SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2103.12605 · CVPR · 2021

MonoRUn: Monocular 3D Object Detection by Reconstruction and Uncertainty Propagation

Hansheng Chen, Wei Tian, Zhong Gao, Lu Xiong, Yuyao Huang

arXiv · PDF · Open in the Atlas

Code that ran

2 of 3 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 2 have no contract verdict; 0 failures of our instrument; 1 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/2103.12605.json · badge: /api/ran/2103.12605.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
tjiiv-cprg/MonoRUn canonical (classifier label)
classifier basis: census
2 ran · 1 no recorded run
FunctionStatusWhere it lives
compute_box_3d Ran
ran on a synthesized input
tjiiv-cprg/MonoRUn/monorun/core/visualizer/image_bev_vis.py
code served (permissive licence) · get_code("1604d2ea3c110258")
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

# Analyze the function:
# - Takes a parameter 'label'
# - If label is a list: accesses indices [14, 10, 9, 8, 11, 12, 13]
# - If label is not a list (e.g., numpy array): accesses indices [6, 0, 2, 1, 3:6]
# - Returns tuple of (corners array, edge_idx array)

# Create a label as a numpy array (non-list case)
# Need indices: 0, 1, 2, 3, 4, 5, 6
# Index mapping:
# [0] = bl (length)
# [1] = bh (height)
# [2] = bw (width)
# [3:6] = t (translation x, y, z)
# [6] = ry (rotation around y-axis)

label_array = np.array([
    0.5,      # [0] bl (length)
    1.5,      # [1] bh (height)
    0.8,      # [2] bw (width)
    1.0,      # [3] tx
    2.0,      # [4] ty
    3.0,      # [5] tz
    0.785     # [6] ry (rotation, ~45 degrees)
])

ARGS = {
    "label": label_array
}
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 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
compute_box_bev Ran
ran on a synthesized input
tjiiv-cprg/MonoRUn/monorun/core/visualizer/image_bev_vis.py
code served (permissive licence) · get_code("e29ed068395662e0")
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, 7) 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: label as a list
label_list = [
    1.5,      # [0] - not used in list case
    2.0,      # [1] - not used in list case
    3.5,      # [2] - not used in list case
    0.1,      # [3] - not used in list case
    0.2,      # [4] - not used in list case
    0.3,      # [5] - not used in list case
    0.4,      # [6] - not used in list case
    0.5,      # [7] - not used in list case
    0.6,      # [8] - not used in list case
    2.5,      # [9] - bw (width)
    1.8,      # [10] - bl (length)
    5.0,      # [11] - t[0] (x position)
    10.0,     # [12] - t[1] (y position)
    0.5,      # [13] - t[2] (z position)
    0.785,    # [14] - ry (rotation angle in radians)
]

ARGS = {
    "label": label_list
}
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, 7) — shape (3, 7) 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
show_bev Not yet run
unverified (harvested, no recorded run)
tjiiv-cprg/MonoRUn/monorun/core/visualizer/image_bev_vis.py
code served (permissive licence) · get_code("91aa6849c937defe")
How it ran

no invocation recorded.

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 3 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.

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

Object localization in 3D space is a challenging aspect in monocular 3D object detection. Recent advances in 6DoF pose estimation have shown that predicting dense 2D-3D correspondence maps between image and object 3D model and then estimating object pose via Perspective-n-Point (PnP) algorithm can achieve remarkable localization accuracy. Yet these methods rely on training with ground truth of object geometry, which is difficult to acquire in real outdoor scenes. To address this issue, we propose MonoRUn, a novel detection framework that learns dense correspondences and geometry in a self-supervised manner, with simple 3D bounding box annotations. To regress the pixel-related 3D object coordinates, we employ a regional reconstruction network with uncertainty awareness. For self-supervised training, the predicted 3D coordinates are projected back to the image plane. A Robust KL loss is proposed to minimize the uncertainty-weighted reprojection error. During testing phase, we exploit the network uncertainty by propagating it through all downstream modules. More specifically, the uncertainty-driven PnP algorithm is leveraged to estimate object pose and its covariance. Extensive experiments demonstrate that our proposed approach outperforms current state-of-the-art methods on KITTI benchmark.

For agents

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

get_harvested_code_for_paper("2103.12605")
get_code_for_paper("2103.12605")
have("2103.12605")

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

curl https://syntology.ai/api/ran/2103.12605.json

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

[![Syntology run record](https://syntology.ai/api/ran/2103.12605.svg)](https://syntology.ai/paper/2103.12605)

Connect an agent — have() is free.