SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2209.12699 · 2022

Accurate and Efficient Stereo Matching via Attention Concatenation Volume

arXiv · PDF · Open in the Atlas

Code that ran

10 of 11 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; 2 honoured the contract we drafted, 1 violated it and 4 have no contract verdict; 3 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/2209.12699.json · badge: /api/ran/2209.12699.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
gangweix/fast-acvnet canonical (classifier label)
classifier basis not recorded on the link
10 ran · 0 no recorded run
gangweix/acvnet canonical (classifier label)
classifier basis: classifier_2025
0 ran · 1 no recorded run
FunctionStatusWhere it lives
build_concat_volume Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
gangweix/fast-acvnet/models/submodule.py
pointer only (licence: MIT); the stored copy get_code serves, from NVlabs/FoundationStereo, is pointer only (licence: NOASSERTION) · get_code("c7a66c78764c1b17")
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 NVlabs/FoundationStereo, and GitHub could not classify the licence of that repository (NOASSERTION). 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.

default_loader Ran
ran, honoured the contract we drafted
gangweix/fast-acvnet/datasets/MiddleburyLoader.py
pointer only (licence: MIT); the stored copy get_code serves, from xlgsyzp/cvpt, is pointer only (licence: NONE) · get_code("ac269a0e4b8d946e")
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 xlgsyzp/cvpt, 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.

disparity_loader Ran
ran, honoured the contract we drafted
gangweix/fast-acvnet/datasets/MiddleburyLoader.py
code served (permissive licence) · get_code("6f290af6f9436c6b")
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 (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 os
import torch
import numpy as np
from PIL import Image
import tempfile

torch.manual_seed(0)

# Create a temporary PNG file with disparity data
temp_dir = tempfile.gettempdir()
png_path = os.path.join(temp_dir, "test_disparity.png")

# Create a simple grayscale image and save as PNG
disparity_image = Image.fromarray(np.uint8(np.random.randint(0, 256, (4, 3))), mode='L')
disparity_image.save(png_path)

ARGS = {
    'path': png_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, numpy, torch — 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 (4, 3) — shape (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
disparity_regression Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
gangweix/fast-acvnet/models/submodule.py
pointer only (licence: MIT); the stored copy get_code serves, from mickeykang16/Ev-Stereo3D, is pointer only (licence: NONE) · get_code("b667855f4bbc313f")
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 mickeykang16/Ev-Stereo3D, 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.

groupwise_correlation Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
gangweix/fast-acvnet/models/submodule.py
pointer only (licence: MIT); the stored copy get_code serves, from 3dcvdeveloper/bgnet, is pointer only (licence: NONE) · get_code("2e5c0e4dfa009847")
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 3dcvdeveloper/bgnet, 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.

is_image_file Ran
ran, violated the contract we drafted
gangweix/fast-acvnet/datasets/MiddleburyLoader.py
pointer only (licence: MIT); the stored copy get_code serves, from sgoldyaev/DeepFashion.ADGAN, is pointer only (licence: NONE) · get_code("ab4109634b75ef8b")
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 sgoldyaev/DeepFashion.ADGAN, 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.

model_loss_test Ran
ran on a synthesized input
gangweix/fast-acvnet/models/loss.py
code served (permissive licence) · get_code("01fd0a6b91ef3469")
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 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 torch
import torch.nn.functional as F

torch.manual_seed(0)

# Construct the arguments
batch_size = 2
height = 4
width = 3

# Create sample disparity estimates (predicted)
disp_ests = [
    torch.randn(batch_size, height, width),
    torch.randn(batch_size, height, width)
]

# Create sample disparity ground truth
disp_gts = [
    torch.randn(batch_size, height, width),
    torch.randn(batch_size, height, width)
]

# Create sample masks (boolean tensors indicating valid regions)
img_masks = [
    torch.randint(0, 2, (batch_size, height, width), dtype=torch.bool),
    torch.randint(0, 2, (batch_size, height, width), dtype=torch.bool)
]

ARGS = {
    'disp_ests': disp_ests,
    'disp_gts': disp_gts,
    'img_masks': img_masks
}
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 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
model_loss_train Ran
ran on a synthesized input
gangweix/fast-acvnet/models/loss.py
code served (permissive licence) · get_code("a1871814fca5baa9")
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 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 torch
import torch.nn.functional as F

torch.manual_seed(0)

# The function expects:
# - disp_ests: list of tensors (estimated disparities)
# - disp_gts: list of tensors (ground truth disparities)
# - img_masks: list of boolean tensors (masks)
# All lists should have length equal to len(weights) = 4

batch_size = 2
height = 4
width = 3

# Create 4 estimated disparity tensors
disp_ests = [
    torch.randn(batch_size, height, width),
    torch.randn(batch_size, height, width),
    torch.randn(batch_size, height, width),
    torch.randn(batch_size, height, width),
]

# Create 4 ground truth disparity tensors
disp_gts = [
    torch.randn(batch_size, height, width),
    torch.randn(batch_size, height, width),
    torch.randn(batch_size, height, width),
    torch.randn(batch_size, height, width),
]

# Create 4 boolean mask tensors
img_masks = [
    torch.rand(batch_size, height, width) > 0.3,
    torch.rand(batch_size, height, width) > 0.3,
    torch.rand(batch_size, height, width) > 0.3,
    torch.rand(batch_size, height, width) > 0.3,
]

ARGS = {
    "disp_ests": disp_ests,
    "disp_gts": disp_gts,
    "img_masks": img_masks,
}
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 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
pfm_imread Ran
ran on a synthesized input
gangweix/fast-acvnet/datasets/data_io.py
code served (permissive licence) · get_code("c35f13ea74c6be42")
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 tempfile
import os

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

# Write a valid PFM file (color, 3x2 image, scale 1.0)
with open(pfm_path, 'wb') as f:
    # Header: PF for color
    f.write(b'PF\n')
    # Dimensions: width=3, height=2
    f.write(b'3 2\n')
    # Scale: 1.0 (positive = big endian)
    f.write(b'1.0\n')
    # Image data: 2 rows x 3 cols x 3 channels = 18 floats
    data = np.ones((2, 3, 3), dtype='>f')
    data.tofile(f)

ARGS = {
    'filename': pfm_path
}
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 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
read_all_lines Ran
ran on a synthesized input
gangweix/fast-acvnet/datasets/data_io.py
code served (permissive licence) · get_code("e711a03e74028ed6")
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 tempfile
import os

# Create a temporary file with some test content
with tempfile.NamedTemporaryFile(mode='w', delete=False, suffix='.txt') as f:
    f.write("line one\n")
    f.write("line two\n")
    f.write("line three\n")
    temp_filename = f.name

ARGS = {
    "filename": temp_filename
}
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
acv Not yet run
unverified (harvested, no recorded run)
gangweix/acvnet/models/acv.py
code served (permissive licence) · get_code("ff1d9364a7618b1b")
How it ran

no invocation recorded.

Also present in other papers' code

Of 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 11 distinct functions with an identity, 8 are also present in other papers whose code we hold (7 with at least one paper dated earlier, 2 the same month, 7 later) and 3 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_image_file 62 other papers
29 dated earlier, 1 the same month, 30 later, 2 same year, order not determinable
1609.04802 (2016-09)
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network
1703.07511 (2017-03)
Deep Photo Style Transfer
1710.10916 (2017-10)
StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial Networks
and 59 more not named here
default_loader 27 other papers
18 dated earlier, 1 the same month, 8 later
1710.03463 (2017-10)
Learning to Generalize: Meta-Learning for Domain Generalization
1803.08669 (2018-03)
Pyramid Stereo Matching Network
1810.11408 (2018-10)
Anytime Stereo Image Depth Estimation on Mobile Devices
and 24 more not named here
groupwise_correlation 5 other papers
1 dated earlier, 4 later
2101.01601 (2021-01)
Bilateral Grid Learning for Stereo Matching Networks
2403.00486 (2024-03)
Selective-Stereo: Adaptive Frequency Information Selection for Stereo Matching
2403.11193 (2024-03)
Neural Markov Random Field for Stereo Matching
and 2 more not named here
pfm_imread 4 other papers
3 dated earlier, 1 later
1806.01260 (2018-06)
Digging Into Self-Supervised Monocular Depth Estimation
1912.06378 (2019-12)
Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matching
2104.04314 (2021-04)
CFNet: Cascade and Fused Cost Volume for Robust Stereo Matching
and 1 more not named here
read_all_lines 4 other papers
3 dated earlier, 1 later
1806.01260 (2018-06)
Digging Into Self-Supervised Monocular Depth Estimation
1912.06378 (2019-12)
Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matching
2104.04314 (2021-04)
CFNet: Cascade and Fused Cost Volume for Robust Stereo Matching
and 1 more not named here
disparity_regression 3 other papers
1 dated earlier, 2 later
2104.04314 (2021-04)
CFNet: Cascade and Fused Cost Volume for Robust Stereo Matching
2508.02288 (2025-08)
Unleashing the Temporal Potential of Stereo Event Cameras for Continuous-Time 3D Object Detection
build_concat_volume 2 other papers
2 later
2501.09898 (2025-01)
FoundationStereo: Zero-Shot Stereo Matching
2508.02288 (2025-08)
Unleashing the Temporal Potential of Stereo Event Cameras for Continuous-Time 3D Object Detection
disparity_loader 1 other paper
1 dated earlier
2104.04314 (2021-04)
CFNet: Cascade and Fused Cost Volume for Robust 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

Stereo matching is a fundamental building block for many vision and robotics applications. An informative and concise cost volume representation is vital for stereo matching of high accuracy and efficiency. In this paper, we present a novel cost volume construction method, named attention concatenation volume (ACV), which generates attention weights from correlation clues to suppress redundant information and enhance matching-related information in the concatenation volume. The ACV can be seamlessly embedded into most stereo matching networks, the resulting networks can use a more lightweight aggregation network and meanwhile achieve higher accuracy. We further design a fast version of ACV to enable real-time performance, named Fast-ACV, which generates high likelihood disparity hypotheses and the corresponding attention weights from low-resolution correlation clues to significantly reduce computational and memory cost and meanwhile maintain a satisfactory accuracy. The core idea of our Fast-ACV is volume attention propagation (VAP) which can automatically select accurate correlation values from an upsampled correlation volume and propagate these accurate values to the surroundings pixels with ambiguous correlation clues. Furthermore, we design a highly accurate network ACVNet and a real-time network Fast-ACVNet based on our ACV and Fast-ACV respectively, which achieve the state-of-the-art performance on several benchmarks (i.e., our ACVNet ranks the 2nd on KITTI 2015 and Scene Flow, and the 3rd on KITTI 2012 and ETH3D among all the published methods; our Fast-ACVNet outperforms almost all state-of-the-art real-time methods on Scene Flow, KITTI 2012 and 2015 and meanwhile has better generalization ability)

For agents

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

get_harvested_code_for_paper("2209.12699")
get_code_for_paper("2209.12699")
have("2209.12699")

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

curl https://syntology.ai/api/ran/2209.12699.json

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

[![Syntology run record](https://syntology.ai/api/ran/2209.12699.svg)](https://syntology.ai/paper/2209.12699)

Connect an agent — have() is free.