SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2305.02528 · CVPR · 2023

Self-Supervised 3D Scene Flow Estimation Guided by Superpoints

Le Hui, Jin Xie, Jian Yang, Yaqi Shen

arXiv · PDF · Open in the Atlas

Code that ran

4 of 13 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 3 have no contract verdict; 1 failure of our instrument; 9 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/2305.02528.json · badge: /api/ran/2305.02528.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
supersyq/spflownet marked official in Papers with Code
Papers with Code archive
4 ran · 9 no recorded run
FunctionStatusWhere it lives
Graph Ran
ran on a synthesized input · constructed an object; no result was computed
supersyq/spflownet/model.py
code served (permissive licence) · get_code("6da1b74810b3d2b3")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, class construct-then-call prompt, model not recorded) and returned Graph: the class was constructed and called, and the call returned an instance of its own class. 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 torch

# Point cloud: batch_size=2, num_points=5, coordinates=3
pcloud = torch.randn(2, 5, 3)
nb_neighbors = 3

INIT_ARGS = {
    'edges': torch.tensor([0, 1, 2, 0, 1, 2, 5, 6, 7, 5, 6, 7, 10, 11, 12, 10, 11, 12, 15, 16, 17, 15, 16, 17, 20, 21, 22, 20, 21, 22]),
    'edge_feats': torch.randn(30, 3),
    'k_neighbors': 3,
    'size': (10, 10)
}

ARGS = {
    'pcloud': pcloud,
    'nb_neighbors': nb_neighbors
}

METHOD = 'construct_graph'
Setup block drafted by
a language model, class construct-then-call prompt, model not recorded
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Graph — the call returned an instance of its own class, which has no array shape; none is stated — the instrument coerces any output to an array; for a Graph 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: torch and numpy seeded to 0 by the harness immediately before the class was constructed from INIT_ARGS (fixture_check.py)
SetConv Ran
ran on a synthesized input
supersyq/spflownet/model.py
code served (permissive licence) · get_code("1c8b3aeac2b9fa9e")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, class construct-then-call prompt, model not recorded) and returned Tensor, ndim 3, 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 torch
import numpy as np

# Create a simple graph-like object to hold edges and edge features
class SimpleGraph:
    def __init__(self, edges, edge_feats, k_neighbors, size):
        self.edges = edges
        self.edge_feats = edge_feats
        self.k_neighbors = k_neighbors
        self.size = size

# Initialize parameters
nb_feat_in = 4
nb_feat_out = 6
batch_size = 2
n_points = 5
k_neighbors = 3

# Create input signal: B x N x nb_feat_in
signal = torch.randn(batch_size, n_points, nb_feat_in)

# Create graph structure
# For a point cloud with B batches, N points, and K neighbors per point
# edges should index into the flattened (B*N) points
# Total number of edges = B * N * K
total_points = batch_size * n_points
total_edges = batch_size * n_points * k_neighbors

# Create edges: indices into flattened signal (B*N points)
# Each point has k_neighbors connections
edges = torch.randint(0, total_points, (total_edges,))

# Edge features: relative positions (3D coordinates)
edge_feats = torch.randn(total_edges, 3)

# Create graph object
graph = SimpleGraph(
    edges=edges,
    edge_feats=edge_feats,
    k_neighbors=k_neighbors,
    size=torch.tensor([batch_size * n_points])  # size[0] should be B * N_out
)

INIT_ARGS = {
    'nb_feat_in': nb_feat_in,
    'nb_feat_out': nb_feat_out
}

ARGS = {
    'signal': signal,
    'graph': graph
}
Setup block drafted by
a language model, class construct-then-call prompt, model not recorded
Imports
numpy, 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 — no output shape is stated: observe_signature.py observed this class with its constructor sizes canonicalised where it could, which the node does not record, so its shape is not stated as this setup block's
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: torch and numpy seeded to 0 by the harness immediately before the class was constructed from INIT_ARGS (fixture_check.py)
SetConv3 Ran
ran on a synthesized input
supersyq/spflownet/model.py
code served (permissive licence) · get_code("e38f31e385630980")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, class construct-then-call prompt, model not recorded) and returned Tensor, ndim 4, 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 torch
import numpy as np

# INIT_ARGS: parameters for SetConv3.__init__
INIT_ARGS = {
    'nb_feat_in': 8,
    'nb_feat_out': 12
}

# ARGS: parameters for SetConv3.forward
# forward expects signal with shape (b, c, n, k)
# where c must match nb_feat_in from INIT_ARGS
ARGS = {
    'signal': torch.randn(2, 8, 5, 7)  # batch=2, channels=8 (matches nb_feat_in), n=5, k=7
}
Setup block drafted by
a language model, class construct-then-call prompt, model not recorded
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 4, dtype family float — no output shape is stated: observe_signature.py observed this class with its constructor sizes canonicalised where it could, which the node does not record, so its shape is not stated as this setup block's
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: torch and numpy seeded to 0 by the harness immediately before the class was constructed from INIT_ARGS (fixture_check.py)
knn_point Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
supersyq/spflownet/model.py
code served (permissive licence) · get_code("fe77e7e139a83777")
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 Tensor, ndim 3, dtype family int, 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)

# nsample: max sample number in local region (int)
nsample = 3

# xyz: all points, [B, N, C]
# B=2 (batch), N=5 (number of points), C=4 (coordinates)
xyz = torch.randn(2, 5, 4)

# new_xyz: query points, [B, S, C]
# B=2 (batch), S=3 (number of query points), C=4 (coordinates)
new_xyz = torch.randn(2, 3, 4)

ARGS = {
    "nsample": nsample,
    "xyz": xyz,
    "new_xyz": new_xyz,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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 int, 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
FlowEmbedding Not yet run
unverified (harvested, no recorded run)
supersyq/spflownet/model.py
code served (permissive licence) · get_code("b9376d811db33172")
How it ran

no invocation recorded.

GRU Not yet run
unverified (harvested, no recorded run)
supersyq/spflownet/model.py
code served (permissive licence) · get_code("a39c43b84a95d0f0")
How it ran

no invocation recorded.

PointWarping Not yet run
unverified (harvested, no recorded run)
supersyq/spflownet/model.py
code served (permissive licence) · get_code("d7d8b95a60997e40")
How it ran

no invocation recorded.

PointWarping_feat Not yet run
unverified (harvested, no recorded run)
supersyq/spflownet/model.py
code served (permissive licence) · get_code("379cac634dc98756")
How it ran

no invocation recorded.

SPFlowNet Not yet run
unverified (harvested, no recorded run)
supersyq/spflownet/model.py
code served (permissive licence) · get_code("ef1cf52278469d4f")
How it ran

no invocation recorded.

UpsampleFlow Not yet run
unverified (harvested, no recorded run)
supersyq/spflownet/model.py
code served (permissive licence) · get_code("b65f4f22c93edb15")
How it ran

no invocation recorded.

index_points_gather Not yet run
unverified (harvested, no recorded run)
supersyq/spflownet/model.py
code served (permissive licence) · get_code("09f37ba1ec8da732")
How it ran

no invocation recorded.

index_points_group Not yet run
unverified (harvested, no recorded run)
supersyq/spflownet/model.py
code served (permissive licence) · get_code("4fa04f3cc6b992c4")
How it ran

no invocation recorded.

learn_SLIC_calc_mutual Not yet run
unverified (harvested, no recorded run)
supersyq/spflownet/model.py
code served (permissive licence) · get_code("f4d1c98a584e7adb")
How it ran

no invocation recorded.

Also present in other papers' code

Of 13 samples lifted from this paper's linked repositories, 13 carry a function identity and 0 do not. Of the 13 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 1 later) and 12 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
knn_point
brick of this paper's assembly: helper
21 other papers
6 dated earlier, 15 later · 1 only as an assembly brick
1612.00593 (2016-12)
PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
2111.14819 (2021-11)
Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling
2202.07123 (2022-02)
Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework
and 18 more not named here

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

3D scene flow estimation aims to estimate point-wise motions between two consecutive frames of point clouds. Superpoints, i.e., points with similar geometric features, are usually employed to capture similar motions of local regions in 3D scenes for scene flow estimation. However, in existing methods, superpoints are generated with the offline clustering methods, which cannot characterize local regions with similar motions for complex 3D scenes well, leading to inaccurate scene flow estimation. To this end, we propose an iterative end-to-end superpoint based scene flow estimation framework, where the superpoints can be dynamically updated to guide the point-level flow prediction. Specifically, our framework consists of a flow guided superpoint generation module and a superpoint guided flow refinement module. In our superpoint generation module, we utilize the bidirectional flow information at the previous iteration to obtain the matching points of points and superpoint centers for soft point-to-superpoint association construction, in which the superpoints are generated for pairwise point clouds. With the generated superpoints, we first reconstruct the flow for each point by adaptively aggregating the superpoint-level flow, and then encode the consistency between the reconstructed flow of pairwise point clouds. Finally, we feed the consistency encoding along with the reconstructed flow into GRU to refine point-level flow. Extensive experiments on several different datasets show that our method can achieve promising performance. Code is available at https://github. com/supersyq/SPFlowNet.

For agents

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

get_harvested_code_for_paper("2305.02528")
get_code_for_paper("2305.02528")
have("2305.02528")

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

curl https://syntology.ai/api/ran/2305.02528.json

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

[![Syntology run record](https://syntology.ai/api/ran/2305.02528.svg)](https://syntology.ai/paper/2305.02528)

Connect an agent — have() is free.