SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1806.01260 · 2018

Digging Into Self-Supervised Monocular Depth Estimation

arXiv · PDF · Open in the Atlas

Code that ran

23 of 24 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; 5 honoured the contract we drafted, 1 violated it and 5 have no contract verdict; 12 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/1806.01260.json · badge: /api/ran/1806.01260.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
qrzyang/pseudo-stereo community (classifier label)
classifier basis not recorded on the link
8 ran · 1 no recorded run
IcarusWizard/monodepth2-paddle community (classifier label)
classifier basis: plan_row
8 ran · 0 no recorded run
CaptainEven/MonoDepthV2 reimplementation (classifier label)
classifier basis: classifier_2025
4 ran · 0 no recorded run
iodncookie/my_loss_monodepth_master reimplementation (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
FangGet/tf-monodepth2 reimplementation (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
FunctionStatusWhere it lives
batch_post_process_disparity Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
IcarusWizard/monodepth2-paddle/evaluate_depth.py
code served (permissive licence) · get_code("a8814cc5c348b987")
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 ndarray, ndim 3, dtype family float, shape (2, 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 numpy as np

# Create small disparity maps
# Shape: (batch, height, width)
batch_size = 2
height = 4
width = 3

l_disp = np.random.rand(batch_size, height, width).astype(np.float32)
r_disp = np.random.rand(batch_size, height, width).astype(np.float32)

ARGS = {
    "l_disp": l_disp,
    "r_disp": r_disp,
}
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 ndarray, ndim 3, dtype family float, shape (2, 4, 3) — shape (2, 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
compute_errors Ran
ran, honoured the contract we drafted
CaptainEven/MonoDepthV2/evaluate_depth.py
pointer only (licence: NOASSERTION) · get_code("d4eb240de6e155d3")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, CaptainEven/MonoDepthV2 (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.

compute_errors Ran
ran, honoured the contract we drafted
IcarusWizard/monodepth2-paddle/evaluate_depth.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from nianticlabs/depth-hints, is pointer only (licence: NOASSERTION) · get_code("edd4f86e8f02732f")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from nianticlabs/depth-hints, 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.

compute_metric_for_each_image Ran
ran on a synthesized input
qrzyang/pseudo-stereo/utils/metrics.py
code served (permissive licence) · get_code("6d968ec37ba07def")
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
from torch.autograd import Variable
from torch import Tensor

torch.manual_seed(0)

# Create a simple metric function that takes D_est, D_gt, mask and returns a scalar
def simple_metric_func(D_est, D_gt, mask, *args):
    """
    Simple metric function that computes mean absolute error on masked region.
    Takes 2D tensors (height, width) and returns a scalar tensor.
    """
    diff = torch.abs(D_est - D_gt)
    masked_diff = diff * mask
    return masked_diff.mean()

# Create sample tensors with shape (batch_size, height, width) = (2, 4, 3)
batch_size = 2
height = 4
width = 3

D_ests = torch.randn(batch_size, height, width)
D_gts = torch.randn(batch_size, height, width)
D_gts = torch.abs(D_gts) + 0.5  # Make positive for meaningful mask computation

# Create masks with meaningful values (not all zeros)
masks = torch.ones(batch_size, height, width)
masks[0, 0, 0] = 0  # Add some variation
masks[1, 1:3, 1:3] = 0

ARGS = {
    'metric_func': simple_metric_func
}
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
concat_image_seq Ran
ran, violated the contract we drafted
FangGet/tf-monodepth2/data/prepare_train_data.py
code served (permissive licence) · get_code("09d614ea6e098976")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned ndarray, ndim 2, dtype family float, shape (3, 15) 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 sequence of small images (2D arrays representing grayscale images)
# Using different widths to make it clear they're being concatenated horizontally
image1 = np.random.rand(3, 4)  # height=3, width=4
image2 = np.random.rand(3, 5)  # height=3, width=5
image3 = np.random.rand(3, 6)  # height=3, width=6

seq = [image1, image2, image3]

ARGS = {
    'seq': seq
}
Setup block drafted by
a language model, Claude Sonnet 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 ndarray, ndim 2, dtype family float, shape (3, 15) — shape (3, 15) 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
convbn Ran
ran; our contract draft was wrong, not the code
qrzyang/pseudo-stereo/models/psm_submodule.py
pointer only (licence: Apache-2.0); 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 (Apache-2.0), 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
qrzyang/pseudo-stereo/models/psm_submodule.py
pointer only (licence: Apache-2.0); 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 (Apache-2.0), 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.

count_text_lines Ran
ran, honoured the contract we drafted
iodncookie/my_loss_monodepth_master/monodepth_main.py
pointer only (licence: NOASSERTION) · get_code("bed135371a969180")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, iodncookie/my_loss_monodepth_master (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.

depth2disp Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
CaptainEven/MonoDepthV2/test_simple.py
pointer only (licence: NOASSERTION) · get_code("dafc01865fd0e64d")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, CaptainEven/MonoDepthV2 (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.

disp2depth Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
CaptainEven/MonoDepthV2/test_simple.py
pointer only (licence: NOASSERTION) · get_code("2f583364067a6299")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, CaptainEven/MonoDepthV2 (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.

disp_to_depth Ran
ran, honoured the contract we drafted
IcarusWizard/monodepth2-paddle/layers.py
code served (permissive licence) · get_code("212db0f1a51698c5")
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 3, 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

torch.manual_seed(0)

# disp_to_depth expects:
# - disp: a tensor of disparity values (sigmoid output, range 0-1)
# - min_depth: scalar float for minimum depth
# - max_depth: scalar float for maximum depth

disp = torch.rand(2, 4)  # batch=2, spatial_dims=4
min_depth = 0.1
max_depth = 100.0

ARGS = {
    "disp": disp,
    "min_depth": min_depth,
    "max_depth": max_depth,
}
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 3, 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
get_smooth_loss Ran
ran on a synthesized input
qrzyang/pseudo-stereo/losses/utils.py
code served (permissive licence) · get_code("ee1c671a6243bdf3")
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 as nn

torch.manual_seed(0)

# Create small tensors with distinct dimensions for clarity
batch_size = 2
channels = 3
height = 4
width = 5

# disp: disparity image tensor, shape (B, C, H, W)
# Used in slicing operations: [:, :, :, :-1], [:, :, :, 1:], [:, :, :-1, :], [:, :, 1:, :]
disp = torch.randn(batch_size, channels, height, width)

# img: color image tensor, shape (B, C, H, W)
# Used in same slicing operations and torch.mean with dim=1
img = torch.randn(batch_size, channels, height, width)

# mask: optional 0-1 tensor, shape (B, C, H, W)
# Used in unfold operation and masking
mask = torch.ones(batch_size, channels, height, width)

ARGS = {
    "disp": disp,
    "img": img,
    "mask": mask,
}
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
load_velodyne_points Ran
ran, honoured the contract we drafted
IcarusWizard/monodepth2-paddle/kitti_utils.py
code served (permissive licence) · get_code("8bfc895e86bfc7bc")
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 (5, 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 numpy as np
import tempfile
import os

# Create a temporary binary file with KITTI point cloud data
# KITTI format: each point is 4 float32 values (x, y, z, reflectance)
temp_dir = tempfile.mkdtemp()
temp_file = os.path.join(temp_dir, "points.bin")

# Create sample point cloud data: 5 points with 4 values each
sample_points = np.array([
    [1.0, 2.0, 3.0, 0.5],
    [4.0, 5.0, 6.0, 0.7],
    [7.0, 8.0, 9.0, 0.9],
    [10.0, 11.0, 12.0, 0.3],
    [13.0, 14.0, 15.0, 0.6]
], dtype=np.float32)

sample_points.tofile(temp_file)

ARGS = {
    "filename": temp_file
}
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 ndarray, ndim 2, dtype family float, shape (5, 4) — shape (5, 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
make_iterative_func Ran
ran; our contract draft was wrong, not the code
qrzyang/pseudo-stereo/utils/experiment.py
code served (permissive licence) · get_code("8233a45ac266ffd4")
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 make_iterative_func takes a function as input and returns a wrapper
# that recursively applies that function to nested structures (lists, tuples, dicts)
# or applies it directly to non-container types.

# We need to provide a simple function that works with various input types
def simple_func(x):
    """A simple function that increments numeric types or processes tensors"""
    if isinstance(x, torch.Tensor):
        return x + 1
    elif isinstance(x, (int, float)):
        return x + 1
    else:
        return x

ARGS = {
    "func": simple_func
}
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
make_nograd_func Ran
ran; our contract draft was wrong, not the code
qrzyang/pseudo-stereo/utils/experiment.py
code served (permissive licence) · get_code("c2cc757b82342e5f")
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 takes a single parameter: func
# It wraps a function to execute it within torch.no_grad() context
# We need to provide a callable that will be wrapped

def sample_func(x, y=10):
    """A simple function that performs some tensor operations"""
    return x + y

ARGS = {
    "func": sample_func
}
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
normalize_image Ran
ran on a synthesized input
IcarusWizard/monodepth2-paddle/utils.py
code served (permissive licence) · get_code("8749078cf4be8f13")
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

torch.manual_seed(0)

# The function expects x to be a tensor with .max(), .min(), and .numpy() methods
# It performs normalization by rescaling to [0, 1]
x = torch.randn(2, 4)

ARGS = {
    "x": x
}
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, 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
pfm_imread Ran
ran on a synthesized input
qrzyang/pseudo-stereo/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
post_process_disparity Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
iodncookie/my_loss_monodepth_master/monodepth_main.py
pointer only (licence: NOASSERTION) · get_code("92cb86f70b5d6123")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, iodncookie/my_loss_monodepth_master (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.

project_depth_to_pointcloud Ran
ran; our contract draft was wrong, not the code
CaptainEven/MonoDepthV2/test_simple.py
pointer only (licence: NOASSERTION) · get_code("7d5438c1a2189f3f")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, CaptainEven/MonoDepthV2 (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.

read_all_lines Ran
ran on a synthesized input
qrzyang/pseudo-stereo/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
read_calib_file Ran
ran; our contract draft was wrong, not the code
IcarusWizard/monodepth2-paddle/kitti_utils.py
code served (permissive licence) · get_code("ff833c099a80a327")
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 dict. 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 KITTI calibration file
temp_dir = tempfile.mkdtemp()
calib_file_path = os.path.join(temp_dir, "calib.txt")

# Write a sample KITTI calibration file
calib_content = """P0: 7.070493e+02 0.000000e+00 6.040814e+02 0.000000e+00 0.000000e+00 7.070493e+02 1.805066e+02 -3.797839e+01 0.000000e+00 0.000000e+00 1.000000e+00 5.371000e-03
P1: 7.070493e+02 0.000000e+00 6.040814e+02 4.694443e+01 0.000000e+00 7.070493e+02 1.805066e+02 -3.701007e+00 0.000000e+00 0.000000e+00 1.000000e+00 4.851000e-03
P2: 7.070493e+02 0.000000e+00 6.040814e+02 4.694443e+01 0.000000e+00 7.070493e+02 1.805066e+02 -3.701007e+00 0.000000e+00 0.000000e+00 1.000000e+00 4.851000e-03
P3: 7.070493e+02 0.000000e+00 6.040814e+02 -3.324873e+01 0.000000e+00 7.070493e+02 1.805066e+02 2.372145e+00 0.000000e+00 0.000000e+00 1.000000e+00 2.162000e-03
R0_rect: 9.999239e-01 9.837760e-03 -7.445570e-03 -9.869795e-03 9.999421e-01 -4.278459e-03 7.402527e-03 4.351614e-03 9.999631e-01
Tr_velo_to_cam: 7.533745e-03 -9.999714e-01 -6.166020e-04 -4.069766e-03 1.480249e-02 7.280733e-04 -9.998902e-01 -7.631618e-02 9.998621e-01 7.523790e-03 1.480755e-02 -2.717806e-01
Tr_imu_to_velo: 9.999976e-01 7.553071e-04 -2.035826e-03 -8.086759e-01 -7.854027e-04 9.998898e-01 -1.482298e-02 3.195559e-01 2.024406e-03 1.482454e-02 9.998881e-01 -7.437787e-01
"""

with open(calib_file_path, 'w') as f:
    f.write(calib_content)

ARGS = {
    "path": calib_file_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 dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
readlines Ran
ran; our contract draft was wrong, not the code
IcarusWizard/monodepth2-paddle/utils.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from eldar/flash3d, is pointer only (licence: NONE) · get_code("859a6ec5fa262fcb")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from eldar/flash3d, 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.

sub2ind Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
IcarusWizard/monodepth2-paddle/kitti_utils.py
code served (permissive licence) · get_code("04e9b96b63844176")
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 int, ndim 0, dtype family int, 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 numpy as np

torch.manual_seed(0)

# The function sub2ind converts row, col matrix subscripts to linear indices
# It takes:
# - matrixSize: a tuple (m, n) representing matrix dimensions
# - rowSub: row subscript(s)
# - colSub: column subscript(s)

# Let's create valid arguments for a 4x3 matrix
matrixSize = (4, 3)
rowSub = 1
colSub = 2

ARGS = {
    "matrixSize": matrixSize,
    "rowSub": rowSub,
    "colSub": colSub
}
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 int, ndim 0, dtype family int, 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
tensor2float Not yet run
unverified (harvested, no recorded run)
qrzyang/pseudo-stereo/utils/experiment.py
code served (permissive licence) · get_code("198cd80d23544257")
How it ran

no invocation recorded.

Also present in other papers' code

Of 24 samples lifted from this paper's linked repositories, 24 carry a function identity and 0 do not. Of the 23 distinct functions with an identity, 16 are also present in other papers whose code we hold (5 with at least one paper dated earlier, 0 the same month, 14 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
compute_errors 24 other papers
2 dated earlier, 22 later
1609.03677 (2016-09)
Unsupervised Monocular Depth Estimation with Left-Right Consistency
1803.02276 (2018-03)
GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Pose
1909.09051 (2019-09)
Self-Supervised Monocular Depth Hints
and 21 more not named here
disp_to_depth 18 other papers
18 later
1809.02627 (2018-09)
Unity: A General Platform for Intelligent Agents
1907.10326 (2019-07)
From Big to Small: Multi-Scale Local Planar Guidance for Monocular Depth Estimation
Zhou_R-MSFM_Recurrent_Multi-Scale_Feature_Modulation_for_Monocular_Depth_Estimating_ICCV_2021_paper (2021 (year only))
R-MSFM: Recurrent Multi-Scale Feature Modulation for Monocular Depth Estimating
and 15 more not named here
batch_post_process_disparity 17 other papers
17 later
1909.09051 (2019-09)
Self-Supervised Monocular Depth Hints
2003.13951 (2020-03)
Self-supervised Monocular Trained Depth Estimation using Self-attention and Discrete Disparity Volume
2004.00171 (2020-04)
The Edge of Depth: Explicit Constraints between Segmentation and Depth
and 14 more not named here
make_nograd_func 16 other papers
16 later
1912.06378 (2019-12)
Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matching
2007.10872 (2020-07)
Dense Hybrid Recurrent Multi-view Stereo Net with Dynamic Consistency Checking
2104.00681 (2021-04)
NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Video
and 13 more not named here
convbn 13 other papers
1 dated earlier, 12 later
1803.08669 (2018-03)
Pyramid Stereo Matching Network
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
1 dated earlier, 8 later
1803.08669 (2018-03)
Pyramid Stereo Matching Network
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
load_velodyne_points 7 other papers
7 later
Zhou_R-MSFM_Recurrent_Multi-Scale_Feature_Modulation_for_Monocular_Depth_Estimating_ICCV_2021_paper (2021 (year only))
R-MSFM: Recurrent Multi-Scale Feature Modulation for Monocular Depth Estimating
2104.00556 (2021-04)
Deep Two-View Structure-from-Motion Revisited
2309.05254 (2023-09)
Towards Better Data Exploitation in Self-Supervised Monocular Depth Estimation
and 4 more not named here
read_calib_file 7 other papers
7 later
Zhou_R-MSFM_Recurrent_Multi-Scale_Feature_Modulation_for_Monocular_Depth_Estimating_ICCV_2021_paper (2021 (year only))
R-MSFM: Recurrent Multi-Scale Feature Modulation for Monocular Depth Estimating
2104.00556 (2021-04)
Deep Two-View Structure-from-Motion Revisited
2309.05254 (2023-09)
Towards Better Data Exploitation in Self-Supervised Monocular Depth Estimation
and 4 more not named here
readlines 7 other papers
7 later
Zhou_R-MSFM_Recurrent_Multi-Scale_Feature_Modulation_for_Monocular_Depth_Estimating_ICCV_2021_paper (2021 (year only))
R-MSFM: Recurrent Multi-Scale Feature Modulation for Monocular Depth Estimating
2204.03636 (2022-04)
SurroundDepth: Entangling Surrounding Views for Self-Supervised Multi-Camera Depth Estimation
2309.05254 (2023-09)
Towards Better Data Exploitation in Self-Supervised Monocular Depth Estimation
and 4 more not named here
sub2ind 7 other papers
7 later
Zhou_R-MSFM_Recurrent_Multi-Scale_Feature_Modulation_for_Monocular_Depth_Estimating_ICCV_2021_paper (2021 (year only))
R-MSFM: Recurrent Multi-Scale Feature Modulation for Monocular Depth Estimating
2104.00556 (2021-04)
Deep Two-View Structure-from-Motion Revisited
2309.05254 (2023-09)
Towards Better Data Exploitation in Self-Supervised Monocular Depth Estimation
and 4 more not named here
pfm_imread 4 other papers
4 later
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
2209.12699 (2022-09)
Accurate and Efficient Stereo Matching via Attention Concatenation Volume
and 1 more not named here
read_all_lines 4 other papers
4 later
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
2209.12699 (2022-09)
Accurate and Efficient Stereo Matching via Attention Concatenation Volume
and 1 more not named here
post_process_disparity 3 other papers
3 dated earlier
1609.03677 (2016-09)
Unsupervised Monocular Depth Estimation with Left-Right Consistency
1704.03489 (2017-04)
CNN-SLAM: Real-time dense monocular SLAM with learned depth prediction
1803.05619 (2018-03)
Fast End-to-End Trainable Guided Filter
count_text_lines 2 other papers
2 dated earlier
1609.03677 (2016-09)
Unsupervised Monocular Depth Estimation with Left-Right Consistency
1704.03489 (2017-04)
CNN-SLAM: Real-time dense monocular SLAM with learned depth prediction
make_iterative_func 1 other paper
1 later
2404.06605 (2024-04)
RoadBEV: Road Surface Reconstruction in Bird's Eye View
tensor2float 1 other paper
1 later
2404.06605 (2024-04)
RoadBEV: Road Surface Reconstruction in Bird's Eye View

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

Per-pixel ground-truth depth data is challenging to acquire at scale. To overcome this limitation, self-supervised learning has emerged as a promising alternative for training models to perform monocular depth estimation. In this paper, we propose a set of improvements, which together result in both quantitatively and qualitatively improved depth maps compared to competing self-supervised methods. Research on self-supervised monocular training usually explores increasingly complex architectures, loss functions, and image formation models, all of which have recently helped to close the gap with fully-supervised methods. We show that a surprisingly simple model, and associated design choices, lead to superior predictions. In particular, we propose (i) a minimum reprojection loss, designed to robustly handle occlusions, (ii) a full-resolution multi-scale sampling method that reduces visual artifacts, and (iii) an auto-masking loss to ignore training pixels that violate camera motion assumptions. We demonstrate the effectiveness of each component in isolation, and show high quality, state-of-the-art results on the KITTI benchmark.

For agents

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

get_harvested_code_for_paper("1806.01260")
get_code_for_paper("1806.01260")
have("1806.01260")

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

curl https://syntology.ai/api/ran/1806.01260.json

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

[![Syntology run record](https://syntology.ai/api/ran/1806.01260.svg)](https://syntology.ai/paper/1806.01260)

Connect an agent — have() is free.