SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1803.08669 · 2018

Pyramid Stereo Matching Network

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; 1 honoured the contract we drafted, 1 violated it and 6 have no contract verdict; 2 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/1803.08669.json · badge: /api/ran/1803.08669.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
JiaRenChang/PSMNet canonical (classifier label)
classifier basis: census
10 ran · 1 no recorded run
FunctionStatusWhere it lives
convbn Ran
ran; our contract draft was wrong, not the code
JiaRenChang/PSMNet/models/submodule.py
pointer only (licence: MIT); the stored copy get_code serves, from 3dcvdeveloper/bgnet, is pointer only (licence: NONE) · get_code("15ab3c76823aef7e")
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.

convbn_3d Ran
ran; our contract draft was wrong, not the code
JiaRenChang/PSMNet/models/submodule.py
pointer only (licence: MIT); the stored copy get_code serves, from mickeykang16/temporaleventstereo, is pointer only (licence: NONE) · get_code("46674adf87c5459d")
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/temporaleventstereo, 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.

dataloader Ran
ran on a synthesized input
JiaRenChang/PSMNet/dataloader/KITTI_submission_loader.py
code served (permissive licence) · get_code("70963b30440822d8")
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 2, 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 with test files
tmpdir = tempfile.mkdtemp()
left_fold = 'image_2/'
right_fold = 'image_3/'

# Create subdirectories
os.makedirs(os.path.join(tmpdir, left_fold), exist_ok=True)
os.makedirs(os.path.join(tmpdir, right_fold), exist_ok=True)

# Create dummy image files with '_10' in the name
for i in range(3):
    left_file = os.path.join(tmpdir, left_fold, f'image_{i}_10.png')
    right_file = os.path.join(tmpdir, right_fold, f'image_{i}_10.png')
    open(left_file, 'w').close()
    open(right_file, 'w').close()

# Also create some files without '_10' to test filtering
for i in range(2):
    left_file = os.path.join(tmpdir, left_fold, f'image_{i}_11.png')
    right_file = os.path.join(tmpdir, right_fold, f'image_{i}_11.png')
    open(left_file, 'w').close()
    open(right_file, 'w').close()

filepath = tmpdir + '/'

ARGS = {
    'filepath': filepath
}
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 tuple, ndim 2, 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
dataloader Ran
ran on a synthesized input
JiaRenChang/PSMNet/dataloader/KITTI_submission_loader2012.py
code served (permissive licence) · get_code("9a9e2227f81699e9")
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 2, 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_dir = tempfile.mkdtemp()
left_fold_path = os.path.join(temp_dir, 'colored_0')
right_fold_path = os.path.join(temp_dir, 'colored_1')

os.makedirs(left_fold_path, exist_ok=True)
os.makedirs(right_fold_path, exist_ok=True)

# Create some dummy image files with '_10' in the name
for i in range(2):
    open(os.path.join(left_fold_path, f'image_{10+i}.jpg'), 'w').close()
    open(os.path.join(right_fold_path, f'image_{10+i}.jpg'), 'w').close()

# Create some image files without '_10' to ensure filtering works
open(os.path.join(left_fold_path, 'image_20.jpg'), 'w').close()
open(os.path.join(right_fold_path, 'image_20.jpg'), 'w').close()

ARGS = {
    'filepath': temp_dir + '/'
}
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 tuple, ndim 2, 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
dataloader Ran
ran on a synthesized input
JiaRenChang/PSMNet/dataloader/KITTIloader2012.py
code served (permissive licence) · get_code("facba429ec9a5e75")
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 os
import tempfile
import shutil

# Create a temporary directory structure that mimics the expected layout
temp_dir = tempfile.mkdtemp()
filepath = temp_dir + '/'

# Create subdirectories
os.makedirs(filepath + 'colored_0/', exist_ok=True)
os.makedirs(filepath + 'colored_1/', exist_ok=True)
os.makedirs(filepath + 'disp_occ/', exist_ok=True)

# Create dummy image files with '_10' in the name
# We need at least 160 images for the function to work (val = image[160:])
for i in range(200):
    open(filepath + 'colored_0/' + f'image_{i:06d}_10.png', 'a').close()
    open(filepath + 'colored_1/' + f'image_{i:06d}_10.png', 'a').close()
    open(filepath + 'disp_occ/' + f'image_{i:06d}_10.png', 'a').close()

ARGS = {
    'filepath': filepath
}
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 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
dataloader Ran
ran on a synthesized input
JiaRenChang/PSMNet/dataloader/KITTIloader2015.py
code served (permissive licence) · get_code("71cbc3b4bc1e8f34")
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 os
import tempfile
import shutil

# Create a temporary directory structure that mimics the expected dataset layout
temp_dir = tempfile.mkdtemp()

# Create the required subdirectories
os.makedirs(os.path.join(temp_dir, 'image_2'), exist_ok=True)
os.makedirs(os.path.join(temp_dir, 'image_3'), exist_ok=True)
os.makedirs(os.path.join(temp_dir, 'disp_occ_0'), exist_ok=True)
os.makedirs(os.path.join(temp_dir, 'disp_occ_1'), exist_ok=True)

# Create dummy image files with '_10' in the name
# Create 170 files to have enough for train (160) and val (10)
for i in range(170):
    open(os.path.join(temp_dir, 'image_2', f'image_{i:06d}_10.png'), 'w').close()
    open(os.path.join(temp_dir, 'image_3', f'image_{i:06d}_10.png'), 'w').close()
    open(os.path.join(temp_dir, 'disp_occ_0', f'image_{i:06d}_10.png'), 'w').close()
    open(os.path.join(temp_dir, 'disp_occ_1', f'image_{i:06d}_10.png'), 'w').close()

# The function expects a filepath that ends with a separator
filepath = temp_dir + os.sep

ARGS = {
    'filepath': filepath
}
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 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
dataloader Ran
ran on a synthesized input
JiaRenChang/PSMNet/dataloader/listflowfile.py
code served (permissive licence) · get_code("722050d7e9df5e9c")
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 os
import tempfile
import shutil

# Create a temporary directory structure that mimics the expected dataset layout
temp_dir = tempfile.mkdtemp()

# Create the directory structure
def create_dir_structure(base_path):
    # Create monkaa structure
    monkaa_frames = os.path.join(base_path, 'frames_cleanpass_monkaa')
    monkaa_disp = os.path.join(base_path, 'disparity_monkaa')
    os.makedirs(monkaa_frames, exist_ok=True)
    os.makedirs(monkaa_disp, exist_ok=True)
    
    for scene in ['scene1']:
        left_dir = os.path.join(monkaa_frames, scene, 'left')
        right_dir = os.path.join(monkaa_frames, scene, 'right')
        left_disp_dir = os.path.join(monkaa_disp, scene, 'left')
        os.makedirs(left_dir, exist_ok=True)
        os.makedirs(right_dir, exist_ok=True)
        os.makedirs(left_disp_dir, exist_ok=True)
        
        # Create dummy image files
        open(os.path.join(left_dir, 'image_001.png'), 'w').close()
        open(os.path.join(right_dir, 'image_001.png'), 'w').close()
        open(os.path.join(left_disp_dir, 'image_001.pfm'), 'w').close()
    
    # Create flying structure
    flying_frames = os.path.join(base_path, 'frames_cleanpass')
    flying_disp = os.path.join(base_path, 'frames_disparity')
    os.makedirs(flying_frames, exist_ok=True)
    os.makedirs(flying_disp, exist_ok=True)
    
    for split in ['TRAIN', 'TEST']:
        for subdir in ['A', 'B', 'C']:
            for scene in ['scene1']:
                left_dir = os.path.join(flying_frames, split, subdir, scene, 'left')
                right_dir = os.path.join(flying_frames, split, subdir, scene, 'right')
                left_disp_dir = os.path.join(flying_disp, split, subdir, scene, 'left')
                os.makedirs(left_dir, exist_ok=True)
                os.makedirs(right_dir, exist_ok=True)
                os.makedirs(left_disp_dir, exist_ok=True)
                
                open(os.path.join(left_dir, 'image_001.png'), 'w').close()
                open(os.path.join(right_dir, 'image_001.png'), 'w').close()
                open(os.path.join(left_disp_dir, 'image_001.pfm'), 'w').close()
    
    # Create driving structure
    driving_frames = os.path.join(base_path, 'frames_cleanpass_driving')
    driving_disp = os.path.join(base_path, 'disparity_driving')
    os.makedirs(driving_frames, exist_ok=True)
    os.makedirs(driving_disp, exist_ok=True)
    
    for focal in ['35mm_focallength', '15mm_focallength']:
        for direction in ['scene_backwards', 'scene_forwards']:
            for speed in ['fast', 'slow']:
                left_dir = os.path.join(driving_frames, focal, direction, speed, 'left')
                right_dir = os.path.join(driving_frames, focal, direction, speed, 'right')
                left_disp_dir = os.path.join(driving_disp, focal, direction, speed, 'left')
                os.makedirs(left_dir, exist_ok=True)
                os.makedirs(right_dir, exist_ok=True)
                os.makedirs(left_disp_dir, exist_ok=True)
                
                open(os.path.join(left_dir, 'image_001.png'), 'w').close()
                open(os.path.join(right_dir, 'image_001.png'), 'w').close()
                open(os.path.join(left_disp_dir, 'image_001.pfm'), 'w').close()

create_dir_structure(temp_dir)

ARGS = {
    'filepath': temp_dir + '/'
}
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 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
default_loader Ran
ran, honoured the contract we drafted
JiaRenChang/PSMNet/dataloader/KITTILoader.py
code served (permissive licence) · get_code("0b3ce8456d675a8c")
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 Image. 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 os

# Create a temporary image file
temp_dir = tempfile.mkdtemp()
temp_image_path = os.path.join(temp_dir, "test_image.jpg")

# Create a simple RGB image and save it
img = Image.new('RGB', (100, 100), color='red')
img.save(temp_image_path)

# Define ARGS with the path parameter
ARGS = {
    'path': temp_image_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Image — a Image output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Image output the recorded ndim 3 and dtype family int 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
disparity_loader Ran
ran on a synthesized input
JiaRenChang/PSMNet/dataloader/KITTILoader.py
code served (permissive licence) · get_code("c0ce2ceaa41309b3")
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 PngImageFile. 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
from PIL import Image
import tempfile
import os

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

# Create a simple test image and save it
test_image = Image.new('L', (64, 48), color=128)
test_image_path = os.path.join(temp_dir, 'test_disparity.png')
test_image.save(test_image_path)

# Define ARGS with the path parameter
ARGS = {
    'path': test_image_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type PngImageFile — a PngImageFile output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a PngImageFile output the recorded ndim 2 and dtype family int 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
is_image_file Ran
ran, violated the contract we drafted
JiaRenChang/PSMNet/dataloader/KITTILoader.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.

disparity_loader Not yet run
unverified (harvested, no recorded run)
JiaRenChang/PSMNet/dataloader/SecenFlowLoader.py
code served (permissive licence) · get_code("aaf877e27c4a3c3e")
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, 6 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 6 later) and 5 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
4 dated earlier, 58 later
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
1 dated earlier, 26 later
1710.03463 (2017-10)
Learning to Generalize: Meta-Learning for Domain Generalization
1810.11408 (2018-10)
Anytime Stereo Image Depth Estimation on Mobile Devices
1906.06310 (2019-06)
Pseudo-LiDAR++: Accurate Depth for 3D Object Detection in Autonomous Driving
and 24 more not named here
convbn 13 other papers
13 later
1806.01260 (2018-06)
Digging Into Self-Supervised Monocular Depth Estimation
1905.00538 (2019-05)
DPSNet: End-to-end Deep Plane Sweep Stereo
1911.04460 (2019-11)
360SD-Net: 360° Stereo Depth Estimation with Learnable Cost Volume
and 10 more not named here
convbn_3d 9 other papers
9 later
1806.01260 (2018-06)
Digging Into Self-Supervised Monocular Depth Estimation
1905.00538 (2019-05)
DPSNet: End-to-end Deep Plane Sweep Stereo
1911.04460 (2019-11)
360SD-Net: 360° Stereo Depth Estimation with Learnable Cost Volume
and 6 more not named here
disparity_loader 2 other papers
2 later
1810.11408 (2018-10)
Anytime Stereo Image Depth Estimation on Mobile Devices
2007.03085 (2020-07)
Wasserstein Distances for Stereo Disparity Estimation
disparity_loader 1 other paper
1 later
1810.11408 (2018-10)
Anytime Stereo Image Depth Estimation on Mobile Devices

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

Recent work has shown that depth estimation from a stereo pair of images can be formulated as a supervised learning task to be resolved with convolutional neural networks (CNNs). However, current architectures rely on patch-based Siamese networks, lacking the means to exploit context information for finding correspondence in illposed regions. To tackle this problem, we propose PSMNet, a pyramid stereo matching network consisting of two main modules: spatial pyramid pooling and 3D CNN. The spatial pyramid pooling module takes advantage of the capacity of global context information by aggregating context in different scales and locations to form a cost volume. The 3D CNN learns to regularize cost volume using stacked multiple hourglass networks in conjunction with intermediate supervision. The proposed approach was evaluated on several benchmark datasets. Our method ranked first in the KITTI 2012 and 2015 leaderboards before March 18, 2018. The codes of PSMNet are available at: https://github.com/JiaRenChang/PSMNet.

For agents

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

get_harvested_code_for_paper("1803.08669")
get_code_for_paper("1803.08669")
have("1803.08669")

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

curl https://syntology.ai/api/ran/1803.08669.json

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

[![Syntology run record](https://syntology.ai/api/ran/1803.08669.svg)](https://syntology.ai/paper/1803.08669)

Connect an agent — have() is free.