SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1912.06704 · 2019

Hierarchical Deep Stereo Matching on High-resolution Images

arXiv · PDF · Open in the Atlas

Code that ran

8 of 10 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; 0 failures of our instrument; 2 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/1912.06704.json · badge: /api/ran/1912.06704.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
gengshan-y/high-res-stereo community (classifier label)
classifier basis not recorded on the link
6 ran · 1 no recorded run
ibaiGorordo/PyTorch-High-Res-Stereo-Depth-Estimation community (classifier label)
classifier basis not recorded on the link
2 ran · 1 no recorded run
FunctionStatusWhere it lives
dataloader Ran
ran on a synthesized input
gengshan-y/high-res-stereo/dataloader/KITTIloader2012.py
code served (permissive licence) · get_code("7dfd7be48993bd31")
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 that mimics the expected layout
tmpdir = tempfile.mkdtemp()
left_fold = os.path.join(tmpdir, 'colored_0')
right_fold = os.path.join(tmpdir, 'colored_1')
disp_fold = os.path.join(tmpdir, 'disp_occ')

os.makedirs(left_fold, exist_ok=True)
os.makedirs(right_fold, exist_ok=True)
os.makedirs(disp_fold, exist_ok=True)

# Create dummy image files with '_10' in the name
dummy_files = ['image_10.png', 'frame_10.jpg', 'scene_10.png']
for filename in dummy_files:
    open(os.path.join(left_fold, filename), 'w').close()
    open(os.path.join(right_fold, filename), 'w').close()
    open(os.path.join(disp_fold, filename), '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
gengshan-y/high-res-stereo/dataloader/KITTIloader2015.py
code served (permissive licence) · get_code("1f37c6395f8cb912")
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)

# Create dummy image files with the expected naming pattern (_10)
# We need at least 200 files to match the range in the function
for i in range(200):
    filename = f"{i:06d}_10.png"
    open(os.path.join(temp_dir, 'image_2', filename), 'w').close()
    open(os.path.join(temp_dir, 'image_3', filename), 'w').close()
    open(os.path.join(temp_dir, 'disp_occ_0', filename), 'w').close()

ARGS = {
    'filepath': temp_dir + '/',
    'typ': 'train'
}
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
gengshan-y/high-res-stereo/dataloader/listfiles.py
code served (permissive licence) · get_code("89def291c40ceb41")
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 that mimics the expected dataset layout
temp_dir = tempfile.mkdtemp()

# Create subdirectories with image and disparity files
for i in range(2):
    subdir = os.path.join(temp_dir, f'sample_{i}')
    os.makedirs(subdir, exist_ok=True)
    
    # Create dummy files that the function expects
    open(os.path.join(subdir, 'im0.png'), 'w').close()
    open(os.path.join(subdir, 'im1.png'), 'w').close()
    open(os.path.join(subdir, 'disp0GT.pfm'), 'w').close()
    open(os.path.join(subdir, 'disp1GT.pfm'), '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
default_loader Ran
ran, honoured the contract we drafted
gengshan-y/high-res-stereo/dataloader/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.

draw_depth Ran
ran on a synthesized input
ibaiGorordo/PyTorch-High-Res-Stereo-Depth-Estimation/highres_stereo/utils_highres.py
code served (permissive licence) · get_code("9d919b029837f9f6")
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 int, shape (3, 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 cv2
import numpy as np

# Construct arguments for draw_depth function
# The function expects:
# - depth_map: a 2D array-like object that supports indexing and arithmetic
# - max_dist: a scalar value representing maximum distance

# Create a small depth map (2D array)
depth_map = np.array([
    [0.0, 1.5, 2.0, 3.5],
    [1.0, 2.5, 3.0, 4.5],
    [0.5, 2.0, 2.8, 5.0]
], dtype=np.float32)

# Maximum distance value
max_dist = 5.0

ARGS = {
    "depth_map": depth_map,
    "max_dist": max_dist
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
cv2, 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 int, shape (3, 4, 3) — shape (3, 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
draw_disparity Ran
ran on a synthesized input
ibaiGorordo/PyTorch-High-Res-Stereo-Depth-Estimation/highres_stereo/utils_highres.py
code served (permissive licence) · get_code("6b0647447e051d47")
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 int, shape (4, 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 numpy as np

# Create a small disparity map
# The function expects a numpy array that can be converted to uint8
# It uses min/max normalization and applies a colormap
disparity_map = np.random.rand(4, 3) * 64  # Small 4x3 disparity map with values 0-64

ARGS = {
    "disparity_map": disparity_map
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
cv2, 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 int, shape (4, 3, 3) — shape (4, 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
is_image_file Ran
ran, violated the contract we drafted
gengshan-y/high-res-stereo/dataloader/KITTIloader2012.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.

sepConv3d Ran
ran on a synthesized input
gengshan-y/high-res-stereo/models/submodule.py
code served (permissive licence) · get_code("edb7ea423ba81407")
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 Sequential. 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)

ARGS = {
    "in_planes": 3,
    "out_planes": 16,
    "kernel_size": 3,
    "stride": 1,
    "pad": 1,
    "bias": False
}
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 Sequential — a Sequential output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Sequential output the recorded ndim 1 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
dataloader Not yet run
unverified (harvested, no recorded run)
gengshan-y/high-res-stereo/dataloader/listsceneflow.py
code served (permissive licence) · get_code("93ba7c1654dce94b")
How it ran

no invocation recorded.

set_disparity_range Not yet run
unverified (harvested, no recorded run)
ibaiGorordo/PyTorch-High-Res-Stereo-Depth-Estimation/highres_stereo/utils_highres.py
code served (permissive licence) · get_code("caf4b59007e31e9a")
How it ran

no invocation recorded.

Also present in other papers' code

Of 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 10 distinct functions with an identity, 3 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 3 later) and 7 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
10 dated earlier, 52 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
7 dated earlier, 20 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
draw_depth 1 other paper
1 later
2108.09770 (2021-08)
MobileStereoNet: Towards Lightweight Deep Networks 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

We explore the problem of real-time stereo matching on high-res imagery. Many state-of-the-art (SOTA) methods struggle to process high-res imagery because of memory constraints or speed limitations. To address this issue, we propose an end-to-end framework that searches for correspondences incrementally over a coarse-to-fine hierarchy. Because high-res stereo datasets are relatively rare, we introduce a dataset with high-res stereo pairs for both training and evaluation. Our approach achieved SOTA performance on Middlebury-v3 and KITTI-15 while running significantly faster than its competitors. The hierarchical design also naturally allows for anytime on-demand reports of disparity by capping intermediate coarse results, allowing us to accurately predict disparity for near-range structures with low latency (30ms). We demonstrate that the performance-vs-speed trade-off afforded by on-demand hierarchies may address sensing needs for time-critical applications such as autonomous driving.

For agents

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

get_harvested_code_for_paper("1912.06704")
get_code_for_paper("1912.06704")
have("1912.06704")

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

curl https://syntology.ai/api/ran/1912.06704.json

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

[![Syntology run record](https://syntology.ai/api/ran/1912.06704.svg)](https://syntology.ai/paper/1912.06704)

Connect an agent — have() is free.