SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1609.03677 · 2016

Unsupervised Monocular Depth Estimation with Left-Right Consistency

arXiv · PDF · Open in the Atlas

Code that ran

8 of 12 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; 1 failure of our instrument; 4 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/1609.03677.json · badge: /api/ran/1609.03677.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
mrharicot/monodepth canonical (classifier label)
classifier basis: census
1 ran · 0 no recorded run
IcarusWizard/monodepth-paddle community (classifier label)
classifier basis: plan_row
6 ran · 1 no recorded run
Lebhoryi/learn_monodepth reimplementation (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
rickgroen/depthgan extension (classifier label)
classifier basis: classifier_2025
0 ran · 3 no recorded run
FunctionStatusWhere it lives
compute_errors Ran
ran, violated the contract we drafted
IcarusWizard/monodepth-paddle/eval/evaluation_utils.py
code served (permissive licence) · get_code("d83582de454a0b40")
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 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 numpy as np
import torch

torch.manual_seed(0)

# Create small numpy arrays for ground truth and predictions
# These should be 1D arrays of depth values (common for depth estimation tasks)
gt = np.array([1.0, 2.0, 3.0, 4.0, 5.0], dtype=np.float32)
pred = np.array([1.1, 1.9, 3.2, 3.8, 5.1], dtype=np.float32)

ARGS = {
    "gt": gt,
    "pred": pred,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 1, 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
count_text_lines Ran
ran, honoured the contract we drafted
IcarusWizard/monodepth-paddle/utils.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from iodncookie/my_loss_monodepth_master, is pointer only (licence: NOASSERTION) · get_code("bed135371a969180")
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 iodncookie/my_loss_monodepth_master, 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.

count_text_lines Ran
ran, honoured the contract we drafted
Lebhoryi/learn_monodepth/monodepth_main.py
pointer only (licence: NOASSERTION) · get_code("914c9ab4e7b7469a")
How it ran

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

gradient_x Ran
ran on a synthesized input
IcarusWizard/monodepth-paddle/loss.py
code served (permissive licence) · get_code("f98fd14e1515b523")
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 4, dtype family float, shape (2, 3, 4, 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 a 4D tensor (batch, channels, height, width)
# It computes gradients along the width dimension (last dimension)
# by subtracting adjacent columns
img = torch.randn(2, 3, 4, 5)  # batch=2, channels=3, height=4, width=5

ARGS = {
    "img": img
}
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 4, dtype family float, shape (2, 3, 4, 4) — shape (2, 3, 4, 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
gradient_y Ran
ran on a synthesized input
IcarusWizard/monodepth-paddle/loss.py
code served (permissive licence) · get_code("7155e35b4a8e3f1d")
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 4, dtype family float, shape (2, 4, 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 torch
import numpy as np

torch.manual_seed(0)

# The function expects img to be a 4D tensor
# It performs slicing on dimensions 2 and 3
# img[:, :, :-1, :] and img[:, :, 1:, :] suggest shape (batch, channels, height, width)
# We'll create a small tensor with distinct dimension sizes for probing

img = torch.randn(2, 4, 5, 3)

ARGS = {
    'img': img
}
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 Tensor, ndim 4, dtype family float, shape (2, 4, 4, 3) — shape (2, 4, 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
load_gt_disp_kitti Ran
ran on a synthesized input
IcarusWizard/monodepth-paddle/eval/evaluation_utils.py
code served (permissive licence) · get_code("6f8a54ff22b913e2")
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 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 numpy as np
import cv2
import tempfile
import os

# Create a temporary directory structure to simulate the KITTI dataset
temp_dir = tempfile.mkdtemp()
training_dir = os.path.join(temp_dir, 'training', 'disp_noc_0')
os.makedirs(training_dir, exist_ok=True)

# Create 200 dummy disparity images
for i in range(200):
    # Create a small dummy disparity image (uint16 format, as KITTI uses)
    # The function reads with cv2.imread(..., -1) which preserves the original format
    disp_data = np.random.randint(0, 5000, size=(32, 64), dtype=np.uint16)
    filename = os.path.join(training_dir, str(i).zfill(6) + '_10.png')
    cv2.imwrite(filename, disp_data)

ARGS = {
    'path': temp_dir
}
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 list, ndim 3, 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
post_process_disparity Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
mrharicot/monodepth/monodepth_main.py
pointer only (licence: NONE); the stored copy get_code serves, from iodncookie/my_loss_monodepth_master, is pointer only (licence: NOASSERTION) · get_code("92cb86f70b5d6123")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, mrharicot/monodepth 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.

post_process_disparity Ran
ran on a synthesized input
IcarusWizard/monodepth-paddle/utils.py
code served (permissive licence) · get_code("450c4a6f57ea4ed1")
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, 6) 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 with batch size 2
# disp should have shape (2, H, W) where we can extract h, w from last 2 dims
h, w = 4, 6
disp = np.random.randn(2, h, w).astype(np.float32)

ARGS = {
    "disp": disp
}
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 (4, 6) — shape (4, 6) 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
convert_disps_to_depths_kitti Not yet run
unverified (harvested, no recorded run)
IcarusWizard/monodepth-paddle/eval/evaluation_utils.py
code served (permissive licence) · get_code("cf98eb3840092327")
How it ran

no invocation recorded.

evaluate_cityscapes Not yet run
unverified (harvested, no recorded run)
rickgroen/depthgan/evaluate.py
pointer only (licence: NONE) · get_code("4083ce7b80803fcd")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, rickgroen/depthgan 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. No invocation recorded.

evaluate_eigen Not yet run
unverified (harvested, no recorded run)
rickgroen/depthgan/evaluate.py
pointer only (licence: NONE) · get_code("95194f001fcc993e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, rickgroen/depthgan 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. No invocation recorded.

evaluate_kitti Not yet run
unverified (harvested, no recorded run)
rickgroen/depthgan/evaluate.py
pointer only (licence: NONE) · get_code("557c80de93088f84")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, rickgroen/depthgan 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. No invocation recorded.

Also present in other papers' code

Of 12 samples lifted from this paper's linked repositories, 12 carry a function identity and 0 do not. Of the 12 distinct functions with an identity, 8 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 8 later) and 4 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
compute_errors 24 other papers
24 later
1803.02276 (2018-03)
GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Pose
1806.01260 (2018-06)
Digging Into Self-Supervised Monocular Depth Estimation
1909.09051 (2019-09)
Self-Supervised Monocular Depth Hints
and 21 more not named here
post_process_disparity 3 other papers
3 later
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
1806.01260 (2018-06)
Digging Into Self-Supervised Monocular Depth Estimation
convert_disps_to_depths_kitti 2 other papers
2 later
1803.02276 (2018-03)
GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Pose
1909.09115 (2019-09)
Self-Supervised Learning of Depth and Motion Under Photometric Inconsistency
count_text_lines 2 other papers
2 later
1704.03489 (2017-04)
CNN-SLAM: Real-time dense monocular SLAM with learned depth prediction
1806.01260 (2018-06)
Digging Into Self-Supervised Monocular Depth Estimation
load_gt_disp_kitti 2 other papers
2 later
1803.02276 (2018-03)
GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Pose
1909.09115 (2019-09)
Self-Supervised Learning of Depth and Motion Under Photometric Inconsistency
evaluate_cityscapes 1 other paper
1 later
1910.13340 (2019-10)
On the Benefit of Adversarial Training for Monocular Depth Estimation
evaluate_eigen 1 other paper
1 later
1910.13340 (2019-10)
On the Benefit of Adversarial Training for Monocular Depth Estimation
evaluate_kitti 1 other paper
1 later
1910.13340 (2019-10)
On the Benefit of Adversarial Training for Monocular Depth Estimation

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

Learning based methods have shown very promising results for the task of depth estimation in single images. However, most existing approaches treat depth prediction as a supervised regression problem and as a result, require vast quantities of corresponding ground truth depth data for training. Just recording quality depth data in a range of environments is a challenging problem. In this paper, we innovate beyond existing approaches, replacing the use of explicit depth data during training with easier-to-obtain binocular stereo footage. We propose a novel training objective that enables our convolutional neural network to learn to perform single image depth estimation, despite the absence of ground truth depth data. Exploiting epipolar geometry constraints, we generate disparity images by training our network with an image reconstruction loss. We show that solving for image reconstruction alone results in poor quality depth images. To overcome this problem, we propose a novel training loss that enforces consistency between the disparities produced relative to both the left and right images, leading to improved performance and robustness compared to existing approaches. Our method produces state of the art results for monocular depth estimation on the KITTI driving dataset, even outperforming supervised methods that have been trained with ground truth depth.

For agents

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

get_harvested_code_for_paper("1609.03677")
get_code_for_paper("1609.03677")
have("1609.03677")

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

curl https://syntology.ai/api/ran/1609.03677.json

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

[![Syntology run record](https://syntology.ai/api/ran/1609.03677.svg)](https://syntology.ai/paper/1609.03677)

Connect an agent — have() is free.