SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1912.04799 · 2019

Learning Depth-Guided Convolutions for Monocular 3D Object Detection

arXiv · PDF · Open in the Atlas

Code that ran

9 of 16 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 1 has no contract verdict; 8 failures of our instrument; 7 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/1912.04799.json · badge: /api/ran/1912.04799.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
dingmyu/D4LCN canonical (classifier label)
classifier basis: census
9 ran · 7 no recorded run
FunctionStatusWhere it lives
absolute_import Ran
ran; our contract draft was wrong, not the code
dingmyu/D4LCN/lib/util.py
code served (permissive licence) · get_code("1f9619e12d3bd0b1")
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 module. 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 os
import sys
import tempfile
import importlib.util

# Create a temporary Python module to import
temp_dir = tempfile.mkdtemp()
temp_module_path = os.path.join(temp_dir, "test_module.py")

# Write a simple Python module to the temporary file
with open(temp_module_path, "w") as f:
    f.write("""
def hello_world():
    return "Hello, World!"

class TestClass:
    def __init__(self):
        self.value = 42
""")

# Define ARGS with the absolute path to the temporary module
ARGS = {
    "file_path": temp_module_path
}
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 module — a module output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a module 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
dingmyu/D4LCN/models/resnet.py
pointer only (licence: MIT); the stored copy get_code serves, from lixiaotong97/DSU, is pointer only (licence: NONE) · get_code("fac5364e2f53c6db")
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 lixiaotong97/DSU, 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.

dynamic_local_filtering Ran
ran on a synthesized input
dingmyu/D4LCN/models/resnet_dilate.py
code served (permissive licence) · get_code("9a981aab334c245b")
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, 4, 3, 5) 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)

# Create small test tensors
# x: input tensor with shape (batch, channels, height, width)
x = torch.randn(2, 4, 3, 5)

# depth: depth map with same spatial dimensions as x
depth = torch.randn(2, 4, 3, 5)

# dilated: dilation parameter
dilated = 1

ARGS = {
    'x': x,
    'depth': depth,
    'dilated': dilated
}
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, 4, 3, 5) — shape (2, 4, 3, 5) 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
init_config Ran
ran; our contract draft was wrong, not the code
dingmyu/D4LCN/lib/core.py
code served (permissive licence) · get_code("241163a78260b639")
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. 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 os
import sys
import tempfile
import importlib.util
from pathlib import Path

# Create a temporary config module
temp_dir = tempfile.mkdtemp()
config_dir = os.path.join(temp_dir, 'config')
os.makedirs(config_dir, exist_ok=True)

# Create __init__.py for config package
init_file = os.path.join(config_dir, '__init__.py')
with open(init_file, 'w') as f:
    f.write('')

# Create a sample configuration file
test_config_file = os.path.join(config_dir, 'test_conf.py')
with open(test_config_file, 'w') as f:
    f.write('''
def Config():
    return {
        'learning_rate': 0.001,
        'batch_size': 32,
        'epochs': 10,
        'model_type': 'resnet',
        'hidden_dim': 128,
    }
''')

# Add temp_dir to sys.path so importlib can find the config package
sys.path.insert(0, temp_dir)

ARGS = {
    'conf_name': 'test_conf'
}
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 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
init_log_file Ran
ran; our contract draft was wrong, not the code
dingmyu/D4LCN/lib/util.py
code served (permissive licence) · get_code("992842247d4e98e5")
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 str. 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 os
import sys
import logging
import datetime
import tempfile

# Create a temporary directory for the log file
temp_dir = tempfile.mkdtemp()

ARGS = {
    'folder_path': temp_dir,
    'suffix': 'test_run',
    'log_level': logging.INFO
}
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 str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
pretty_print Ran
ran; our contract draft was wrong, not the code
dingmyu/D4LCN/lib/util.py
code served (permissive licence) · get_code("aacaef36624e2635")
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 str. 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
import pprint

# Set random seed for reproducibility
np.random.seed(0)

# Create test data for the function
test_dict = {
    'learning_rate': 0.001,
    'batch_size': 32,
    'epochs': 100,
    'model_name': 'ResNet50',
    'metrics': [0.95, 0.87, 0.92, 0.88],
    'weights': np.random.rand(4, 3),
    'config': {'optimizer': 'adam', 'loss': 'crossentropy'},
    'very_long_string_value': 'This is a very long string that will exceed the default value width and should be formatted with pprint',
}

ARGS = {
    'name': 'test_config',
    'input': test_dict,
    'val_width': 40,
    'key_width': 0,
}
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 str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
py_cpu_nms Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
dingmyu/D4LCN/lib/nms/py_cpu_nms.py
pointer only (licence: MIT); the stored copy get_code serves, from Anymake/DRN_CVPR2020, is pointer only (licence: GPL-2.0) · get_code("5502a789c2da0e5e")
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 Anymake/DRN_CVPR2020, and GPL-2.0, as GitHub detects it on that repository, is not in the permissive set Syntology serves inline. 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.

resnet18 Ran
ran; our contract draft was wrong, not the code
dingmyu/D4LCN/models/resnet.py
code served (permissive licence) · get_code("e72da04e104d0cd4")
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 ResNet. 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 = {
    'pretrained': False,
}
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 ResNet — a ResNet output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ResNet 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
resnet34 Ran
ran; our contract draft was wrong, not the code
dingmyu/D4LCN/models/resnet.py
code served (permissive licence) · get_code("aa939462813f803e")
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 ResNet. 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)

ARGS = {
    'pretrained': False,
}
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 ResNet — a ResNet output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ResNet 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
anchor_center Not yet run
unverified (harvested, no recorded run)
dingmyu/D4LCN/lib/rpn_util.py
code served (permissive licence) · get_code("86a6965b9bf27579")
How it ran

no invocation recorded.

cluster_anchors Not yet run
unverified (harvested, no recorded run)
dingmyu/D4LCN/lib/rpn_util.py
code served (permissive licence) · get_code("1469325b29d17885")
How it ran

no invocation recorded.

compute_targets Not yet run
unverified (harvested, no recorded run)
dingmyu/D4LCN/lib/rpn_util.py
code served (permissive licence) · get_code("9e27707b6ba89592")
How it ran

no invocation recorded.

intersect Not yet run
unverified (harvested, no recorded run)
dingmyu/D4LCN/lib/core.py
code served (permissive licence) · get_code("e214e5ed10c86a42")
How it ran

no invocation recorded.

read_kitti_cal Not yet run
unverified (harvested, no recorded run)
dingmyu/D4LCN/lib/imdb_util.py
code served (permissive licence) · get_code("94692e33979fd4e6")
How it ran

no invocation recorded.

read_kitti_label Not yet run
unverified (harvested, no recorded run)
dingmyu/D4LCN/lib/imdb_util.py
code served (permissive licence) · get_code("9bba40886e60c915")
How it ran

no invocation recorded.

read_kitti_poses Not yet run
unverified (harvested, no recorded run)
dingmyu/D4LCN/lib/imdb_util.py
code served (permissive licence) · get_code("09bdf9f5b1f17bb7")
How it ran

no invocation recorded.

Also present in other papers' code

Of 16 samples lifted from this paper's linked repositories, 16 carry a function identity and 0 do not. Of the 16 distinct functions with an identity, 15 are also present in other papers whose code we hold (13 with at least one paper dated earlier, 1 the same month, 15 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
conv3x3 686 other papers
178 dated earlier, 3 the same month, 505 later · 31 only as an assembly brick
1406.2661 (2014-06)
Generative Adversarial Networks
1409.0575 (2014-09)
ImageNet Large Scale Visual Recognition Challenge
1412.6572 (2014-12)
Explaining and Harnessing Adversarial Examples
and 683 more not named here
py_cpu_nms 9 other papers
5 dated earlier, 4 later
1506.01497 (2015-06)
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
1812.00155 (2018-12)
Learning RoI Transformer for Detecting Oriented Objects in Aerial Images
1905.00641 (2019-05)
RetinaFace: Single-stage Dense Face Localisation in the Wild
and 6 more not named here
resnet18 3 other papers
1 dated earlier, 2 later
1904.09739 (2019-04)
Switchable Whitening for Deep Representation Learning
2103.16470 (2021-03)
Depth-conditioned Dynamic Message Propagation for Monocular 3D Object Detection
2403.06098 (2024-03)
A Million-scale Real Prompt-Gallery Dataset for Text-to-Video Diffusion Models
resnet34 3 other papers
1 dated earlier, 2 later
1904.09739 (2019-04)
Switchable Whitening for Deep Representation Learning
aaai_6622 (2020 (year only))
Learning Deep Relations to Promote Saliency Detection
2103.16470 (2021-03)
Depth-conditioned Dynamic Message Propagation for Monocular 3D Object Detection
absolute_import 2 other papers
1 dated earlier, 1 later
1907.06038 (2019-07)
M3D-RPN: Monocular 3D Region Proposal Network for Object Detection
2103.16470 (2021-03)
Depth-conditioned Dynamic Message Propagation for Monocular 3D Object Detection
anchor_center 2 other papers
1 dated earlier, 1 later
1907.06038 (2019-07)
M3D-RPN: Monocular 3D Region Proposal Network for Object Detection
2103.16470 (2021-03)
Depth-conditioned Dynamic Message Propagation for Monocular 3D Object Detection
cluster_anchors 2 other papers
1 dated earlier, 1 later
1907.06038 (2019-07)
M3D-RPN: Monocular 3D Region Proposal Network for Object Detection
2103.16470 (2021-03)
Depth-conditioned Dynamic Message Propagation for Monocular 3D Object Detection
init_config 2 other papers
1 dated earlier, 1 later
1907.06038 (2019-07)
M3D-RPN: Monocular 3D Region Proposal Network for Object Detection
2103.16470 (2021-03)
Depth-conditioned Dynamic Message Propagation for Monocular 3D Object Detection
init_log_file 2 other papers
1 dated earlier, 1 later
1907.06038 (2019-07)
M3D-RPN: Monocular 3D Region Proposal Network for Object Detection
2103.16470 (2021-03)
Depth-conditioned Dynamic Message Propagation for Monocular 3D Object Detection
intersect 2 other papers
1 dated earlier, 1 later
1907.06038 (2019-07)
M3D-RPN: Monocular 3D Region Proposal Network for Object Detection
2103.16470 (2021-03)
Depth-conditioned Dynamic Message Propagation for Monocular 3D Object Detection
pretty_print 2 other papers
1 dated earlier, 1 later
1907.06038 (2019-07)
M3D-RPN: Monocular 3D Region Proposal Network for Object Detection
2103.16470 (2021-03)
Depth-conditioned Dynamic Message Propagation for Monocular 3D Object Detection
read_kitti_cal 2 other papers
1 dated earlier, 1 later
1907.06038 (2019-07)
M3D-RPN: Monocular 3D Region Proposal Network for Object Detection
2103.16470 (2021-03)
Depth-conditioned Dynamic Message Propagation for Monocular 3D Object Detection
read_kitti_poses 2 other papers
1 dated earlier, 1 later
1907.06038 (2019-07)
M3D-RPN: Monocular 3D Region Proposal Network for Object Detection
2103.16470 (2021-03)
Depth-conditioned Dynamic Message Propagation for Monocular 3D Object Detection
compute_targets 1 other paper
1 later
2103.16470 (2021-03)
Depth-conditioned Dynamic Message Propagation for Monocular 3D Object Detection
read_kitti_label 1 other paper
1 later
2103.16470 (2021-03)
Depth-conditioned Dynamic Message Propagation for Monocular 3D Object Detection

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

3D object detection from a single image without LiDAR is a challenging task due to the lack of accurate depth information. Conventional 2D convolutions are unsuitable for this task because they fail to capture local object and its scale information, which are vital for 3D object detection. To better represent 3D structure, prior arts typically transform depth maps estimated from 2D images into a pseudo-LiDAR representation, and then apply existing 3D point-cloud based object detectors. However, their results depend heavily on the accuracy of the estimated depth maps, resulting in suboptimal performance. In this work, instead of using pseudo-LiDAR representation, we improve the fundamental 2D fully convolutions by proposing a new local convolutional network (LCN), termed Depth-guided Dynamic-Depthwise-Dilated LCN (D$^4$LCN), where the filters and their receptive fields can be automatically learned from image-based depth maps, making different pixels of different images have different filters. D$^4$LCN overcomes the limitation of conventional 2D convolutions and narrows the gap between image representation and 3D point cloud representation. Extensive experiments show that D$^4$LCN outperforms existing works by large margins. For example, the relative improvement of D$^4$LCN against the state-of-the-art on KITTI is 9.1\% in the moderate setting. The code is available at https://github.com/dingmyu/D4LCN.

For agents

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

get_harvested_code_for_paper("1912.04799")
get_code_for_paper("1912.04799")
have("1912.04799")

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

curl https://syntology.ai/api/ran/1912.04799.json

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

[![Syntology run record](https://syntology.ai/api/ran/1912.04799.svg)](https://syntology.ai/paper/1912.04799)

Connect an agent — have() is free.