SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2002.12212 · 2020

Total3DUnderstanding: Joint Layout, Object Pose and Mesh Reconstruction for Indoor Scenes from a Single Image

arXiv · PDF · Open in the Atlas

Code that ran

7 of 9 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 5 have no contract verdict; 1 failure of our instrument; 2 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/2002.12212.json · badge: /api/ran/2002.12212.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
yinyunie/Total3DUnderstanding canonical (classifier label)
classifier basis: census
7 ran · 2 no recorded run
FunctionStatusWhere it lives
find_optim_module Ran
ran; our contract draft was wrong, not the code
yinyunie/Total3DUnderstanding/models/optimizers.py
code served (permissive licence) · get_code("7c5097f4707309ec")
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 torch
import torch.nn as nn

torch.manual_seed(0)

# Create a simple module with optim_spec
class ModuleWithOptim(nn.Module):
    def __init__(self):
        super().__init__()
        self.optim_spec = {'lr': 0.001, 'weight_decay': 1e-5}
    
    def forward(self, x):
        return x

# Create a simple module without optim_spec
class ModuleWithoutOptim(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)
    
    def forward(self, x):
        return self.linear(x)

# Create a nested module structure
class NestedModuleWithOptim(nn.Module):
    def __init__(self):
        super().__init__()
        self.sub_module = ModuleWithOptim()
    
    def forward(self, x):
        return self.sub_module(x)

# Build the test network with mixed optim specs
net = nn.Module()
net.optim_module_1 = ModuleWithOptim()
net.plain_module = ModuleWithoutOptim()
net.nested_module = NestedModuleWithOptim()

# Reconstruct as a proper container to ensure children() works
class TestNet(nn.Module):
    def __init__(self):
        super().__init__()
        self.optim_module_1 = ModuleWithOptim()
        self.plain_module = ModuleWithoutOptim()
        self.nested_module = NestedModuleWithOptim()
    
    def forward(self, x):
        return x

net = TestNet()

ARGS = {
    'net': net
}
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 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
has_optim_in_children Ran
ran, violated the contract we drafted
yinyunie/Total3DUnderstanding/models/optimizers.py
code served (permissive licence) · get_code("6456fb43944fedf5")
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 bool, ndim 0, dtype family float, shape () 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 SubnetWithOptim(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)
        self.optim_spec = {'lr': 0.001}

class SubnetWithoutOptim(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)

class NestedSubnetWithOptim(nn.Module):
    def __init__(self):
        super().__init__()
        self.child1 = SubnetWithoutOptim()
        self.child2 = SubnetWithOptim()

class TestSubnet(nn.Module):
    def __init__(self):
        super().__init__()
        self.layer1 = nn.Linear(4, 3)
        self.layer2 = nn.Linear(3, 2)
        self.child_with_optim = SubnetWithOptim()

subnet = TestSubnet()

ARGS = {
    'subnet': subnet
}
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 bool, ndim 0, dtype family float, shape () — shape () 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
load_device Ran
ran on a synthesized input
yinyunie/Total3DUnderstanding/net_utils/utils.py
code served (permissive licence) · get_code("b0cbe76658e8cbd9")
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 device. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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

class MockConfig:
    def __init__(self):
        self.config = {
            'device': {
                'use_gpu': False,
                'gpu_ids': [0, 1]
            }
        }
        self.logs = []
    
    def log_string(self, message):
        self.logs.append(message)

cfg = MockConfig()

ARGS = {
    'cfg': cfg
}
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 device — a device output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a device 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
load_scheduler Ran
ran on a synthesized input
yinyunie/Total3DUnderstanding/models/optimizers.py
code served (permissive licence) · get_code("6993951c91b8384b")
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 ReduceLROnPlateau. 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.optim as optim
import torch.nn as nn

torch.manual_seed(0)

# Create a minimal model for the optimizer
class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)
    
    def forward(self, x):
        return self.linear(x)

# Create model and optimizer
model = SimpleModel()
optimizer = optim.SGD(model.parameters(), lr=0.1)

# Create config dict with required scheduler parameters
config = {
    'scheduler': {
        'factor': 0.1,
        'patience': 10,
        'threshold': 1e-4
    }
}

ARGS = {
    'config': config,
    'optimizer': optimizer
}
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 ReduceLROnPlateau — a ReduceLROnPlateau output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ReduceLROnPlateau 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
num_from_bins Ran
ran on a synthesized input
yinyunie/Total3DUnderstanding/net_utils/libs.py
code served (permissive licence) · get_code("511b658275852213")
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 1, dtype family float, shape (2,) 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)

# Construct arguments for num_from_bins
# bins: b x 2 tensors - batch size 2, each element has 2 values (bin boundaries)
bins = torch.tensor([[1.0, 2.0], [3.0, 4.0]], dtype=torch.float32)

# cls: b long tensors - indices into the bins tensor (batch size 2)
cls = torch.tensor([0, 1], dtype=torch.long)

# reg: b tensors - regression offsets (batch size 2)
reg = torch.tensor([0.1, 0.2], dtype=torch.float32)

ARGS = {
    "bins": bins,
    "cls": cls,
    "reg": reg
}
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 Tensor, ndim 1, dtype family float, shape (2,) — shape (2,) 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
sample_points_on_edges Ran
ran on a synthesized input
yinyunie/Total3DUnderstanding/net_utils/misc.py
code served (permissive licence) · get_code("67a1fe9a74ab3c9e")
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, 3, 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)

# points: shape (n_batch, 3, n_points) - 3D coordinates for points
# edges: shape (n_batch, n_edges, 2) - edge indices (1-indexed)
n_batch = 2
n_points = 4
n_edges = 3

# Create points tensor with shape (batch, 3, n_points)
# 3 is for x, y, z coordinates
points = torch.randn(n_batch, 3, n_points)

# Create edges tensor with shape (batch, n_edges, 2)
# Each edge connects two points (1-indexed)
edges = torch.tensor([
    [[1, 2], [2, 3], [3, 4]],
    [[1, 3], [2, 4], [1, 4]]
], dtype=torch.long)

ARGS = {
    'points': points,
    'edges': edges,
    'quantity': 1,
    'mode': 'train'
}
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 Tensor, ndim 3, dtype family float, shape (2, 3, 3) — shape (2, 3, 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
to_dict_tensor Ran
ran on a synthesized input
yinyunie/Total3DUnderstanding/net_utils/libs.py
code served (permissive licence) · get_code("ea8d8ed9d5ec6bb2")
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. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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 numpy as np

torch.manual_seed(0)

# Construct the arguments for to_dict_tensor
dicts = {
    'array_1': np.array([1.0, 2.0, 3.0, 4.0]),
    'array_2': np.array([[1.0, 2.0], [3.0, 4.0], [5.0, 6.0]]),
    'array_3': np.random.randn(2, 4).astype(np.float64),
}

if_cuda = False

ARGS = {
    'dicts': dicts,
    'if_cuda': if_cuda,
}
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 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
R_from_yaw_pitch_roll Not yet run
unverified (harvested, no recorded run)
yinyunie/Total3DUnderstanding/net_utils/libs.py
code served (permissive licence) · get_code("584839f99e9b512b")
How it ran

no invocation recorded.

load_template Not yet run
unverified (harvested, no recorded run)
yinyunie/Total3DUnderstanding/net_utils/misc.py
code served (permissive licence) · get_code("23eae901d43d45b9")
How it ran

no invocation recorded.

Also present in other papers' code

Of 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 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 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
find_optim_module 1 other paper
1 later
2309.11133 (2023-09)
Shape Anchor Guided Holistic Indoor Scene Understanding
has_optim_in_children 1 other paper
1 later
2309.11133 (2023-09)
Shape Anchor Guided Holistic Indoor Scene Understanding

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

Semantic reconstruction of indoor scenes refers to both scene understanding and object reconstruction. Existing works either address one part of this problem or focus on independent objects. In this paper, we bridge the gap between understanding and reconstruction, and propose an end-to-end solution to jointly reconstruct room layout, object bounding boxes and meshes from a single image. Instead of separately resolving scene understanding and object reconstruction, our method builds upon a holistic scene context and proposes a coarse-to-fine hierarchy with three components: 1. room layout with camera pose; 2. 3D object bounding boxes; 3. object meshes. We argue that understanding the context of each component can assist the task of parsing the others, which enables joint understanding and reconstruction. The experiments on the SUN RGB-D and Pix3D datasets demonstrate that our method consistently outperforms existing methods in indoor layout estimation, 3D object detection and mesh reconstruction.

For agents

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

get_harvested_code_for_paper("2002.12212")
get_code_for_paper("2002.12212")
have("2002.12212")

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

curl https://syntology.ai/api/ran/2002.12212.json

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

[![Syntology run record](https://syntology.ai/api/ran/2002.12212.svg)](https://syntology.ai/paper/2002.12212)

Connect an agent — have() is free.