SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1711.08488 · 2017

Frustum PointNets for 3D Object Detection from RGB-D Data

arXiv · PDF · Open in the Atlas

Code that ran

2 of 4 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 0 have no contract verdict; 2 failures of our instrument; 2 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/1711.08488.json · badge: /api/ran/1711.08488.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
Veincore/f-pointnet reimplementation (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
alpemek/ais3d reimplementation (classifier label)
classifier basis: classifier_2025
0 ran · 2 no recorded run
FunctionStatusWhere it lives
get_lidar_in_image_fov Ran
ran; our contract draft was wrong, not the code
Veincore/f-pointnet/infer/prep_data_infer.py
code served (permissive licence) · get_code("47397a2377a470c7")
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) and returned ndarray, 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
import numpy as np

torch.manual_seed(0)

class MockCalib:
    """Mock calibration object that projects velodyne points to image coordinates"""
    def project_velo_to_image(self, pc_velo):
        """
        Project 3D velodyne points to 2D image coordinates.
        pc_velo: (N, 3) or (N, 4) array of points in velodyne frame
        Returns: (N, 2) array of 2D image coordinates
        """
        # Simple mock projection: just use first two coordinates scaled
        if isinstance(pc_velo, torch.Tensor):
            pc_velo = pc_velo.numpy()
        
        n_points = pc_velo.shape[0]
        pts_2d = np.zeros((n_points, 2), dtype=np.float32)
        
        # Mock projection: scale x and y coordinates to image space
        pts_2d[:, 0] = pc_velo[:, 0] * 100 + 50  # x coordinate
        pts_2d[:, 1] = pc_velo[:, 1] * 100 + 50  # y coordinate
        
        return pts_2d

# Create mock calibration object
calib = MockCalib()

# Create point cloud in velodyne frame (N, 4) with x, y, z, intensity
pc_velo = np.array([
    [3.0, 0.5, 1.0, 1.0],   # Point in FOV, far enough
    [2.5, 0.3, 0.5, 1.0],   # Point in FOV, far enough
    [1.0, 0.2, 0.8, 1.0],   # Point too close (x < clip_distance)
    [5.0, 2.0, 1.5, 1.0],   # Point outside FOV
], dtype=np.float32)

# Image dimensions
xmin = 0
ymin = 0
xmax = 400
ymax = 400
clip_distance = 2.0

ARGS = {
    'pc_velo': pc_velo,
    'calib': calib,
    'xmin': xmin,
    'ymin': ymin,
    'xmax': xmax,
    'ymax': ymax,
    'return_more': False,
    'clip_distance': clip_distance,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy, torch — 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 (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
transform_bbox_inverse Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
Veincore/f-pointnet/infer/prep_data_infer.py
code served (permissive licence) · get_code("6a56057817a2ab9b")
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) and returned ndarray, ndim 2, dtype family int, 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 numpy as np

# Construct arguments for transform_bbox_inverse
# The function expects:
# - bbox_lists: a numpy array with shape (N, 4) containing bounding boxes
# - img_ori_shape: tuple of (width, height, channels) for original image
# - img_shape: tuple of (width, height, channels) for transformed image

# Create a small bounding box array with 2 boxes, 4 coordinates each
bbox_lists = np.array([
    [10.0, 20.0, 30.0, 40.0],
    [50.0, 60.0, 70.0, 80.0]
], dtype=float)

# Original image shape (width, height, channels)
img_ori_shape = (640, 480, 3)

# Transformed image shape (width, height, channels) - smaller than original
img_shape = (320, 240, 3)

ARGS = {
    "bbox_lists": bbox_lists,
    "img_ori_shape": img_ori_shape,
    "img_shape": img_shape
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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 int, 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
computeBox3D Not yet run
unverified (harvested, no recorded run)
alpemek/ais3d/computeBox3D.py
pointer only (licence: NONE) · get_code("f95b1b0c4fc91241")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, alpemek/ais3d 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. No invocation recorded.

projectToImage Not yet run
unverified (harvested, no recorded run)
alpemek/ais3d/computeBox3D.py
pointer only (licence: NONE) · get_code("0b905dfd500cd40d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, alpemek/ais3d 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. No invocation recorded.

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 1 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 1 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.

FunctionAlso present inEarliest-datedOthers named
get_lidar_in_image_fov 3 other papers
3 later
1811.07782 (2018-11)
Modeling Local Geometric Structure of 3D Point Clouds using Geo-CNN
1912.12147 (2019-12)
Cooperative Perception for 3D Object Detection in Driving Scenarios using Infrastructure Sensors
2203.09780 (2022-03)
Sparse Fuse Dense: Towards High Quality 3D Detection with Depth Completion

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

More are linked than shown here.

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

Abstract

In this work, we study 3D object detection from RGB-D data in both indoor and outdoor scenes. While previous methods focus on images or 3D voxels, often obscuring natural 3D patterns and invariances of 3D data, we directly operate on raw point clouds by popping up RGB-D scans. However, a key challenge of this approach is how to efficiently localize objects in point clouds of large-scale scenes (region proposal). Instead of solely relying on 3D proposals, our method leverages both mature 2D object detectors and advanced 3D deep learning for object localization, achieving efficiency as well as high recall for even small objects. Benefited from learning directly in raw point clouds, our method is also able to precisely estimate 3D bounding boxes even under strong occlusion or with very sparse points. Evaluated on KITTI and SUN RGB-D 3D detection benchmarks, our method outperforms the state of the art by remarkable margins while having real-time capability.

For agents

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

get_harvested_code_for_paper("1711.08488")
get_code_for_paper("1711.08488")
have("1711.08488")

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

curl https://syntology.ai/api/ran/1711.08488.json

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

[![Syntology run record](https://syntology.ai/api/ran/1711.08488.svg)](https://syntology.ai/paper/1711.08488)

Connect an agent — have() is free.