SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2006.14865 · 2020

RPM-Net: Recurrent Prediction of Motion and Parts from Point Cloud

arXiv · PDF · Open in the Atlas

Code that ran

8 of 14 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; 6 failures of our instrument; 6 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/2006.14865.json · badge: /api/ran/2006.14865.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
Salingo/RPM-Net canonical (classifier label)
classifier basis: census
8 ran · 6 no recorded run
FunctionStatusWhere it lives
ComputeAP Ran
ran on a synthesized input
Salingo/RPM-Net/code/cluster.py
code served (permissive licence) · get_code("6a0cf8f1b8644ae1")
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 float64, ndim 0, dtype family float; 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 numpy as np

# Create sample segmentation arrays
# group_seg: predicted group segmentation with labels 0, 1, 2
# gt_group_seg: ground truth group segmentation with labels 0, 1, 2

np.random.seed(0)

# Create a small segmentation mask (e.g., 10 pixels)
# group_seg has groups labeled 0, 1, 2
group_seg = np.array([0, 0, 1, 1, 2, 2, 0, 1, 2, 0])

# gt_group_seg has groups labeled 0, 1, 2 with some overlap
gt_group_seg = np.array([0, 0, 1, 1, 2, 2, 1, 0, 2, 0])

ARGS = {
    "group_seg": group_seg,
    "gt_group_seg": gt_group_seg,
}
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 float64, ndim 0, dtype family float — no output shape is stated: observe_signature.py recorded float ndim 0, which disagrees with the fixture run
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
GroupMergingSimDist Ran
ran on a synthesized input
Salingo/RPM-Net/code/cluster.py
code served (permissive licence) · get_code("6c24525e803030b9")
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

# Construct valid arguments for GroupMergingSimDist

# Create point cloud positions: num_points x 3 (x, y, z coordinates)
num_points = 150
pcpos = np.random.rand(num_points, 3).astype(np.float32) * 100

# Create similarity matrix: num_points x num_points
# This should have values that can be thresholded at 80
simmat_raw = np.random.randint(0, 150, size=(num_points, num_points)).astype(np.float32)

# Create movement segmentation: binary array where 0=reference, 1=moving
# Make sure we have both reference and moving points, with enough moving points
mov_seg = np.zeros(num_points, dtype=np.int32)
mov_seg[50:] = 1  # Points 50-149 are moving points

ARGS = {
    "pcpos": pcpos,
    "simmat_raw": simmat_raw,
    "mov_seg": mov_seg,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, sklearn — 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
point_cloud_to_volume Ran
ran; our contract draft was wrong, not the code
Salingo/RPM-Net/code/utils/pc_util.py
code served (permissive licence) · get_code("65920d5373d155d2")
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 3, dtype family float, shape (4, 4, 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

# Create sample point cloud data
# The function expects Nx3 points in range [-radius, radius]
np.random.seed(0)
points = np.random.uniform(-1.0, 1.0, size=(8, 3)).astype(np.float32)

# Define vsize - the volume grid dimension
vsize = 4

# Define radius - the range of points
radius = 1.0

ARGS = {
    "points": points,
    "vsize": vsize,
    "radius": radius,
}
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 3, dtype family float, shape (4, 4, 4) — shape (4, 4, 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
point_cloud_to_volume_batch Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
Salingo/RPM-Net/code/utils/pc_util.py
code served (permissive licence) · get_code("e9858b2203038709")
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 (2, 1728) 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

# Create a small batch of point clouds
# BxNx3 where B=2 (batch size), N=4 (number of points), 3 (x,y,z coordinates)
batch_size = 2
num_points = 4
point_clouds = np.random.uniform(-1.0, 1.0, size=(batch_size, num_points, 3)).astype(np.float32)

# Ensure points are within the expected radius range
point_clouds = np.clip(point_clouds, -0.9, 0.9)

ARGS = {
    "point_clouds": point_clouds,
    "vsize": 12,
    "radius": 1.0,
    "flatten": True,
}
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 (2, 1728) — shape (2, 1728) 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
rotate_point_cloud Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
Salingo/RPM-Net/code/utils/provider.py
code served (permissive licence) · get_code("adb85367d5bf360a")
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 3, dtype family float, shape (2, 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 numpy as np

np.random.seed(0)

# Create a small batch of point clouds
# BxNx3 array where B=2 (batch size), N=4 (number of points), 3 (x,y,z coordinates)
batch_data = np.random.randn(2, 4, 3).astype(np.float32)

ARGS = {
    "batch_data": batch_data
}
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 3, dtype family float, shape (2, 4, 3) — shape (2, 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
shuffle_data Ran
ran; our contract draft was wrong, not the code
Salingo/RPM-Net/code/utils/provider.py
pointer only (licence: MIT); the stored copy get_code serves, from Levishery/Flywire-Neuron-Tracing, is pointer only (licence: NONE) · get_code("06353aadebc1724b")
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 Levishery/Flywire-Neuron-Tracing, 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.

shuffle_points Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
Salingo/RPM-Net/code/utils/provider.py
code served (permissive licence) · get_code("a97f76b9c0811c93")
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 3, dtype family float, shape (2, 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 numpy as np

# Create a small batch of point cloud data
# BxNxC format: B=batch size, N=number of points, C=channels (coordinates)
batch_size = 2
num_points = 4
channels = 3

batch_data = np.random.randn(batch_size, num_points, channels).astype(np.float32)

ARGS = {
    "batch_data": batch_data
}
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 3, dtype family float, shape (2, 4, 3) — shape (2, 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
volume_to_point_cloud Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
Salingo/RPM-Net/code/utils/pc_util.py
code served (permissive licence) · get_code("660539278e1dca50")
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 int, 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

# Create a small occupancy grid (3x3x3) with some occupied voxels
vol = np.zeros((3, 3, 3), dtype=np.int32)
vol[0, 0, 0] = 1
vol[1, 1, 1] = 1
vol[2, 2, 2] = 1

ARGS = {
    "vol": vol
}
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 int, 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
conv1d Not yet run
unverified (harvested, no recorded run)
Salingo/RPM-Net/code/utils/tf_util.py
code served (permissive licence) · get_code("18d51d8d06002af3")
How it ran

no invocation recorded.

conv2d Not yet run
unverified (harvested, no recorded run)
Salingo/RPM-Net/code/utils/tf_util.py
code served (permissive licence) · get_code("dd4ea839e0207aea")
How it ran

no invocation recorded.

conv2d_transpose Not yet run
unverified (harvested, no recorded run)
Salingo/RPM-Net/code/utils/tf_util.py
code served (permissive licence) · get_code("5d5a54e9e61f622c")
How it ran

no invocation recorded.

get_partseg_loss Not yet run
unverified (harvested, no recorded run)
Salingo/RPM-Net/code/model_rpm.py
code served (permissive licence) · get_code("a0f1d6f56f0bc83d")
How it ran

no invocation recorded.

placeholder_inputs Not yet run
unverified (harvested, no recorded run)
Salingo/RPM-Net/code/model_rpm.py
code served (permissive licence) · get_code("9240c7268167d920")
How it ran

no invocation recorded.

sample_and_group_all Not yet run
unverified (harvested, no recorded run)
Salingo/RPM-Net/code/utils/pointnet_util.py
code served (permissive licence) · get_code("142a56400c483118")
How it ran

no invocation recorded.

Also present in other papers' code

Of 14 samples lifted from this paper's linked repositories, 14 carry a function identity and 0 do not. Of the 14 distinct functions with an identity, 10 are also present in other papers whose code we hold (10 with at least one paper dated earlier, 0 the same month, 9 later) and 4 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
shuffle_data 17 other papers
8 dated earlier, 9 later
1803.05827 (2018-03)
Local Spectral Graph Convolution for Point Set Feature Learning
1803.11527 (2018-03)
SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filters
1811.07246 (2018-11)
PointConv: Deep Convolutional Networks on 3D Point Clouds
and 14 more not named here
shuffle_points 11 other papers
2 dated earlier, 9 later
1811.07246 (2018-11)
PointConv: Deep Convolutional Networks on 3D Point Clouds
1812.11647 (2018-12)
Path-Invariant Map Networks
2103.01458 (2021-03)
Diffusion Probabilistic Models for 3D Point Cloud Generation
and 8 more not named here
rotate_point_cloud 7 other papers
3 dated earlier, 4 later
1803.11527 (2018-03)
SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filters
1904.10014 (2019-04)
Linked Dynamic Graph CNN: Learning on Point Cloud via Linking Hierarchical Features
1908.04616 (2019-08)
Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Data
and 4 more not named here
sample_and_group_all 7 other papers
5 dated earlier, 1 later, 1 same year, order not determinable
1803.05827 (2018-03)
Local Spectral Graph Convolution for Point Set Feature Learning
1811.07782 (2018-11)
Modeling Local Geometric Structure of 3D Point Clouds using Geo-CNN
1812.03320 (2018-12)
GSPN: Generative Shape Proposal Network for 3D Instance Segmentation in Point Cloud
and 4 more not named here
conv1d 5 other papers
4 dated earlier, 1 later
1811.07782 (2018-11)
Modeling Local Geometric Structure of 3D Point Clouds using Geo-CNN
1812.00020 (2018-12)
TextureNet: Consistent Local Parametrizations for Learning from High-Resolution Signals on Meshes
1812.03320 (2018-12)
GSPN: Generative Shape Proposal Network for 3D Instance Segmentation in Point Cloud
and 2 more not named here
conv2d 5 other papers
4 dated earlier, 1 later
1811.07782 (2018-11)
Modeling Local Geometric Structure of 3D Point Clouds using Geo-CNN
1812.00020 (2018-12)
TextureNet: Consistent Local Parametrizations for Learning from High-Resolution Signals on Meshes
1812.03320 (2018-12)
GSPN: Generative Shape Proposal Network for 3D Instance Segmentation in Point Cloud
and 2 more not named here
point_cloud_to_volume 4 other papers
1 dated earlier, 2 later, 1 same year, order not determinable
1803.05827 (2018-03)
Local Spectral Graph Convolution for Point Set Feature Learning
aaai_6994 (2020 (year only))
JSNet: Joint Instance and Semantic Segmentation of 3D Point Clouds
2401.01552 (2024-01)
CRA-PCN: Point Cloud Completion with Intra-and Inter-level Cross-Resolution Transformers
and 1 more not named here
point_cloud_to_volume_batch 4 other papers
1 dated earlier, 2 later, 1 same year, order not determinable
1803.05827 (2018-03)
Local Spectral Graph Convolution for Point Set Feature Learning
aaai_6994 (2020 (year only))
JSNet: Joint Instance and Semantic Segmentation of 3D Point Clouds
2401.01552 (2024-01)
CRA-PCN: Point Cloud Completion with Intra-and Inter-level Cross-Resolution Transformers
and 1 more not named here
volume_to_point_cloud 4 other papers
1 dated earlier, 2 later, 1 same year, order not determinable
1803.05827 (2018-03)
Local Spectral Graph Convolution for Point Set Feature Learning
aaai_6994 (2020 (year only))
JSNet: Joint Instance and Semantic Segmentation of 3D Point Clouds
2401.01552 (2024-01)
CRA-PCN: Point Cloud Completion with Intra-and Inter-level Cross-Resolution Transformers
and 1 more not named here
conv2d_transpose 2 other papers
2 dated earlier
1812.00020 (2018-12)
TextureNet: Consistent Local Parametrizations for Learning from High-Resolution Signals on Meshes
1812.11647 (2018-12)
Path-Invariant Map Networks

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

We introduce RPM-Net, a deep learning-based approach which simultaneously infers movable parts and hallucinates their motions from a single, un-segmented, and possibly partial, 3D point cloud shape. RPM-Net is a novel Recurrent Neural Network (RNN), composed of an encoder-decoder pair with interleaved Long Short-Term Memory (LSTM) components, which together predict a temporal sequence of pointwise displacements for the input point cloud. At the same time, the displacements allow the network to learn movable parts, resulting in a motion-based shape segmentation. Recursive applications of RPM-Net on the obtained parts can predict finer-level part motions, resulting in a hierarchical object segmentation. Furthermore, we develop a separate network to estimate part mobilities, e.g., per-part motion parameters, from the segmented motion sequence. Both networks learn deep predictive models from a training set that exemplifies a variety of mobilities for diverse objects. We show results of simultaneous motion and part predictions from synthetic and real scans of 3D objects exhibiting a variety of part mobilities, possibly involving multiple movable parts.

For agents

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

get_harvested_code_for_paper("2006.14865")
get_code_for_paper("2006.14865")
have("2006.14865")

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

curl https://syntology.ai/api/ran/2006.14865.json

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

[![Syntology run record](https://syntology.ai/api/ran/2006.14865.svg)](https://syntology.ai/paper/2006.14865)

Connect an agent — have() is free.