SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1806.01411 · 2018

FlowNet3D: Learning Scene Flow in 3D Point Clouds

arXiv · PDF · Open in the Atlas

Code that ran

5 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; 3 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/1806.01411.json · badge: /api/ran/1806.01411.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
xingyul/flownet3d canonical (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
hyangwinter/flownet3d_pytorch community (classifier label)
classifier basis not recorded on the link
4 ran · 2 no recorded run
FunctionStatusWhere it lives
jitter_pointcloud Ran
ran on a synthesized input
hyangwinter/flownet3d_pytorch/data.py
code served (permissive licence) · get_code("0eecf33500f60f91")
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, 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 a small pointcloud array
# Shape: (N, C) where N=2 points, C=4 coordinates
pointcloud = np.random.randn(2, 4).astype(np.float32)

ARGS = {
    "pointcloud": pointcloud,
    "sigma": 0.01,
    "clip": 0.05,
}
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, 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
quat2mat Ran
ran; our contract draft was wrong, not the code
hyangwinter/flownet3d_pytorch/util.py
code served (permissive licence) · get_code("838e2078ad9224da")
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, 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 torch

torch.manual_seed(0)

# Create a batch of quaternions in [x, y, z, w] format
# Shape: (batch_size, 4)
quat = torch.randn(2, 4)

ARGS = {
    "quat": quat
}
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, 3, 3) — shape (2, 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
scene_flow_EPE_np Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
xingyul/flownet3d/evaluate.py
code served (permissive licence) · get_code("ad28e10d41422ea2")
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, ndim 1, 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

# Analyze the function:
# - pred: shape (batch, points, 3) - predicted scene flow
# - labels: shape (batch, points, 3) - ground truth scene flow
# - mask: shape (batch, points) - binary mask indicating valid points
# The function computes error metrics on scene flow predictions

# Create small sample data
batch_size = 2
num_points = 4
flow_dim = 3

# Predicted flow: (batch=2, points=4, dim=3)
pred = np.random.randn(batch_size, num_points, flow_dim).astype(np.float32)

# Ground truth labels: (batch=2, points=4, dim=3)
labels = np.random.randn(batch_size, num_points, flow_dim).astype(np.float32)

# Mask: (batch=2, points=4) - boolean mask with some valid points
mask = np.random.randint(0, 2, size=(batch_size, num_points)).astype(bool)
# Ensure at least some points are valid in each batch
mask[0, 0] = True
mask[1, 0] = True

ARGS = {
    "pred": pred,
    "labels": labels,
    "mask": mask
}
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, ndim 1, dtype family float — a tuple 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
transform_point_cloud Ran
ran on a synthesized input
hyangwinter/flownet3d_pytorch/util.py
code served (permissive licence) · get_code("421c2d3aa126a3e8")
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, 3, 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 batch of 2 point clouds, each with 3 points in 3D space
# Shape: (batch_size=2, channels=3, num_points=4)
point_cloud = torch.randn(2, 3, 4)

# Create quaternion rotations for batch of 2
# Shape: (batch_size=2, 4) where 4 is [x, y, z, w]
# Normalize to make valid quaternions
quat_rotation = torch.randn(2, 4)
quat_rotation = quat_rotation / torch.norm(quat_rotation, dim=1, keepdim=True)

# Create translation vectors for batch of 2
# Shape: (batch_size=2, 3)
translation = torch.randn(2, 3)

ARGS = {
    "point_cloud": point_cloud,
    "rotation": quat_rotation,
    "translation": translation,
}
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, 3, 4) — shape (2, 3, 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
translate_pointcloud Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
hyangwinter/flownet3d_pytorch/data.py
pointer only (licence: MIT); the stored copy get_code serves, from MosyMosy/Purge-Gate, is pointer only (licence: NONE) · get_code("791051c3e72b67d2")
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 MosyMosy/Purge-Gate, 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.

load_data Not yet run
unverified (harvested, no recorded run)
hyangwinter/flownet3d_pytorch/data.py
code served (permissive licence) · get_code("de4ec31e485abce5")
How it ran

no invocation recorded.

npmat2euler Not yet run
unverified (harvested, no recorded run)
hyangwinter/flownet3d_pytorch/util.py
code served (permissive licence) · get_code("5aaf14d09c81093c")
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, 5 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 5 later) and 2 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
translate_pointcloud 13 other papers
13 later
1906.12320 (2019-06)
PointFlow: 3D Point Cloud Generation with Continuous Normalizing Flows
1912.00195 (2019-12)
SGAS: Sequential Greedy Architecture Search
2110.02210 (2021-10)
Mix3D: Out-of-Context Data Augmentation for 3D Scenes
and 10 more not named here
quat2mat 3 other papers
3 later
2110.02210 (2021-10)
Mix3D: Out-of-Context Data Augmentation for 3D Scenes
2202.11292 (2022-02)
Reliable Inlier Evaluation for Unsupervised Point Cloud Registration
2310.17359 (2023-10)
SE(3) Diffusion Model-based Point Cloud Registration for Robust 6D Object Pose Estimation
jitter_pointcloud 1 other paper
1 later
2110.02210 (2021-10)
Mix3D: Out-of-Context Data Augmentation for 3D Scenes
npmat2euler 1 other paper
1 later
2202.11292 (2022-02)
Reliable Inlier Evaluation for Unsupervised Point Cloud Registration
transform_point_cloud 1 other paper
1 later
2202.11292 (2022-02)
Reliable Inlier Evaluation for Unsupervised Point Cloud Registration

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

Many applications in robotics and human-computer interaction can benefit from understanding 3D motion of points in a dynamic environment, widely noted as scene flow. While most previous methods focus on stereo and RGB-D images as input, few try to estimate scene flow directly from point clouds. In this work, we propose a novel deep neural network named $FlowNet3D$ that learns scene flow from point clouds in an end-to-end fashion. Our network simultaneously learns deep hierarchical features of point clouds and flow embeddings that represent point motions, supported by two newly proposed learning layers for point sets. We evaluate the network on both challenging synthetic data from FlyingThings3D and real Lidar scans from KITTI. Trained on synthetic data only, our network successfully generalizes to real scans, outperforming various baselines and showing competitive results to the prior art. We also demonstrate two applications of our scene flow output (scan registration and motion segmentation) to show its potential wide use cases.

For agents

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

get_harvested_code_for_paper("1806.01411")
get_code_for_paper("1806.01411")
have("1806.01411")

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

curl https://syntology.ai/api/ran/1806.01411.json

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

[![Syntology run record](https://syntology.ai/api/ran/1806.01411.svg)](https://syntology.ai/paper/1806.01411)

Connect an agent — have() is free.