SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2404.03181 · CVPR · 2024

MonoCD: Monocular 3D Object Detection with Complementary Depths

Pei Yan, Yihua Tan, Shengzhou Xiong, Longfei Yan, Xuanyu Xiang

arXiv · PDF · Open in the Atlas

Code that ran

6 of 6 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 4 failures of our instrument; 0 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/2404.03181.json · badge: /api/ran/2404.03181.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
elvintanhust/monocd canonical (classifier label)
classifier basis not recorded on the link
5 ran · 0 no recorded run
elvintanhust/MonoCD community
Papers with Code archive
1 ran · 0 no recorded run
FunctionStatusWhere it lives
Depth_Refine_Loss Ran
ran on a synthesized input · constructed an object; no result was computed
elvintanhust/MonoCD/model/head/depth_losses.py
code served (permissive licence) · get_code("8d31e92618998e55")
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, Depth_Refine_Loss: 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)

# Parameters for Depth_Refine_Loss
bin_num = 4
bin_size = 0.5
device = 'cpu'

ARGS = {
    'bin_num': bin_num,
    'bin_size': bin_size,
    'device': device
}
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 Depth_Refine_Loss — 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 Depth_Refine_Loss 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
affine_transform Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
elvintanhust/monocd/model/heatmap_coder.py
code served (permissive licence) · get_code("65a16c264996059d")
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 2, dtype family float, shape (3, 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 numpy as np

# Create a small point array (multiple points)
point = np.array([[1.0, 2.0], [3.0, 4.0], [5.0, 6.0]])

# Create a 3x3 affine transformation matrix
# For 2D points extended to homogeneous coordinates (x, y, 1),
# we need a 3x3 matrix that will be transposed before matrix multiplication
matrix = np.array([
    [1.0, 0.0, 0.5],
    [0.0, 1.0, 0.3],
    [0.0, 0.0, 1.0]
])

ARGS = {
    "point": point,
    "matrix": matrix
}
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 2, dtype family float, shape (3, 2) — shape (3, 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
cat Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
elvintanhust/monocd/model/utils.py
pointer only (licence: MIT); the stored copy get_code serves, from xinyulyu/fgpl, is pointer only (licence: NONE) · get_code("6cbf46794989b731")
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 xinyulyu/fgpl, 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.

gaussian_radius Ran
ran, honoured the contract we drafted
elvintanhust/monocd/model/heatmap_coder.py
code served (permissive licence) · get_code("c044d44b5a7087e4")
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 float64, ndim 0, 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

# This function computes a gaussian radius given height and width
# It takes three numeric parameters: height, width, and min_overlap (with default 0.7)

ARGS = {
    "height": 32,
    "width": 64,
    "min_overlap": 0.7
}
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 float64, ndim 0, dtype family float — no output shape is stated: observe_signature.py recorded float ndim 0, which disagrees with the fixture run
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
get_transfrom_matrix Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
elvintanhust/monocd/model/heatmap_coder.py
code served (permissive licence) · get_code("194052ec40659a42")
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 2, dtype family float, shape (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 numpy as np

# Create small example inputs
center = np.array([100.0, 120.0], dtype=np.float32)
scale = np.array([50.0, 60.0], dtype=np.float32)
center_scale = [center, scale]

output_size = (64, 48)

ARGS = {
    "center_scale": center_scale,
    "output_size": output_size
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, skimage — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 2, dtype family float, shape (3, 3) — shape (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
strip_prefix_if_present Ran
ran; our contract draft was wrong, not the code
elvintanhust/monocd/utils/model_serialization.py
pointer only (licence: MIT); the stored copy get_code serves, from BIT-DA/SDCA, is pointer only (licence: NONE) · get_code("5a951495ac113177")
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 BIT-DA/SDCA, 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.

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 5 are also present in other papers whose code we hold (5 with at least one paper dated earlier, 0 the same month, 5 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
cat 18 other papers
17 dated earlier, 1 later · 3 only as an assembly brick
1804.08864 (2018-04)
Learning to See the Invisible: End-to-End Trainable Amodal Instance Segmentation
1908.07836 (2019-08)
PubLayNet: largest dataset ever for document layout analysis
2002.10111 (2020-02)
SMOKE: Single-Stage Monocular 3D Object Detection via Keypoint Estimation
and 15 more not named here
strip_prefix_if_present 14 other papers
12 dated earlier, 2 later
2002.10111 (2020-02)
SMOKE: Single-Stage Monocular 3D Object Detection via Keypoint Estimation
2104.02323 (2021-04)
Objects are Different: Flexible Monocular 3D Object Detection
2105.05013 (2021-05)
Semantic Distribution-aware Contrastive Adaptation for Semantic Segmentation
and 11 more not named here
affine_transform 5 other papers
4 dated earlier, 1 later
2104.02323 (2021-04)
Objects are Different: Flexible Monocular 3D Object Detection
2206.07372 (2022-06)
MonoGround: Detecting Monocular 3D Objects from the Ground
2207.04448 (2022-07)
Mix-Teaching: A Simple, Unified and Effective Semi-Supervised Learning Framework for Monocular 3D Object Detection
and 2 more not named here
gaussian_radius 5 other papers
4 dated earlier, 1 later
2104.02323 (2021-04)
Objects are Different: Flexible Monocular 3D Object Detection
2206.07372 (2022-06)
MonoGround: Detecting Monocular 3D Objects from the Ground
2207.04448 (2022-07)
Mix-Teaching: A Simple, Unified and Effective Semi-Supervised Learning Framework for Monocular 3D Object Detection
and 2 more not named here
get_transfrom_matrix 5 other papers
4 dated earlier, 1 later
2104.02323 (2021-04)
Objects are Different: Flexible Monocular 3D Object Detection
2206.07372 (2022-06)
MonoGround: Detecting Monocular 3D Objects from the Ground
2207.04448 (2022-07)
Mix-Teaching: A Simple, Unified and Effective Semi-Supervised Learning Framework for Monocular 3D Object Detection
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

Monocular 3D object detection has attracted widespread attention due to its potential to accurately obtain object 3D localization from a single image at a low cost. Depth estimation is an essential but challenging subtask of monocular 3D object detection due to the ill-posedness of 2D to 3D mapping. Many methods explore multiple local depth clues such as object heights and keypoints and then formulate the object depth estimation as an ensemble of multiple depth predictions to mitigate the insufficiency of singledepth information. However, the errors of existing multiple depths tend to have the same sign, which hinders them from neutralizing each other and limits the overall accuracy of combined depth. To alleviate this problem, we propose to increase the complementarity of depths with two novel designs. First, we add a new depth prediction branch named complementary depth that utilizes global and efficient depth clues from the entire image rather than the local clues to reduce the similarity of depth predictions. Second, we propose to fully exploit the geometric relations between multiple depth clues to achieve complementarity in form. Benefiting from these designs, our method achieves higher complementarity. Experiments on the KITTI benchmark demonstrate that our method achieves state-of-theart performance without introducing extra data. In addition, complementary depth can also be a lightweight and plug-and-play module to boost multiple existing monocular 3d object detectors. Code is available at https: //github.com/elvintanhust/MonoCD.

For agents

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

get_harvested_code_for_paper("2404.03181")
get_code_for_paper("2404.03181")
have("2404.03181")

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

curl https://syntology.ai/api/ran/2404.03181.json

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

[![Syntology run record](https://syntology.ai/api/ran/2404.03181.svg)](https://syntology.ai/paper/2404.03181)

Connect an agent — have() is free.