SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2007.08856 · 2020

EPNet: Enhancing Point Features with Image Semantics for 3D Object Detection

arXiv · PDF · Open in the Atlas

Code that ran

6 of 7 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; 4 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/2007.08856.json · badge: /api/ran/2007.08856.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
happinesslz/EPNet canonical (classifier label)
classifier basis: census
4 ran · 1 no recorded run
copy not recorded community
not in the paper's declared repositories
2 ran · 0 no recorded run
FunctionStatusWhere it lives
Feature_Gather Ran
ran; our contract draft was wrong, not the code
happinesslz/EPNet/lib/net/pointnet2_msg.py
code served (permissive licence) · get_code("f42100530caf4875")
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 3, dtype family float, shape (2, 4, 6) 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.functional as F

torch.manual_seed(0)

# Create a small feature map tensor (B, C, H, W)
# B=2 (batch size), C=4 (channels), H=3 (height), W=5 (width)
feature_map = torch.randn(2, 4, 3, 5)

# Create normalized xy coordinates (B, N, 2)
# B=2 (batch size), N=6 (number of points), 2 (x, y coordinates)
# Values normalized to [-1, 1] as required by grid_sample
xy = torch.rand(2, 6, 2) * 2 - 1  # Random values in [-1, 1]

ARGS = {
    "feature_map": feature_map,
    "xy": xy,
}
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 3, dtype family float, shape (2, 4, 6) — shape (2, 4, 6) 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
conv3x3 Ran
ran; our contract draft was wrong, not the code
happinesslz/EPNet/lib/net/pointnet2_msg.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.

create_logger Ran
ran; our contract draft was wrong, not the code
this paper's copy was not recorded; identical code first harvested from sshaoshuai/PointRCNN
pointer only · get_code("bae007593bd3dfd1")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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.

create_logger Ran
ran; our contract draft was wrong, not the code
this paper's copy was not recorded; identical code first harvested from sshaoshuai/PointRCNN
pointer only · get_code("c349bc6f8ed16220")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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.

get_calib_from_file Ran
ran on a synthesized input
happinesslz/EPNet/lib/utils/calibration.py
code served (permissive licence) · get_code("ebd8a3fc2a270133")
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 tempfile
import os

# Create a temporary calibration file with the expected format
temp_dir = tempfile.mkdtemp()
calib_file = os.path.join(temp_dir, "calib.txt")

with open(calib_file, 'w') as f:
    # Lines 0-1: dummy content
    f.write("P0: dummy\n")
    f.write("P1: dummy\n")
    # Line 2: P2 (3x4 = 12 values)
    f.write("P2: " + " ".join([str(i) for i in range(12)]) + "\n")
    # Line 3: P3 (3x4 = 12 values)
    f.write("P3: " + " ".join([str(i+12) for i in range(12)]) + "\n")
    # Line 4: R0 (3x3 = 9 values)
    f.write("R0: " + " ".join([str(i+24) for i in range(9)]) + "\n")
    # Line 5: Tr_velo_to_cam (3x4 = 12 values)
    f.write("Tr_velo_to_cam: " + " ".join([str(i+33) for i in range(12)]) + "\n")

ARGS = {
    "calib_file": calib_file
}
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 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
rotate_pc_along_y_torch Ran
ran on a synthesized input
happinesslz/EPNet/lib/utils/bbox_transform.py
code served (permissive licence) · get_code("16c5408b73888ff1")
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)

# pc: (N, 3 + C) - batch of N point clouds, each with 3 spatial coords + C extra channels
# For this function, only the first 3 columns matter (x, y, z), but we include extra channels
N = 2  # batch size
C = 1  # number of extra channels beyond x, y, z
pc = torch.randn(N, 3 + C)

# rot_angle: (N) - rotation angles for each point cloud in the batch
rot_angle = torch.randn(N)

ARGS = {
    "pc": pc,
    "rot_angle": rot_angle,
}
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
interpolate_img_by_xy Not yet run
unverified (harvested, no recorded run)
happinesslz/EPNet/lib/datasets/kitti_rcnn_dataset.py
code served (permissive licence) · get_code("675132277ed16adf")
How it ran

no invocation recorded.

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 7 are also present in other papers whose code we hold (5 with at least one paper dated earlier, 2 the same month, 6 later) and 0 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
238 dated earlier, 16 the same month, 431 later, 1 same year, order not determinable · 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
create_logger 8 other papers
4 dated earlier, 4 later
1712.00726 (2017-12)
Cascade R-CNN: Delving into High Quality Object Detection
1812.04244 (2018-12)
PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud
1902.06326 (2019-02)
PIXOR: Real-time 3D Object Detection from Point Clouds
and 5 more not named here
create_logger 5 other papers
3 dated earlier, 2 later
1712.00726 (2017-12)
Cascade R-CNN: Delving into High Quality Object Detection
1812.04244 (2018-12)
PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud
2005.08139 (2020-05)
Train in Germany, Test in The USA: Making 3D Object Detectors Generalize
and 2 more not named here
get_calib_from_file 5 other papers
2 dated earlier, 1 the same month, 2 later
1812.04244 (2018-12)
PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud
2006.11275 (2020-06)
Center-based 3D Object Detection and Tracking
2007.11901 (2020-07)
Weakly Supervised 3D Object Detection from Lidar Point Cloud
and 2 more not named here
Feature_Gather 1 other paper
1 later
2112.11088 (2021-12)
EPNet++: Cascade Bi-directional Fusion for Multi-Modal 3D Object Detection
interpolate_img_by_xy 1 other paper
1 later
2112.11088 (2021-12)
EPNet++: Cascade Bi-directional Fusion for Multi-Modal 3D Object Detection
rotate_pc_along_y_torch 1 other paper
1 dated earlier
1812.04244 (2018-12)
PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud

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

In this paper, we aim at addressing two critical issues in the 3D detection task, including the exploitation of multiple sensors~(namely LiDAR point cloud and camera image), as well as the inconsistency between the localization and classification confidence. To this end, we propose a novel fusion module to enhance the point features with semantic image features in a point-wise manner without any image annotations. Besides, a consistency enforcing loss is employed to explicitly encourage the consistency of both the localization and classification confidence. We design an end-to-end learnable framework named EPNet to integrate these two components. Extensive experiments on the KITTI and SUN-RGBD datasets demonstrate the superiority of EPNet over the state-of-the-art methods. Codes and models are available at: \url{https://github.com/happinesslz/EPNet}.

For agents

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

get_harvested_code_for_paper("2007.08856")
get_code_for_paper("2007.08856")
have("2007.08856")

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

curl https://syntology.ai/api/ran/2007.08856.json

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

[![Syntology run record](https://syntology.ai/api/ran/2007.08856.svg)](https://syntology.ai/paper/2007.08856)

Connect an agent — have() is free.