SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2002.10111 · 2020

SMOKE: Single-Stage Monocular 3D Object Detection via Keypoint Estimation

arXiv · PDF · Open in the Atlas

Code that ran

8 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, 0 violated it and 6 have no contract verdict; 2 failures of our instrument; 1 no recorded run), measured 2026-11-21; 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/2002.10111.json · badge: /api/ran/2002.10111.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
lzccccc/SMOKE canonical (classifier label)
classifier basis: census
8 ran · 1 no recorded run
FunctionStatusWhere it lives
affine_transform Ran
ran on a synthesized input
lzccccc/SMOKE/smoke/modeling/heatmap_coder.py
code served (permissive licence) · get_code("f3636481f50cd9a9")
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 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 numpy as np

# Construct arguments for affine_transform function
# The function takes a 2D point and applies an affine transformation using a matrix

# Create a simple 2D point
point = np.array([1.0, 2.0])

# Create a 3x3 affine transformation matrix
# This matrix will transform homogeneous 2D coordinates [x, y, 1]
matrix = np.array([
    [2.0, 0.5, 1.0],  # Row for new x coordinate
    [0.3, 1.5, 0.5],  # Row for new y coordinate
    [0.0, 0.0, 1.0]   # Homogeneous row (typically [0, 0, 1])
])

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 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
cat Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
lzccccc/SMOKE/smoke/modeling/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.

encode_label Ran
ran on a synthesized input
lzccccc/SMOKE/smoke/modeling/smoke_coder.py
code served (permissive licence) · get_code("d564528b55724ff2")
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

ARGS = {
    "K": np.array([[718.856, 0, 607.1928],
                   [0, 718.856, 185.2157],
                   [0, 0, 1]], dtype=np.float32),
    "ry": np.float32(0.5),
    "dims": np.array([3.88, 1.63, 1.53], dtype=np.float32),
    "locs": np.array([10.0, 1.5, 5.0], dtype=np.float32)
}
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
get_3rd_point Ran
ran on a synthesized input
lzccccc/SMOKE/smoke/modeling/heatmap_coder.py
code served (permissive licence) · get_code("b7a39d17dbb951b8")
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 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 numpy as np

# Analyze the function: get_3rd_point takes two points (point_a and point_b)
# Both are expected to be numpy arrays that support:
# - subtraction (d = point_a - point_b)
# - indexing (d[1], d[0])
# - array construction from a list
# The function computes a third point based on geometric operations

# Create two distinct 2D points as numpy arrays
point_a = np.array([3.0, 4.0])
point_b = np.array([1.0, 2.0])

ARGS = {
    "point_a": point_a,
    "point_b": point_b,
}
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 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
get_transfrom_matrix Ran
ran on a synthesized input
lzccccc/SMOKE/smoke/modeling/heatmap_coder.py
code served (permissive licence) · get_code("a46a4b1c0a5a4ac2")
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
from skimage import transform as trans

def get_3rd_point(point_a, point_b):
    d = point_a - point_b
    point_c = point_b + np.array([-d[1], d[0]])
    return point_c

def get_transfrom_matrix(center_scale, output_size):
    center, scale = (center_scale[0], center_scale[1])
    src_w = scale[0]
    dst_w = output_size[0]
    dst_h = output_size[1]
    src_dir = np.array([0, src_w * -0.5])
    dst_dir = np.array([0, dst_w * -0.5])
    src = np.zeros((3, 2), dtype=np.float32)
    dst = np.zeros((3, 2), dtype=np.float32)
    src[0, :] = center
    src[1, :] = center + src_dir
    dst[0, :] = np.array([dst_w * 0.5, dst_h * 0.5])
    dst[1, :] = np.array([dst_w * 0.5, dst_h * 0.5]) + dst_dir
    src[2, :] = get_3rd_point(src[0, :], src[1, :])
    dst[2, :] = get_3rd_point(dst[0, :], dst[1, :])
    get_matrix = trans.estimate_transform('affine', src, dst)
    matrix = get_matrix.params
    return matrix.astype(np.float32)

# Construct valid arguments
center = np.array([256.0, 256.0], dtype=np.float32)
scale = np.array([512.0, 512.0], dtype=np.float32)
center_scale = (center, scale)

output_size = (256, 256)

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
nms_hm Ran
ran on a synthesized input
lzccccc/SMOKE/smoke/layers/utils.py
code served (permissive licence) · get_code("0389a686f602c24d")
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, 1, 4, 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 torch.nn as nn
import torch.nn.functional as F

torch.manual_seed(0)

# Create a small heat map tensor
# Shape: (batch=2, channels=1, height=4, width=3)
heat_map = torch.rand(2, 1, 4, 3)

# Define the kernel size parameter
kernel = 3

# Construct ARGS dict with all parameters
ARGS = {
    "heat_map": heat_map,
    "kernel": kernel
}
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, 1, 4, 3) — shape (2, 1, 4, 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
sigmoid_hm Ran
ran on a synthesized input
lzccccc/SMOKE/smoke/layers/utils.py
code served (permissive licence) · get_code("a0aad7a92e4801dc")
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 2, dtype family float, shape (2, 4) 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

torch.manual_seed(0)

# Create a small tensor to serve as hm_features
# The function calls .sigmoid_() on it, which modifies in-place
# Then calls .clamp() on the result
# So we need a tensor with floating point values
hm_features = torch.randn(2, 4)

ARGS = {
    "hm_features": hm_features
}
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 2, dtype family float, shape (2, 4) — shape (2, 4) 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
lzccccc/SMOKE/smoke/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.

select_topk Not yet run
unverified (harvested, no recorded run)
lzccccc/SMOKE/smoke/layers/utils.py
code served (permissive licence) · get_code("22aa597947eab5d5")
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 (1 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
cat 18 other papers
2 dated earlier, 16 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
2003.05176 (2020-03)
Equalization Loss for Long-Tailed Object Recognition
and 15 more not named here
strip_prefix_if_present 14 other papers
14 later
2104.02323 (2021-04)
Objects are Different: Flexible Monocular 3D Object Detection
2105.05013 (2021-05)
Semantic Distribution-aware Contrastive Adaptation for Semantic Segmentation
aaai_20163 (2022 (year only))
Negative Sample Matters: A Renaissance of Metric Learning for Temporal Grounding
and 11 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 2026-11-21.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Estimating 3D orientation and translation of objects is essential for infrastructure-less autonomous navigation and driving. In case of monocular vision, successful methods have been mainly based on two ingredients: (i) a network generating 2D region proposals, (ii) a R-CNN structure predicting 3D object pose by utilizing the acquired regions of interest. We argue that the 2D detection network is redundant and introduces non-negligible noise for 3D detection. Hence, we propose a novel 3D object detection method, named SMOKE, in this paper that predicts a 3D bounding box for each detected object by combining a single keypoint estimate with regressed 3D variables. As a second contribution, we propose a multi-step disentangling approach for constructing the 3D bounding box, which significantly improves both training convergence and detection accuracy. In contrast to previous 3D detection techniques, our method does not require complicated pre/post-processing, extra data, and a refinement stage. Despite of its structural simplicity, our proposed SMOKE network outperforms all existing monocular 3D detection methods on the KITTI dataset, giving the best state-of-the-art result on both 3D object detection and Bird's eye view evaluation. The code will be made publicly available.

For agents

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

get_harvested_code_for_paper("2002.10111")
get_code_for_paper("2002.10111")
have("2002.10111")

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

curl https://syntology.ai/api/ran/2002.10111.json

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

[![Syntology run record](https://syntology.ai/api/ran/2002.10111.svg)](https://syntology.ai/paper/2002.10111)

Connect an agent — have() is free.