SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2207.09291 · ECCV · 2022

3D Room Layout Estimation from a Cubemap of Panorama Image via Deep Manhattan Hough Transform

Yue Gao, Yining Zhao, Wen Chao, Zhou Xue

arXiv · PDF · Open in the Atlas

Code that ran

7 of 12 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (5 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; 2 failures of our instrument; 5 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/2207.09291.json · badge: /api/ran/2207.09291.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
Starrah/DMH-Net community
Papers with Code archive
7 ran · 5 no recorded run
FunctionStatusWhere it lives
BasicBlock Ran
ran on a synthesized input · constructed an object; no result was computed
Starrah/DMH-Net/model.py
code served (permissive licence) · get_code("38cddce66e8f818b")
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 an instance of its own class, BasicBlock: the run constructed the object and did not call it, so no result was computed. 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 torch.nn as nn

torch.manual_seed(0)

# Create a simple downsample module that matches what BasicBlock expects
downsample_module = nn.Sequential(
    nn.Conv2d(4, 8, kernel_size=1, stride=2, bias=False),
    nn.BatchNorm2d(8)
)

ARGS = {
    'inplanes': 4,
    'planes': 8,
    'stride': 2,
    'downsample': downsample_module,
    'dilation': (1, 1),
    'residual': True
}
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 BasicBlock — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a BasicBlock 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
Bottleneck Ran
ran on a synthesized input · constructed an object; no result was computed
Starrah/DMH-Net/model.py
code served (permissive licence) · get_code("6fb982e46213aab2")
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 an instance of its own class, Bottleneck: the run constructed the object and did not call it, so no result was computed. 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 torch.nn as nn

torch.manual_seed(0)

# Create a downsample module that matches what the forward pass expects
# It takes input x and produces output matching the expanded channels
downsample = nn.Sequential(
    nn.Conv2d(64, 256, kernel_size=1, stride=2, bias=False),
    nn.BatchNorm2d(256)
)

# Create input tensor: batch=2, channels=64, height=4, width=3
x = torch.randn(2, 64, 4, 3)

ARGS = {
    'inplanes': 64,
    'planes': 64,
    'stride': 2,
    'downsample': downsample,
    'dilation': (1, 1),
    'residual': True
}
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 Bottleneck — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a Bottleneck 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
FusionHoughStage Ran
ran on a synthesized input · constructed an object; no result was computed
Starrah/DMH-Net/model.py
code served (permissive licence) · get_code("74ed775ecbbbf553")
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 an instance of its own class, FusionHoughStage: the run constructed the object and did not call it, so no result was computed. 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 torch.nn as nn

torch.manual_seed(0)

class StandInConfig:
    def __init__(self):
        self.some_attr = "config_value"

class CustomUpsampler(nn.Module):
    def __init__(self, scale_factor):
        super(CustomUpsampler, self).__init__()
        self.scale_factor = scale_factor
    
    def forward(self, x):
        return nn.functional.interpolate(x, scale_factor=(self.scale_factor, 1), mode='bilinear', align_corners=False)

cfg = StandInConfig()
type_str = "test_type"
c_ori = 16
c0 = 32
c1 = 32
c2 = 32
c3 = 32
c4 = 32
upsample_rate = [2, 4, 8, 8, 8]
upsampler_class = CustomUpsampler

ARGS = {
    "cfg": cfg,
    "type": type_str,
    "c_ori": c_ori,
    "c0": c0,
    "c1": c1,
    "c2": c2,
    "c3": c3,
    "c4": c4,
    "upsample_rate": upsample_rate,
    "upsampler_class": upsampler_class
}
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 FusionHoughStage — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a FusionHoughStage 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
HoughNewUpSampler Ran
ran on a synthesized input · constructed an object; no result was computed
Starrah/DMH-Net/model.py
code served (permissive licence) · get_code("9a241dda50db8440")
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 an instance of its own class, HoughNewUpSampler: the run constructed the object and did not call it, so no result was computed. 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 torch.nn as nn

torch.manual_seed(0)

ARGS = {
    "upsample_rate": 2
}
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 HoughNewUpSampler — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a HoughNewUpSampler 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
OfficialResnetWrapper Ran
ran; our contract draft was wrong, not the code
Starrah/DMH-Net/model.py
code served (permissive licence) · get_code("e911082d5e2918be")
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 SimpleResnetLike. 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 torch.nn as nn
import types
from typing import Tuple

torch.manual_seed(0)

class SimpleResnetLike(nn.Module):
    """Minimal ResNet-like model with required attributes and methods."""
    def __init__(self):
        super().__init__()
        self.conv1 = nn.Conv2d(3, 4, kernel_size=7, stride=2, padding=3)
        self.bn1 = nn.BatchNorm2d(4)
        self.relu = nn.ReLU(inplace=True)
        self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
        self.layer1 = nn.Sequential(nn.Conv2d(4, 4, 3, padding=1))
        self.layer2 = nn.Sequential(nn.Conv2d(4, 4, 3, padding=1))
        self.layer3 = nn.Sequential(nn.Conv2d(4, 4, 3, padding=1))
        self.layer4 = nn.Sequential(nn.Conv2d(4, 4, 3, padding=1))

model = SimpleResnetLike()

ARGS = {
    "model": model
}
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 SimpleResnetLike — a SimpleResnetLike output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a SimpleResnetLike 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
PerspectiveE2PP2E Ran
ran on a synthesized input · constructed an object; no result was computed
Starrah/DMH-Net/model.py
code served (permissive licence) · get_code("25379e1cb6b596bc")
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 an instance of its own class, PerspectiveE2PP2E: the run constructed the object and did not call it, so no result was computed. 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 torch.nn as nn
import math

torch.manual_seed(0)

class MockConfig:
    def __init__(self):
        self.MODEL = {
            'CONV1_CHANNEL_FACTOR': 2,
            'HOUGH': type('obj', (object,), {
                'CLINE_TYPE': 'NEW'
            })()
        }
    
    def get(self, key, default=None):
        parts = key.split('.')
        obj = self
        for part in parts:
            if isinstance(obj, dict):
                obj = obj.get(part)
            else:
                obj = getattr(obj, part, None)
            if obj is None:
                return default
        return obj

cfg = MockConfig()

ARGS = {
    'cfg': cfg,
    'input_h': 256,
    'input_w': 512,
    'pers_h': 128,
    'fov': 90.0,
    'input_feat': 64,
    'output_feat': 32,
    'hough_angles_num': 180,
    'hoguh_clines_tole': 1.0
}
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 PerspectiveE2PP2E — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a PerspectiveE2PP2E 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
conv3x3 Ran
ran; our contract draft was wrong, not the code
Starrah/DMH-Net/model.py
code served (permissive licence) · get_code("0e722c9ff0920473")
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 Conv2d. 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 torch.nn as nn

torch.manual_seed(0)

ARGS = {
    "in_planes": 3,
    "out_planes": 64,
    "stride": 1,
    "padding": 1,
    "dilation": 1,
}
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 Conv2d — a Conv2d output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Conv2d 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
DMHNet Not yet run
unverified (harvested, no recorded run)
Starrah/DMH-Net/model.py
code served (permissive licence) · get_code("5e730ddb778da042")
How it ran

no invocation recorded.

DRN Not yet run
unverified (harvested, no recorded run)
Starrah/DMH-Net/model.py
code served (permissive licence) · get_code("91a270fec24bc94b")
How it ran

no invocation recorded.

drn_d_22 Not yet run
unverified (harvested, no recorded run)
Starrah/DMH-Net/model.py
code served (permissive licence) · get_code("adfda3dcdeed24a0")
How it ran

no invocation recorded.

drn_d_38 Not yet run
unverified (harvested, no recorded run)
Starrah/DMH-Net/model.py
code served (permissive licence) · get_code("27116490dcbf7321")
How it ran

no invocation recorded.

drn_d_54 Not yet run
unverified (harvested, no recorded run)
Starrah/DMH-Net/model.py
code served (permissive licence) · get_code("9a0e4317db1d8684")
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, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 0 later) and 11 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
conv3x3
brick of this paper's assembly: helper
6 other papers
6 dated earlier
1808.07535 (2018-08)
Learning Hierarchical Semantic Image Manipulation through Structured Representations
1906.05856 (2019-06)
Detecting Photoshopped Faces by Scripting Photoshop
1908.06702 (2019-08)
Floor-SP: Inverse CAD for Floorplans by Sequential Room-wise Shortest Path
and 3 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

Significant geometric structures can be compactly described by global wireframes in the estimation of 3D room layout from a single panoramic image. Based on this observation, we present an alternative approach to estimate the walls in 3D space by modeling long-range geometric patterns in a learnable Hough Transform block. We transform the image feature from a cubemap tile to the Hough space of a Manhattan world and directly map the feature to the geometric output. The convolutional layers not only learn the local gradient-like line features, but also utilize the global information to successfully predict occluded walls with a simple network structure. Unlike most previous work, the predictions are performed individually on each cubemap tile, and then assembled to get the layout estimation. Experimental results show that we achieve comparable results with recent state-of-the-art in prediction accuracy and performance. Code is available at https://github.com/Starrah/DMH-Net.

For agents

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

get_harvested_code_for_paper("2207.09291")
get_code_for_paper("2207.09291")
have("2207.09291")

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

curl https://syntology.ai/api/ran/2207.09291.json

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

[![Syntology run record](https://syntology.ai/api/ran/2207.09291.svg)](https://syntology.ai/paper/2207.09291)

Connect an agent — have() is free.