SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2007.10323 · 2020

Pillar-based Object Detection for Autonomous Driving

arXiv · PDF · Open in the Atlas

Code that ran

10 of 10 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 10 have no contract verdict; 0 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/2007.10323.json · badge: /api/ran/2007.10323.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
WangYueFt/pillar-od canonical (classifier label)
classifier basis: census
10 ran · 0 no recorded run
FunctionStatusWhere it lives
add_points_bboxes Ran
ran on a synthesized input
WangYueFt/pillar-od/waymo_loader.py
code served (permissive licence) · get_code("b200fdbce22c84fb")
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 tensorflow.compat.v2 as tf
import numpy as np

tf.enable_v2_behavior()

# Create small sample tensors for the function
num_points = 2
num_bboxes = 3
point_dim = 3
bbox_dim = 7

# points_xyz: [num_points, 3] - 3D coordinates of points
points_xyz = tf.constant([
    [1.0, 2.0, 3.0],
    [4.0, 5.0, 6.0]
], dtype=tf.float32)

# bboxes: [num_bboxes, 7] - bbox parameters (x, y, z, dx, dy, dz, theta)
bboxes = tf.constant([
    [0.0, 0.0, 0.0, 2.0, 2.0, 2.0, 0.0],
    [5.0, 5.0, 5.0, 3.0, 3.0, 3.0, 0.785],
    [10.0, 10.0, 10.0, 4.0, 4.0, 4.0, 1.57]
], dtype=tf.float32)

# bboxes_label: [num_bboxes] - class labels for each bbox
bboxes_label = tf.constant([1, 2, 3], dtype=tf.int32)

# bboxes_mask: [num_bboxes] - binary mask indicating valid bboxes
bboxes_mask = tf.constant([1.0, 1.0, 0.0], dtype=tf.float32)

ARGS = {
    "points_xyz": points_xyz,
    "bboxes": bboxes,
    "bboxes_label": bboxes_label,
    "bboxes_mask": bboxes_mask,
    "is_2d": False
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — 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
assign_bboxes Ran
ran on a synthesized input
WangYueFt/pillar-od/waymo_loader.py
code served (permissive licence) · get_code("425c4b336ed9b1ca")
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 tensorflow.compat.v2 as tf
import numpy as np

tf.enable_v2_behavior()

# Create small tensors for bboxes
# Each bbox has 7 values: [x, y, z, length, width, height, rotation]
bboxes = tf.constant([
    [0.0, 0.0, 0.0, 2.0, 2.0, 1.5, 0.1],
    [5.0, 5.0, 0.0, 3.0, 2.5, 1.8, 0.2],
], dtype=tf.float32)

# Mask indicating which bboxes are valid (1 = valid, 0 = invalid)
bboxes_mask = tf.constant([1, 1], dtype=tf.float32)

# Label for each bbox (e.g., class index)
bboxes_label = tf.constant([1, 2], dtype=tf.int32)

ARGS = {
    'pillar_map_size': (16, 16),
    'pillar_map_range': (10.0, 10.0),
    'bboxes': bboxes,
    'bboxes_mask': bboxes_mask,
    'bboxes_label': bboxes_label,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — 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
conv1d Ran
ran on a synthesized input
WangYueFt/pillar-od/network.py
code served (permissive licence) · get_code("ae08fa5021cce887")
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 Conv1D. 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 tensorflow.compat.v2 as tf

# Enable eager execution for TensorFlow 2
tf.enable_v2_behavior()

# Define the ARGS dictionary with all parameters for conv1d
ARGS = {
    'odims': 64,
    'kernel_size': 3,
    'stride': 1,
    'use_bias': False
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Conv1D — a Conv1D output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Conv1D 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
conv2d Ran
ran on a synthesized input
WangYueFt/pillar-od/network.py
code served (permissive licence) · get_code("af683bf5fadd331e")
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 Conv2D. 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 tensorflow.compat.v2 as tf

ARGS = {
    'odims': 64,
    'kernel_size': (3, 3),
    'stride': 1,
    'use_bias': True,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Conv2D — a Conv2D output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Conv2D 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
dense Ran
ran on a synthesized input
WangYueFt/pillar-od/network.py
code served (permissive licence) · get_code("b1471476d6fe5102")
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 Dense. 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 tensorflow.compat.v2 as tf

# The function `dense` takes two parameters: odims and use_bias
# odims: integer specifying output dimensions (default 64)
# use_bias: boolean specifying whether to use bias (default False)

# Construct arguments for the dense function
ARGS = {
    'odims': 64,
    'use_bias': False
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Dense — a Dense output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Dense 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
get_shape Ran
ran on a synthesized input
WangYueFt/pillar-od/tf_util.py
code served (permissive licence) · get_code("73717934286fbf5a")
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 list, ndim 1, dtype family int; 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 tensorflow.compat.v2 as tf

tf.enable_v2_behavior()

# Create a simple tensor with known static shape
tensor_with_static_shape = tf.constant([[1.0, 2.0, 3.0, 4.0],
                                        [5.0, 6.0, 7.0, 8.0]])

ARGS = {
    "tensor": tensor_with_static_shape,
    "ndims": None
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, dtype family int — a list output has no array shape of its own; none is stated
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
pad_or_trim_to Ran
ran on a synthesized input
WangYueFt/pillar-od/tf_util.py
code served (permissive licence) · get_code("f42ac0146c825dcc")
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 EagerTensor, ndim 2, dtype family float, shape (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 tensorflow.compat.v2 as tf

# Create a small input tensor
x = tf.constant([[1.0, 2.0, 3.0, 4.0],
                 [5.0, 6.0, 7.0, 8.0]])

# Define target shape (2D: 3 rows, 5 columns)
shape = tf.constant([3, 5], dtype=tf.int32)

# Define pad value
pad_val = 0

ARGS = {
    "x": x,
    "shape": shape,
    "pad_val": pad_val
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type EagerTensor, ndim 2, dtype family float, shape (3, 5) — shape (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
raval_index Ran
ran on a synthesized input
WangYueFt/pillar-od/tf_util.py
code served (permissive licence) · get_code("cf255a3dd2896681")
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 EagerTensor, ndim 1, dtype family int, 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 tensorflow.compat.v2 as tf
import numpy as np

# Enable eager execution for TensorFlow v2
tf.enable_v2_behavior()

# Create small test tensors
# coords: shape (batch_size, num_dimensions) - coordinates to convert to raveled indices
# dims: shape (num_dimensions,) - dimensions of the array being raveled
batch_size = 2
num_dims = 4

# coords should be integer coordinates with values within the bounds of dims
coords = tf.constant([
    [0, 1, 2, 3],
    [1, 0, 1, 2]
], dtype=tf.int32)

# dims defines the shape of the array being raveled
dims = tf.constant([2, 3, 4, 5], dtype=tf.int32)

ARGS = {
    "coords": coords,
    "dims": dims
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type EagerTensor, ndim 1, dtype family int, 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
sigmoid_cross_entropy_focal_loss Ran
ran on a synthesized input
WangYueFt/pillar-od/loss.py
code served (permissive licence) · get_code("eddf699a8d1e9e30")
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 EagerTensor, 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 tensorflow.compat.v2 as tf
import numpy as np

tf.enable_v2_behavior()

# Create small test tensors
batch_size = 2
num_classes = 4

logits = tf.constant(np.random.randn(batch_size, num_classes).astype(np.float32))
labels = tf.constant(np.random.randint(0, 2, size=(batch_size, num_classes)).astype(np.float32))

ARGS = {
    "logits": logits,
    "labels": labels,
    "alpha": 0.25,
    "gamma": 2.0,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type EagerTensor, 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
smooth_l1_loss Ran
ran on a synthesized input
WangYueFt/pillar-od/loss.py
code served (permissive licence) · get_code("cf26f601b7f98582")
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 EagerTensor, 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 tensorflow.compat.v2 as tf
import numpy as np

tf.enable_v2_behavior()

# Create small test tensors
predictions = tf.constant([[1.0, 2.0, 3.0, 4.0], [5.0, 6.0, 7.0, 8.0]], dtype=tf.float32)
labels = tf.constant([[1.1, 2.2, 2.9, 4.1], [5.2, 5.8, 7.1, 7.9]], dtype=tf.float32)
sigma = 3.0

ARGS = {
    "predictions": predictions,
    "labels": labels,
    "sigma": sigma
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type EagerTensor, 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

Also present in other papers' code

Of 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 10 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 10 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

We present a simple and flexible object detection framework optimized for autonomous driving. Building on the observation that point clouds in this application are extremely sparse, we propose a practical pillar-based approach to fix the imbalance issue caused by anchors. In particular, our algorithm incorporates a cylindrical projection into multi-view feature learning, predicts bounding box parameters per pillar rather than per point or per anchor, and includes an aligned pillar-to-point projection module to improve the final prediction. Our anchor-free approach avoids hyperparameter search associated with past methods, simplifying 3D object detection while significantly improving upon state-of-the-art.

For agents

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

get_harvested_code_for_paper("2007.10323")
get_code_for_paper("2007.10323")
have("2007.10323")

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

curl https://syntology.ai/api/ran/2007.10323.json

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

[![Syntology run record](https://syntology.ai/api/ran/2007.10323.svg)](https://syntology.ai/paper/2007.10323)

Connect an agent — have() is free.