graspness_score': torch.randn(batch_size, 1, num_points),  # shape (2, 1, 4)
    'graspness_label': torch.randn(batch_size, num_points, 1),  # shape (2, 4, 1)
    'objectness_label': torch.randint(0, 2, (batch_size, num_points)).float(),  # shape (2, 4)
}

ARGS = {
    'end_points': end_points
}
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
compute_objectness_loss Ran
ran; our contract draft was wrong, not the code
iSEE-Laboratory/EconomicGrasp/models/loss_economicgrasp.py
code served (permissive licence) · get_code("2e1a266839268c0c")
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
import torch.nn as nn

torch.manual_seed(0)

# Create small tensors for objectness_score and objectness_label
batch_size = 2
num_classes = 4

# objectness_score: logits for cross entropy loss (batch_size, num_classes)
objectness_score = torch.randn(batch_size, num_classes)

# objectness_label: class indices for cross entropy loss (batch_size,)
objectness_label = torch.randint(0, num_classes, (batch_size,))

# Construct the end_points dictionary
end_points = {
    'objectness_score': objectness_score,
    'objectness_label': objectness_label
}

ARGS = {
    'end_points': end_points
}
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
generate_grasp_views Ran
ran; our contract draft was wrong, not the code
iSEE-Laboratory/EconomicGrasp/utils/loss_utils.py
code served (permissive licence) · get_code("0f6be1306df35f18")
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 (300, 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
import numpy as np

torch.manual_seed(0)

ARGS = {
    'N': 300,
    'phi': (np.sqrt(5) - 1) / 2,
    'center': np.zeros(3),
    'r': 1
}
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 Tensor, ndim 2, dtype family float, shape (300, 3) — shape (300, 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
set_bn_momentum_default Ran
ran; our contract draft was wrong, not the code
iSEE-Laboratory/EconomicGrasp/libs/pointnet2/pytorch_utils.py
code served (permissive licence) · get_code("0ad12b1e8408e2f9")
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 function. 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)

# The function set_bn_momentum_default takes a bn_momentum parameter
# and returns a function that sets the momentum attribute on BatchNorm modules.
# The bn_momentum parameter should be a float value (typically between 0 and 1).

ARGS = {
    "bn_momentum": 0.1
}
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 function — a function output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a function 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
transform_point_cloud Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
iSEE-Laboratory/EconomicGrasp/utils/loss_utils.py
code served (permissive licence) · get_code("8d4b2fff611706ec")
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 a small point cloud: N=2 points, 3 coordinates each
cloud = torch.randn(2, 3, dtype=torch.float32)

# Create transformation matrices for each format
# 3x3: rotation only
transform_3x3 = torch.randn(3, 3, dtype=torch.float32)

# 4x4: rotation + translation (homogeneous coordinates)
transform_4x4 = torch.randn(4, 4, dtype=torch.float32)

# 3x4: rotation + translation (non-homogeneous form)
transform_3x4 = torch.randn(3, 4, dtype=torch.float32)

# Test with 4x4 format as default
ARGS = {
    'cloud': cloud,
    'transform': transform_4x4,
    'format': '4x4'
}
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

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 1 the same month, 1 later) and 6 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
set_bn_momentum_default 16 other papers
12 dated earlier, 1 the same month, 3 later
1904.09664 (2019-04)
Deep Hough Voting for 3D Object Detection in Point Clouds
1911.11236 (2019-11)
RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds
2004.05679 (2020-04)
MLCVNet: Multi-Level Context VoteNet for 3D Object Detection
and 13 more not named here

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

Robotic grasping in clutters is a fundamental task in robotic manipulation. In this work, we propose an economic framework for 6-DoF grasp detection, aiming to economize the resource cost in training and meanwhile maintain effective grasp performance. To begin with, we discover that the dense supervision is the bottleneck of current SOTA methods that severely encumbers the entire training overload, meanwhile making the training difficult to converge. To solve the above problem, we first propose an economic supervision paradigm for efficient and effective grasping. This paradigm includes a well-designed supervision selection strategy, selecting key labels basically without ambiguity, and an economic pipeline to enable the training after selection. Furthermore, benefit from the economic supervision, we can focus on a specific grasp, and thus we devise a focal representation module, which comprises an interactive grasp head and a composite score estimation to generate the specific grasp more accurately. Combining all together, the Economic-Grasp framework is proposed. Our extensive experiments show that EconomicGrasp surpasses the SOTA grasp method by about 3AP on average, and with extremely low resource cost, for about 1/4 training time cost, 1/8 memory cost and 1/30 storage cost. Our code is available at https://github.com/iSEE-Laboratory/EconomicGrasp.

For agents

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

get_harvested_code_for_paper("2407.08366")
get_code_for_paper("2407.08366")
have("2407.08366")

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

curl https://syntology.ai/api/ran/2407.08366.json

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

[![Syntology run record](https://syntology.ai/api/ran/2407.08366.svg)](https://syntology.ai/paper/2407.08366)

Connect an agent — have() is free.