SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1907.01341 · 2019

Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer

arXiv · PDF · Open in the Atlas

Code that ran

13 of 17 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, 0 violated it and 6 have no contract verdict; 6 failures 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/1907.01341.json · badge: /api/ran/1907.01341.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
isl-org/MiDaS canonical (classifier label)
classifier basis: classifier_2025
1 ran · 2 no recorded run
freshtan/midas_v2 community (classifier label)
classifier basis not recorded on the link
6 ran · 2 no recorded run
anlok/depthmap-loktev community (classifier label)
classifier basis not recorded on the link
4 ran · 0 no recorded run
lasinger/3DVideos2Stereo community (classifier label)
classifier basis not recorded on the link
2 ran · 0 no recorded run
FunctionStatusWhere it lives
apply_min_size Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
anlok/depthmap-loktev/models/transforms.py
code served (permissive licence) · get_code("8d4e5ab503856d09")
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 int; 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 math

# Create a sample dictionary with required keys
sample = {
    'disparity': np.random.rand(10, 15).astype(np.float32),
    'image': np.random.randint(0, 256, (10, 15, 3), dtype=np.uint8),
    'mask': np.random.rand(10, 15) > 0.5
}

# Define the size parameter
size = (20, 25)

# Define the image interpolation method
image_interpolation_method = cv2.INTER_AREA

ARGS = {
    'sample': sample,
    'size': size,
    'image_interpolation_method': image_interpolation_method
}
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 tuple, ndim 1, dtype family int — 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
associate Ran
ran on a synthesized input
freshtan/midas_v2/preprocess/associate.py
code served (permissive licence) · get_code("c0f7dd2e78f91f10")
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 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 torch
import numpy as np

torch.manual_seed(0)

# Construct valid arguments for the associate function
# The function takes two dictionaries where keys are timestamps (floats) and values are data
# It also takes an offset (time delay) and max_difference (search radius)

first_list1 = {
    1.0: np.array([1, 2, 3, 4]),
    2.5: np.array([5, 6, 7, 8]),
    4.0: np.array([9, 10, 11, 12]),
}

second_list1 = {
    1.1: np.array([13, 14, 15, 16]),
    2.6: np.array([17, 18, 19, 20]),
    5.0: np.array([21, 22, 23, 24]),
}

offset = 0.0
max_difference = 0.3

ARGS = {
    "first_list1": first_list1,
    "second_list1": second_list1,
    "offset": offset,
    "max_difference": max_difference,
}
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 list, ndim 2, 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
merge Ran
ran; our contract draft was wrong, not the code
freshtan/midas_v2/src/config.py
code served (permissive licence) · get_code("b9e24c3e3e0e88a7")
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 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 torch
import argparse

torch.manual_seed(0)

# Create a mock args object with some attributes
args = argparse.Namespace(
    learning_rate=0.001,
    batch_size=32,
    epochs=10,
    model_name="test_model",
    debug=True,
    seed=42
)

# Create a base configuration dictionary
cfg = {
    "default_lr": 0.0001,
    "default_batch": 16,
    "dataset": "cifar10"
}

ARGS = {
    "args": args,
    "cfg": cfg
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — 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
parse_cli_to_yaml Ran
ran; our contract draft was wrong, not the code
freshtan/midas_v2/src/config.py
code served (permissive licence) · get_code("738456e1b7388e7e")
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 Namespace. 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 argparse
import ast

# Create minimal parent parser
parent_parser = argparse.ArgumentParser(add_help=False)

# Create base configuration dict with various types
cfg = {
    'learning_rate': 0.001,
    'batch_size': 32,
    'epochs': 10,
    'use_cuda': False,
    'model_name': 'resnet50',
    'dropout': 0.5,
    'debug': True,
    'nested_list': [1, 2, 3],  # This will be skipped since it's a list
    'nested_dict': {'a': 1},   # This will be skipped since it's a dict
}

# Create helper descriptions
helper = {
    'learning_rate': 'Learning rate for optimizer',
    'batch_size': 'Batch size for training',
    'epochs': 'Number of training epochs',
    'use_cuda': 'Whether to use CUDA',
    'model_name': 'Name of the model architecture',
    'dropout': 'Dropout rate',
    'debug': 'Enable debug mode',
}

# Create choices for specific parameters
choices = {
    'model_name': ['resnet50', 'vgg16', 'mobilenet'],
}

# Set config path
cfg_path = 'default_config.yaml'

ARGS = {
    'parser': parent_parser,
    'cfg': cfg,
    'helper': helper,
    'choices': choices,
    'cfg_path': cfg_path,
}
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 Namespace — a Namespace output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Namespace 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
parse_yaml Ran
ran on a synthesized input
freshtan/midas_v2/src/config.py
code served (permissive licence) · get_code("96a9939953d5992d")
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 tempfile
import os
import yaml

# Create a temporary YAML file with valid config structure
temp_dir = tempfile.mkdtemp()
yaml_path = os.path.join(temp_dir, "config.yaml")

# Write a valid YAML file with 3 documents: config, helper, and choices
yaml_content = """
model: resnet50
learning_rate: 0.001
batch_size: 32
---
model: "Model architecture to use"
learning_rate: "Learning rate for optimization"
batch_size: "Batch size for training"
---
model: [resnet50, resnet101, vgg16]
learning_rate: [0.0001, 0.001, 0.01]
batch_size: [16, 32, 64]
"""

with open(yaml_path, 'w') as f:
    f.write(yaml_content)

ARGS = {
    "yaml_path": yaml_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
yaml — 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
patch_embed_forward Ran
ran; our contract draft was wrong, not the code
isl-org/MiDaS/midas/backbones/beit.py
code served (permissive licence) · get_code("a3b0b33caf369c41")
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 3, dtype family float, shape (2, 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
import torch.nn as nn

torch.manual_seed(0)

class PatchEmbed(nn.Module):
    def __init__(self):
        super().__init__()
        # proj: takes input and projects it
        # Input shape: (batch, channels, height, width) -> (batch, embed_dim, h', w')
        self.proj = nn.Conv2d(3, 4, kernel_size=2, stride=2)
        self.flatten = True
        self.norm = nn.LayerNorm(4)
    
    def forward(self, x):
        x = self.proj(x)
        if self.flatten:
            x = x.flatten(2).transpose(1, 2)
        x = self.norm(x)
        return x

# Create instance
patch_embed = PatchEmbed()

# Create input tensor: (batch=2, channels=3, height=4, width=4)
x = torch.randn(2, 3, 4, 4)

ARGS = {
    "self": patch_embed,
    "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 3, dtype family float, shape (2, 4, 4) — shape (2, 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
processShotFile Ran
ran on a synthesized input
lasinger/3DVideos2Stereo/genTraining_recurr.py
code served (permissive licence) · get_code("079a28e19eb8f028")
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 directory and files for testing
temp_dir = tempfile.mkdtemp()
video_prefix = temp_dir + "/"

# Create a sample shot file with the expected format
shot_filename = "shot.txt"
shot_file_path = os.path.join(temp_dir, shot_filename)

# Write test data in the format the function expects
with open(shot_file_path, 'w') as f:
    f.write("some_prefix pkt_pts_time=00.12345 some_suffix\n")
    f.write("another_line pkt_pts_time=01.45678 more_data\n")
    f.write("line_without_marker some other content\n")
    f.write("final_line pkt_pts_time=02.98765 end\n")

ARGS = {
    "video": video_prefix,
    "shotFile": shot_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_file_list Ran
ran on a synthesized input
freshtan/midas_v2/preprocess/associate.py
code served (permissive licence) · get_code("780a0dcc75fb0c82")
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 tempfile
import os

# Create a temporary file with trajectory data
temp_file = tempfile.NamedTemporaryFile(mode='w', delete=False, suffix='.txt')
temp_filename = temp_file.name

# Write sample trajectory data in the expected format
# Format: "stamp d1 d2 d3 ..."
temp_file.write("1234567890.123 0.5 1.2 3.4 4.5\n")
temp_file.write("1234567891.456 1.1 2.3 4.5 5.6\n")
temp_file.write("# This is a comment and should be skipped\n")
temp_file.write("1234567892.789 2.2 3.4 5.6 6.7\n")
temp_file.close()

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 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
read_flow Ran
ran on a synthesized input
lasinger/3DVideos2Stereo/get_disp_and_uncertainty.py
code served (permissive licence) · get_code("484108557b544812")
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 numpy as np
import tempfile
import os

# Create a temporary file to use as the filename argument
temp_dir = tempfile.gettempdir()
temp_filename = os.path.join(temp_dir, "test_flow.flo")

# Create a minimal valid flow file (or just use a string path)
# Since the function doesn't actually read from disk in the provided code,
# we just need a valid filename string
filename = temp_filename

ARGS = {
    "filename": filename
}
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, 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
read_image Ran
ran, honoured the contract we drafted
anlok/depthmap-loktev/utils.py
pointer only (licence: MIT); the stored copy get_code serves, from xingy038/ctnerf, is pointer only (licence: NONE) · get_code("fa28021adde0f186")
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 xingy038/ctnerf, 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.

read_pfm Ran
ran; our contract draft was wrong, not the code
anlok/depthmap-loktev/utils.py
code served (permissive licence) · get_code("188a19865f88f383")
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 tempfile
import os
import numpy as np

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

# Create a valid PFM file (color, 2x3 image)
height, width = 3, 2
with open(pfm_path, 'wb') as f:
    # Header: "PF" for color
    f.write(b"PF\n")
    # Dimensions: width height
    f.write(f"{width} {height}\n".encode('ascii'))
    # Scale: positive indicates big-endian
    f.write(b"1.0\n")
    # Data: height x width x 3 floats (will be flipped vertically)
    data = np.random.rand(height, width, 3).astype('>f4')
    data = np.flipud(data)  # Flip before writing since read_pfm will flip again
    data.tofile(f)

ARGS = {
    "path": 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
resize_image Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
anlok/depthmap-loktev/utils.py
code served (permissive licence) · get_code("80ea105639cd9efd")
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 (1, 3, 384, 288) 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 cv2
import torch

torch.manual_seed(0)

# Create a small test image: 3 channels (BGR), height=200, width=150
# Using uint8 to match typical OpenCV image format
img = np.random.randint(0, 256, size=(200, 150, 3), dtype=np.uint8)

ARGS = {
    "img": img
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
cv2, 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 (1, 3, 384, 288) — shape (1, 3, 384, 288) 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
write_depth Ran
ran on a synthesized input
freshtan/midas_v2/src/util.py
code served (permissive licence) · get_code("d0f2d7d797bf8806")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned ndarray, ndim 2, dtype family float, shape (4, 3) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np
import tempfile
import os

# Create a temporary directory for output files
temp_dir = tempfile.gettempdir()

# Create a valid depth array (2D numpy array of float32)
# Using shape 4x3 to have distinct dimensions
depth = np.random.rand(4, 3).astype(np.float32) * 10.0

# Create the path without extension
path = os.path.join(temp_dir, 'test_depth')

# Define arguments for write_depth function
ARGS = {
    'path': path,
    'depth': depth,
    'bits': 1
}
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 2, dtype family float, shape (4, 3) — shape (4, 3) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
attention_forward Not yet run
unverified (harvested, no recorded run)
isl-org/MiDaS/midas/backbones/beit.py
code served (permissive licence) · get_code("cc0b35f6d7118df1")
How it ran

no invocation recorded.

depth_read_kitti Not yet run
unverified (harvested, no recorded run)
freshtan/midas_v2/src/util.py
code served (permissive licence) · get_code("98b6d75cef37e16d")
How it ran

no invocation recorded.

forward_beit Not yet run
unverified (harvested, no recorded run)
isl-org/MiDaS/midas/backbones/beit.py
code served (permissive licence) · get_code("62d386dcfc041ca8")
How it ran

no invocation recorded.

get_eval_result Not yet run
unverified (harvested, no recorded run)
freshtan/midas_v2/postprocess.py
code served (permissive licence) · get_code("c3d82023511f51f2")
How it ran

no invocation recorded.

Also present in other papers' code

Of 17 samples lifted from this paper's linked repositories, 17 carry a function identity and 0 do not. Of the 17 distinct functions with an identity, 10 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 3 the same month, 10 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
merge 28 other papers
13 dated earlier, 1 the same month, 14 later
1406.1078 (2014-06)
Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
1409.3215 (2014-09)
Sequence to Sequence Learning with Neural Networks
1512.00567 (2015-12)
Rethinking the Inception Architecture for Computer Vision
and 25 more not named here
parse_cli_to_yaml 20 other papers
11 dated earlier, 1 the same month, 8 later
1406.1078 (2014-06)
Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
1409.3215 (2014-09)
Sequence to Sequence Learning with Neural Networks
1512.00567 (2015-12)
Rethinking the Inception Architecture for Computer Vision
and 17 more not named here
parse_yaml 15 other papers
9 dated earlier, 1 the same month, 5 later
1406.1078 (2014-06)
Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
1409.3215 (2014-09)
Sequence to Sequence Learning with Neural Networks
1512.00567 (2015-12)
Rethinking the Inception Architecture for Computer Vision
and 12 more not named here
apply_min_size 4 other papers
4 later
2210.01035 (2022-10)
Expediting Large-Scale Vision Transformer for Dense Prediction without Fine-tuning
2305.19201 (2023-05)
DäRF: Boosting Radiance Fields from Sparse Inputs with Monocular Depth Adaptation
2310.15171 (2023-10)
RoboDepth: Robust Out-of-Distribution Depth Estimation under Corruptions
and 1 more not named here
read_image 3 other papers
3 later
2310.15171 (2023-10)
RoboDepth: Robust Out-of-Distribution Depth Estimation under Corruptions
2312.00206 (2023-12)
SparseGS: Sparse View Synthesis using 3D Gaussian Splatting
2401.04861 (2024-01)
CTNeRF: Cross-Time Transformer for Dynamic Neural Radiance Field from Monocular Video
attention_forward 2 other papers
2 later
2103.13413 (2021-03)
Vision Transformers for Dense Prediction
2307.14460 (2023-07)
MiDaS v3.1 -- A Model Zoo for Robust Monocular Relative Depth Estimation
forward_beit 2 other papers
2 later
2103.13413 (2021-03)
Vision Transformers for Dense Prediction
2307.14460 (2023-07)
MiDaS v3.1 -- A Model Zoo for Robust Monocular Relative Depth Estimation
patch_embed_forward 2 other papers
2 later
2103.13413 (2021-03)
Vision Transformers for Dense Prediction
2307.14460 (2023-07)
MiDaS v3.1 -- A Model Zoo for Robust Monocular Relative Depth Estimation
read_pfm 2 other papers
2 later
2310.15171 (2023-10)
RoboDepth: Robust Out-of-Distribution Depth Estimation under Corruptions
2410.10799 (2024-10)
Towards Foundation Models for 3D Vision: How Close Are We?
resize_image 1 other paper
1 later
2310.15171 (2023-10)
RoboDepth: Robust Out-of-Distribution Depth Estimation under Corruptions

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

The success of monocular depth estimation relies on large and diverse training sets. Due to the challenges associated with acquiring dense ground-truth depth across different environments at scale, a number of datasets with distinct characteristics and biases have emerged. We develop tools that enable mixing multiple datasets during training, even if their annotations are incompatible. In particular, we propose a robust training objective that is invariant to changes in depth range and scale, advocate the use of principled multi-objective learning to combine data from different sources, and highlight the importance of pretraining encoders on auxiliary tasks. Armed with these tools, we experiment with five diverse training datasets, including a new, massive data source: 3D films. To demonstrate the generalization power of our approach we use zero-shot cross-dataset transfer}, i.e. we evaluate on datasets that were not seen during training. The experiments confirm that mixing data from complementary sources greatly improves monocular depth estimation. Our approach clearly outperforms competing methods across diverse datasets, setting a new state of the art for monocular depth estimation. Some results are shown in the supplementary video at https://youtu.be/D46FzVyL9I8

For agents

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

get_harvested_code_for_paper("1907.01341")
get_code_for_paper("1907.01341")
have("1907.01341")

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

curl https://syntology.ai/api/ran/1907.01341.json

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

[![Syntology run record](https://syntology.ai/api/ran/1907.01341.svg)](https://syntology.ai/paper/1907.01341)

Connect an agent — have() is free.