SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1804.00607 · 2018

MegaDepth: Learning Single-View Depth Prediction from Internet Photos

arXiv · PDF · Open in the Atlas

Code that ran

2 of 3 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; 0 honoured the contract we drafted, 0 violated it and 2 have no contract verdict; 0 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/1804.00607.json · badge: /api/ran/1804.00607.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
zhengqili/MegaDepth community (classifier label)
classifier basis not recorded on the link
2 ran · 1 no recorded run
FunctionStatusWhere it lives
encode Ran
ran on a synthesized input
zhengqili/MegaDepth/util/png.py
code served (permissive licence) · get_code("91d4d7845ec139d1")
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 bytes. 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 struct
import zlib

# Create a simple 2x3 RGB image (2 pixels wide, 3 pixels tall)
# Each pixel is 3 bytes (RGB)
width = 2
height = 3
num_pixels = width * height
num_bytes = num_pixels * 3

# Create a simple RGB buffer: alternating red, green, blue pixels
# Red = (255, 0, 0), Green = (0, 255, 0), Blue = (0, 0, 255)
buf = bytearray()
for i in range(num_pixels):
    if i % 3 == 0:
        buf.extend([255, 0, 0])  # Red
    elif i % 3 == 1:
        buf.extend([0, 255, 0])  # Green
    else:
        buf.extend([0, 0, 255])  # Blue

buf = bytes(buf)

ARGS = {
    'buf': buf,
    'width': width,
    'height': height
}
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 bytes — a bytes output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a bytes 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
tensor2im Ran
ran on a synthesized input
zhengqili/MegaDepth/util/util.py
code served (permissive licence) · get_code("9fe591ca11b7e715")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned ndarray, ndim 3, dtype family int, shape (4, 5, 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)

# Create a tensor with shape (batch=1, channels=3, height=4, width=5)
# The function expects image_tensor[0] to be indexable and have cpu(), float(), numpy() methods
image_tensor = torch.randn(1, 3, 4, 5)

ARGS = {
    'image_tensor': image_tensor,
    'imtype': np.uint8
}
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 ndarray, ndim 3, dtype family int, shape (4, 5, 3) — shape (4, 5, 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
varname Not yet run
unverified (harvested, no recorded run)
zhengqili/MegaDepth/util/util.py
code served (permissive licence) · get_code("4f813f672cd81eda")
How it ran

no invocation recorded.

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 distinct functions with an identity, 2 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 2 later) and 1 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
encode 1 other paper
1 later
1809.09767 (2018-09)
Night-to-Day Image Translation for Retrieval-based Localization
varname 1 other paper
1 later
1809.09767 (2018-09)
Night-to-Day Image Translation for Retrieval-based Localization

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

Single-view depth prediction is a fundamental problem in computer vision. Recently, deep learning methods have led to significant progress, but such methods are limited by the available training data. Current datasets based on 3D sensors have key limitations, including indoor-only images (NYU), small numbers of training examples (Make3D), and sparse sampling (KITTI). We propose to use multi-view Internet photo collections, a virtually unlimited data source, to generate training data via modern structure-from-motion and multi-view stereo (MVS) methods, and present a large depth dataset called MegaDepth based on this idea. Data derived from MVS comes with its own challenges, including noise and unreconstructable objects. We address these challenges with new data cleaning methods, as well as automatically augmenting our data with ordinal depth relations generated using semantic segmentation. We validate the use of large amounts of Internet data by showing that models trained on MegaDepth exhibit strong generalization-not only to novel scenes, but also to other diverse datasets including Make3D, KITTI, and DIW, even when no images from those datasets are seen during training.

For agents

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

get_harvested_code_for_paper("1804.00607")
get_code_for_paper("1804.00607")
have("1804.00607")

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

curl https://syntology.ai/api/ran/1804.00607.json

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

[![Syntology run record](https://syntology.ai/api/ran/1804.00607.svg)](https://syntology.ai/paper/1804.00607)

Connect an agent — have() is free.