SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1904.06587 · 2019

GA-Net: Guided Aggregation Net for End-to-end Stereo Matching

arXiv · PDF · Open in the Atlas

Code that ran

6 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; 5 failures of our instrument; 1 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/1904.06587.json · badge: /api/ran/1904.06587.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
feihuzhang/GANet canonical (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
skumailraza/FRSNet-GA extension (classifier label)
classifier basis: classifier_2025
4 ran · 1 no recorded run
FunctionStatusWhere it lives
load_data Ran
ran; our contract draft was wrong, not the code
skumailraza/FRSNet-GA/predict.py
code served (permissive licence) · get_code("f5033afda061ae4f")
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. 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
from PIL import Image
import tempfile
import os

# Create temporary directory for test images
tmpdir = tempfile.mkdtemp()

# Create a simple test image (left image)
left_img_array = np.random.randint(0, 256, (100, 120, 3), dtype=np.uint8)
left_img = Image.fromarray(left_img_array, 'RGB')
left_path = os.path.join(tmpdir, 'left.png')
left_img.save(left_path)

# Create a simple test image (right image)
right_img_array = np.random.randint(0, 256, (100, 120, 3), dtype=np.uint8)
right_img = Image.fromarray(right_img_array, 'RGB')
right_path = os.path.join(tmpdir, 'right.png')
right_img.save(right_path)

ARGS = {
    'leftname': left_path,
    'rightname': right_path,
    'c_height': 80,
    'c_width': 96
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple 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
load_data Ran
ran, honoured the contract we drafted
feihuzhang/GANet/predict.py
code served (permissive licence) · get_code("49a628e53f46ed75")
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 (6, 32, 48) 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
from PIL import Image
import tempfile
import os

# Create temporary image files for testing
temp_dir = tempfile.mkdtemp()

# Create a simple left image (RGB)
left_array = np.random.randint(0, 256, (32, 48, 3), dtype=np.uint8)
left_image = Image.fromarray(left_array, mode='RGB')
left_path = os.path.join(temp_dir, 'left.png')
left_image.save(left_path)

# Create a simple right image (RGB)
right_array = np.random.randint(0, 256, (32, 48, 3), dtype=np.uint8)
right_image = Image.fromarray(right_array, mode='RGB')
right_path = os.path.join(temp_dir, 'right.png')
right_image.save(right_path)

ARGS = {
    'leftname': left_path,
    'rightname': right_path,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, 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 (6, 32, 48) — shape (6, 32, 48) 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
readPFM Ran
ran; our contract draft was wrong, not the code
feihuzhang/GANet/evaluation.py
code served (permissive licence) · get_code("259c1efb59c8cc6f")
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) and returned tuple. 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
import struct
import numpy as np

# Create a temporary PFM file for testing
temp_dir = tempfile.mkdtemp()
temp_file = os.path.join(temp_dir, "test.pfm")

# Create a simple PFM file (grayscale, Pf format)
width = 4
height = 3
channels = 1

# Write PFM header
with open(temp_file, 'wb') as f:
    # Magic number for grayscale
    f.write(b'Pf\n')
    # Width and height
    f.write(f'{width} {height}\n'.encode('latin-1'))
    # Endianness (negative = little endian)
    f.write(b'-1.0\n')
    
    # Write sample data (height * width * channels floats)
    samples = width * height * channels
    data = np.arange(samples, dtype=np.float32)
    buffer = struct.pack('<' + str(samples) + 'f', *data)
    f.write(buffer)

ARGS = {
    'file': temp_file
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple 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
readPNG Ran
ran; our contract draft was wrong, not the code
skumailraza/FRSNet-GA/evaluation.py
code served (permissive licence) · get_code("8bba59acb98c1899")
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. 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
from PIL import Image
import numpy as np

# Create a temporary PNG file for testing
with tempfile.NamedTemporaryFile(suffix='.png', delete=False) as tmp:
    # Create a simple RGB image (4x3 for distinct dimensions)
    img_array = np.random.randint(0, 256, (4, 3, 3), dtype=np.uint8)
    img = Image.fromarray(img_array, mode='RGB')
    img.save(tmp.name)
    temp_png_path = tmp.name

ARGS = {
    'file': temp_png_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple 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
test_transform Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
skumailraza/FRSNet-GA/predict.py
code served (permissive licence) · get_code("a20b38ce75ecff0e")
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. 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 numpy as np

torch.manual_seed(0)

# The function expects:
# - temp_data: a numpy array with shape (6, height, width) containing float32 values
# - crop_height: an integer for the target crop height
# - crop_width: an integer for the target crop width

# Create a temp_data array with 6 channels, height=10, width=12
temp_data = np.random.randn(6, 10, 12).astype('float32')

# Define crop dimensions
crop_height = 8
crop_width = 9

ARGS = {
    "temp_data": temp_data,
    "crop_height": crop_height,
    "crop_width": crop_width,
}
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 tuple — a tuple 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
test_transform Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
skumailraza/FRSNet-GA/evaluation.py
code served (permissive licence) · get_code("674d035839049ef2")
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. 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 a small test array with shape (6, height, width)
# This represents 6 channels (left 3 channels + right 3 channels)
temp_data = np.random.randn(6, 8, 10).astype('float32')

crop_height = 6
crop_width = 8

ARGS = {
    'temp_data': temp_data,
    'crop_height': crop_height,
    'crop_width': crop_width
}
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 tuple — a tuple 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
readPFM Not yet run
unverified (harvested, no recorded run)
skumailraza/FRSNet-GA/evaluation.py
code served (permissive licence) · get_code("e614bb1349b10c4f")
How it ran

no invocation recorded.

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, 3 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 3 later) and 4 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
test_transform 3 other papers
3 later
1911.13287 (2019-11)
Domain-invariant Stereo Matching Networks
2010.13501 (2020-10)
Hierarchical Neural Architecture Search for Deep Stereo Matching
2105.11587 (2021-05)
SRH-Net: Stacked Recurrent Hourglass Network for Stereo Matching
readPFM 2 other papers
2 later
2010.13501 (2020-10)
Hierarchical Neural Architecture Search for Deep Stereo Matching
2105.11587 (2021-05)
SRH-Net: Stacked Recurrent Hourglass Network for Stereo Matching
load_data 1 other paper
1 later
2105.11587 (2021-05)
SRH-Net: Stacked Recurrent Hourglass Network for Stereo Matching

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 the stereo matching task, matching cost aggregation is crucial in both traditional methods and deep neural network models in order to accurately estimate disparities. We propose two novel neural net layers, aimed at capturing local and the whole-image cost dependencies respectively. The first is a semi-global aggregation layer which is a differentiable approximation of the semi-global matching, the second is the local guided aggregation layer which follows a traditional cost filtering strategy to refine thin structures. These two layers can be used to replace the widely used 3D convolutional layer which is computationally costly and memory-consuming as it has cubic computational/memory complexity. In the experiments, we show that nets with a two-layer guided aggregation block easily outperform the state-of-the-art GC-Net which has nineteen 3D convolutional layers. We also train a deep guided aggregation network (GA-Net) which gets better accuracies than state-of-the-art methods on both Scene Flow dataset and KITTI benchmarks.

For agents

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

get_harvested_code_for_paper("1904.06587")
get_code_for_paper("1904.06587")
have("1904.06587")

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

curl https://syntology.ai/api/ran/1904.06587.json

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

[![Syntology run record](https://syntology.ai/api/ran/1904.06587.svg)](https://syntology.ai/paper/1904.06587)

Connect an agent — have() is free.