SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2004.01526 · 2020

RANSAC-Flow: generic two-stage image alignment

arXiv · PDF · Open in the Atlas

Code that ran

1 of 1 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, 1 violated it and 0 have no contract verdict; 0 failures of our instrument; 0 no recorded run), measured 2026-11-21; 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/2004.01526.json · badge: /api/ran/2004.01526.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
XiSHEN0220/RANSAC-Flow canonical (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
FunctionStatusWhere it lives
get_Avg_Image Ran
ran, violated the contract we drafted
XiSHEN0220/RANSAC-Flow/quick_start/align2images.py
code served (permissive licence) · get_code("ca2185ff992b7e52")
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 Image. 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 PIL.Image as Image
import numpy as np

# Create two small PIL Images with different pixel values
# Image 1: 4x3 image with values in range [0, 255]
Is_array = np.array([
    [[100, 120, 140], [150, 160, 170], [180, 190, 200], [210, 220, 230]],
    [[50, 60, 70], [80, 90, 100], [110, 120, 130], [140, 150, 160]]
], dtype=np.uint8)
Is = Image.fromarray(Is_array)

# Image 2: 4x3 image with different values
It_array = np.array([
    [[200, 210, 220], [230, 240, 250], [255, 255, 255], [200, 210, 220]],
    [[100, 110, 120], [130, 140, 150], [160, 170, 180], [190, 200, 210]]
], dtype=np.uint8)
It = Image.fromarray(It_array)

ARGS = {
    "Is": Is,
    "It": It
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
PIL, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Image — a Image output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Image output the recorded ndim 3 and dtype family int 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

Also present in other papers' code

Of 1 samples lifted from this paper's linked repositories, 1 carry a function identity and 0 do not. Of the 1 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 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.

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 2026-11-21.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

This paper considers the generic problem of dense alignment between two images, whether they be two frames of a video, two widely different views of a scene, two paintings depicting similar content, etc. Whereas each such task is typically addressed with a domain-specific solution, we show that a simple unsupervised approach performs surprisingly well across a range of tasks. Our main insight is that parametric and non-parametric alignment methods have complementary strengths. We propose a two-stage process: first, a feature-based parametric coarse alignment using one or more homographies, followed by non-parametric fine pixel-wise alignment. Coarse alignment is performed using RANSAC on off-the-shelf deep features. Fine alignment is learned in an unsupervised way by a deep network which optimizes a standard structural similarity metric (SSIM) between the two images, plus cycle-consistency. Despite its simplicity, our method shows competitive results on a range of tasks and datasets, including unsupervised optical flow on KITTI, dense correspondences on Hpatches, two-view geometry estimation on YFCC100M, localization on Aachen Day-Night, and, for the first time, fine alignment of artworks on the Brughel dataset. Our code and data are available at http://imagine.enpc.fr/~shenx/RANSAC-Flow/

For agents

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

get_harvested_code_for_paper("2004.01526")
get_code_for_paper("2004.01526")
have("2004.01526")

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

curl https://syntology.ai/api/ran/2004.01526.json

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

[![Syntology run record](https://syntology.ai/api/ran/2004.01526.svg)](https://syntology.ai/paper/2004.01526)

Connect an agent — have() is free.