SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2203.16787 · CVPR · 2022

Reflection and Rotation Symmetry Detection via Equivariant Learning

Minsu Cho, Suha Kwak, Byungjin Kim, Ahyun Seo

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; 0 honoured the contract we drafted, 0 violated it and 5 have no contract verdict; 3 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/2203.16787.json · badge: /api/ran/2203.16787.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
ahyunSeo/EquiSym canonical (classifier label)
classifier basis not recorded on the link
8 ran · 4 no recorded run
FunctionStatusWhere it lives
as_numpy Ran
ran; our contract draft was wrong, not the code
ahyunSeo/EquiSym/modeling/sync_batchnorm/unittest.py
pointer only (licence: MIT); the stored copy get_code serves, from chenhongruixuan/i3pe, is pointer only (licence: NONE) · get_code("6b37c8eb77e486dc")
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 chenhongruixuan/i3pe, 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.

conv1x1 Ran
ran; our contract draft was wrong, not the code
ahyunSeo/EquiSym/modeling/resnet.py
pointer only (licence: MIT); the stored copy get_code serves, from medaitech/scrd4ad, is pointer only (licence: NONE) · get_code("2a80220dabcb742a")
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 medaitech/scrd4ad, 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.

conv3x3 Ran
ran; our contract draft was wrong, not the code
ahyunSeo/EquiSym/modeling/resnet.py
pointer only (licence: MIT); the stored copy get_code serves, from medaitech/scrd4ad, is pointer only (licence: NONE) · get_code("600ff2c45e0de056")
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 medaitech/scrd4ad, 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.

draw_axis Ran
ran on a synthesized input
ahyunSeo/EquiSym/utils.py
code served (permissive licence) · get_code("6d1c79f0590d1183")
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
from PIL import Image, ImageDraw

# Construct valid arguments for draw_axis function
# The function expects:
# - lines: an iterable of coordinate tuples/arrays (x1, y1, x2, y2 format)
# - size: a tuple (width, height) for the image

# Create sample lines with coordinates
lines = [
    (10, 20, 50, 60),      # line 1: (x1, y1, x2, y2)
    (70, 15, 30, 80),      # line 2: will be rolled since x1 > x2
    (5, 5, 95, 95),        # line 3
]

# Create size as a tuple (width, height)
size = (100, 100)

ARGS = {
    "lines": lines,
    "size": size
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, 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
draw_points Ran
ran on a synthesized input
ahyunSeo/EquiSym/dendi_loader.py
code served (permissive licence) · get_code("45b829b6128c7a7a")
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
from PIL import Image, ImageDraw

# Construct arguments for draw_points function

# points: list of point coordinates
# Each point should be a tuple of (x, y) coordinates
points = [
    (10, 20),
    (15, 25),
]

# orders: list of order values (grayscale intensity values)
# These are used as the fill value when drawing points
# o == 0 gets converted to 255, otherwise o is used directly
orders = [0, 128]

# size: tuple of (width, height) for the image
size = (64, 48)

ARGS = {
    "points": points,
    "orders": orders,
    "size": size,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, 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
match_input_type Ran
ran on a synthesized input
ahyunSeo/EquiSym/utils.py
code served (permissive licence) · get_code("909f73ddeb90d699")
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 float, 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 numpy as np

# Test case 1: 3-channel image (should pass through unchanged)
img_3channel = np.random.rand(4, 5, 3).astype(np.float32)

# Test case 2: Grayscale image (should be stacked to 3 channels)
img_grayscale = np.random.rand(4, 5).astype(np.float32)

# Use the grayscale image as it tests the main logic path
ARGS = {
    "img": img_grayscale
}
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 3, dtype family float, 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
norm Ran
ran on a synthesized input
ahyunSeo/EquiSym/utils.py
code served (permissive licence) · get_code("eac72b9de183eb07")
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 'norm' takes an image tensor as input
# It performs normalization by subtracting mean and dividing by std
# The tensor should have shape (batch, channels, height, width)
# where channels = 3 (for RGB)

img = torch.randn(2, 3, 4, 4)  # batch=2, channels=3, height=4, width=4

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
set_gspace Ran
ran on a synthesized input
ahyunSeo/EquiSym/modeling/eq_resnet.py
code served (permissive licence) · get_code("6300a37e41b7bcc8")
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 os
from e2cnn import gspaces

# Set up the ARGS dictionary with valid arguments for set_gspace
ARGS = {
    'n_angle': 4,
    'flip': True,
    'cutoff_dilation': False,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
e2cnn — 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
build_backbone Not yet run
unverified (harvested, no recorded run)
ahyunSeo/EquiSym/modeling/module.py
code served (permissive licence) · get_code("0c33da5649aaadc7")
How it ran

no invocation recorded.

patch_replication_callback Not yet run
unverified (harvested, no recorded run)
ahyunSeo/EquiSym/modeling/sync_batchnorm/replicate.py
code served (permissive licence) · get_code("af8ed14d63b51a5f")
How it ran

no invocation recorded.

regular_feature_type Not yet run
unverified (harvested, no recorded run)
ahyunSeo/EquiSym/modeling/eq_resnet.py
code served (permissive licence) · get_code("e1b125d5ce751093")
How it ran

no invocation recorded.

trivial_feature_type Not yet run
unverified (harvested, no recorded run)
ahyunSeo/EquiSym/modeling/eq_resnet.py
code served (permissive licence) · get_code("6f410613e19b5bb7")
How it ran

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, 4 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 2 the same month, 4 later) and 8 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
conv1x1 112 other papers
20 dated earlier, 3 the same month, 88 later, 1 same year, order not determinable · 6 only as an assembly brick
1512.03385 (2015-12)
Deep Residual Learning for Image Recognition
1806.01531 (2018-06)
Deep Mixture of Experts via Shallow Embedding
1905.12794 (2019-05)
Fashion IQ: A New Dataset Towards Retrieving Images by Natural Language Feedback
and 109 more not named here
conv3x3 111 other papers
18 dated earlier, 2 the same month, 90 later, 1 same year, order not determinable · 6 only as an assembly brick
1512.03385 (2015-12)
Deep Residual Learning for Image Recognition
1806.01531 (2018-06)
Deep Mixture of Experts via Shallow Embedding
1905.12794 (2019-05)
Fashion IQ: A New Dataset Towards Retrieving Images by Natural Language Feedback
and 108 more not named here
patch_replication_callback 16 other papers
12 dated earlier, 3 later, 1 same year, order not determinable
1612.01105 (2016-12)
Pyramid Scene Parsing Network
1807.10221 (2018-07)
Unified Perceptual Parsing for Scene Understanding
1904.01941 (2019-04)
Character Region Awareness for Text Detection
and 13 more not named here
as_numpy 5 other papers
3 dated earlier, 2 later
2006.00212 (2020-06)
Complex Sequential Understanding through the Awareness of Spatial and Temporal Concepts
aaai_16243 (2021 (year only))
Progressive One-Shot Human Parsing
2111.04426 (2021-11)
3D Siamese Voxel-to-BEV Tracker for Sparse Point Clouds
and 2 more not named here

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 inherent challenge of detecting symmetries stems from arbitrary orientations of symmetry patterns; a reflection symmetry mirrors itself against an axis with a specific orientation while a rotation symmetry matches its rotated copy with a specific orientation. Discovering such symmetry patterns from an image thus benefits from an equivariant feature representation, which varies consistently with reflection and rotation of the image. In this work, we introduce a group-equivariant convolutional network for symmetry detection, dubbed EquiSym, which leverages equivariant feature maps with respect to a dihedral group of reflection and rotation. The proposed network is built end-toend with dihedrally-equivariant layers and trained to output a spatial map for reflection axes or rotation centers. We also present a new dataset, DENse and DIverse symmetry (DENDI), which mitigates limitations of existing benchmarks for reflection and rotation symmetry detection. Experiments show that our method achieves the state of the arts in symmetry detection on LDRS and DENDI datasets.

For agents

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

get_harvested_code_for_paper("2203.16787")
get_code_for_paper("2203.16787")
have("2203.16787")

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

curl https://syntology.ai/api/ran/2203.16787.json

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

[![Syntology run record](https://syntology.ai/api/ran/2203.16787.svg)](https://syntology.ai/paper/2203.16787)

Connect an agent — have() is free.