SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2408.06110 · ECCV · 2024

RISurConv: Rotation Invariant Surface Attention-Augmented Convolutions for 3D Point Cloud Classification and Segmentation

Zhiyuan Zhang, Xiang, Yang Licheng, Zhiyu 2⋆

arXiv · PDF · Open in the Atlas

Code that ran

11 of 16 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (2 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; 9 failures of our instrument; 5 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/2408.06110.json · badge: /api/ran/2408.06110.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
cszyzhang/RISurConv marked official in Papers with Code
Papers with Code archive
11 ran · 5 no recorded run
FunctionStatusWhere it lives
RISP_features Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
cszyzhang/RISurConv/models/risurconv_utils.py
code served (permissive licence) · get_code("43cf46f25fd17bf8")
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 torch

torch.manual_seed(0)

# Build small tensors with distinct dimensions
B = 2  # batch size
N = 4  # number of points
C = 3  # coordinate dimension
K = 5  # number of neighbors

# xyz: [B, N, C] - point cloud coordinates
xyz = torch.randn(B, N, C)

# norm: [B, N, C] - normal vectors at each point
norm = torch.randn(B, N, C)

# new_xyz: [B, N, C] - query point positions
new_xyz = torch.randn(B, N, C)

# new_norm: [B, N, C] - normal vectors at query points
new_norm = torch.randn(B, N, C)

# idx: [B, N, K] - neighbor indices
idx = torch.randint(0, N, (B, N, K))

# group_all: boolean parameter
group_all = False

ARGS = {
    'xyz': xyz,
    'norm': norm,
    'new_xyz': new_xyz,
    'new_norm': new_norm,
    'idx': idx,
    'group_all': group_all
}
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 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
SA_Layer Ran
ran on a synthesized input · constructed an object; no result was computed
cszyzhang/RISurConv/models/risurconv_utils.py
code served (permissive licence) · get_code("df1d41f48a849dc1")
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 an instance of its own class, SA_Layer: the run constructed the object and did not call it, so no result was computed. 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
import torch.nn as nn

torch.manual_seed(0)

class SA_Layer(nn.Module):

    def __init__(self, channels):
        super(SA_Layer, self).__init__()
        self.q_conv = nn.Conv1d(channels, channels // 4, 1, bias=False)
        self.k_conv = nn.Conv1d(channels, channels // 4, 1, bias=False)
        self.v_conv = nn.Conv1d(channels, channels, 1)
        self.trans_conv = nn.Conv1d(channels, channels, 1)
        self.after_norm = nn.BatchNorm1d(channels)
        self.act = nn.ReLU()
        self.softmax = nn.Softmax(dim=-1)

    def forward(self, x):
        x_q = self.q_conv(x).permute(0, 2, 1)
        x_k = self.k_conv(x)
        x_v = self.v_conv(x)
        energy = x_q @ x_k
        attention = self.softmax(energy)
        attention = attention / (1e-09 + attention.sum(dim=1, keepdims=True))
        x_r = x_v @ attention
        x_r = self.act(self.after_norm(self.trans_conv(x - x_r)))
        x = x + x_r
        return x

channels = 4
input_tensor = torch.randn(2, 4, 3)

ARGS = {
    'channels': channels
}

sa_layer = SA_Layer(**ARGS)
output = sa_layer(input_tensor)
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 SA_Layer — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a SA_Layer 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
SA_Layer_2d Ran
ran on a synthesized input · constructed an object; no result was computed
cszyzhang/RISurConv/models/risurconv_utils.py
code served (permissive licence) · get_code("1094b06a1786c824")
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 an instance of its own class, SA_Layer_2d: the run constructed the object and did not call it, so no result was computed. 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
import torch.nn as nn

torch.manual_seed(0)

# SA_Layer_2d expects:
# - channels: int (number of input channels)
# The forward method expects:
# - x: tensor of shape (batch, channels, height, width)

channels = 8
batch_size = 2
height = 4
width = 3

# Create input tensor with shape (batch, channels, height, width)
x = torch.randn(batch_size, channels, height, width)

ARGS = {
    "channels": channels,
}
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 SA_Layer_2d — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a SA_Layer_2d 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
calculate_new_surface_feature Ran
ran; our contract draft was wrong, not the code
cszyzhang/RISurConv/models/risurconv_utils.py
code served (permissive licence) · get_code("1f0459a13258d8d5")
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 4, dtype family float, shape (2, 3, 4, 5) 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 tensors with shape (batch=2, height=3, width=4, channels=3)
# These represent surface normal vectors or position vectors
batch_size = 2
height = 3
width = 4
channels = 3

new_xi = torch.randn(batch_size, height, width, channels)
new_xi_norm = torch.randn(batch_size, height, width, channels)
x1 = torch.randn(batch_size, height, width, channels)
x1_norm = torch.randn(batch_size, height, width, channels)
x2 = torch.randn(batch_size, height, width, channels)
x2_norm = torch.randn(batch_size, height, width, channels)
x3 = torch.randn(batch_size, height, width, channels)
x3_norm = torch.randn(batch_size, height, width, channels)

ARGS = {
    "new_xi": new_xi,
    "new_xi_norm": new_xi_norm,
    "x1": x1,
    "x1_norm": x1_norm,
    "x2": x2,
    "x2_norm": x2_norm,
    "x3": x3,
    "x3_norm": x3_norm,
}
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 4, dtype family float, shape (2, 3, 4, 5) — shape (2, 3, 4, 5) 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
calculate_surface_norm Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
cszyzhang/RISurConv/models/risurconv_utils.py
code served (permissive licence) · get_code("8f64768fc45382ea")
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 4, dtype family float, shape (2, 4, 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)

# The function expects two tensors with shape (batch, height, width, 3)
# It performs cross product operations on the last dimension
# We'll create two small tensors with batch=2, height=4, width=3, channels=3

surface_norm1 = torch.randn(2, 4, 3, 3)
surface_norm2 = torch.randn(2, 4, 3, 3)

ARGS = {
    "surface_norm1": surface_norm1,
    "surface_norm2": surface_norm2,
}
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 4, dtype family float, shape (2, 4, 3, 3) — shape (2, 4, 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
calculate_two_surface_feature Ran
ran; our contract draft was wrong, not the code
cszyzhang/RISurConv/models/risurconv_utils.py
code served (permissive licence) · get_code("8feced39236919ff")
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 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

torch.manual_seed(0)

# The function expects:
# - x1: a tensor that supports norm, subtraction, division, multiplication, sum operations
# - x1_norm: a tensor representing normals for x1
# - x2: a tensor similar to x1
# - x2_norm: a tensor representing normals for x2

# Looking at the function body:
# - x1 and x2 are subtracted: x1 - x2
# - Result is normalized with torch.norm(..., dim=-1, keepdim=True)
# - This normalized result is multiplied with x1_norm and x2_norm
# - Results are summed along dim=-1
# All operations suggest batch dimension and feature dimension

# Create small tensors: batch_size=2, feature_dim=4
batch_size = 2
feature_dim = 4

x1 = torch.randn(batch_size, feature_dim)
x1_norm = torch.randn(batch_size, feature_dim)
x2 = torch.randn(batch_size, feature_dim)
x2_norm = torch.randn(batch_size, feature_dim)

ARGS = {
    "x1": x1,
    "x1_norm": x1_norm,
    "x2": x2,
    "x2_norm": x2_norm,
}
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 tuple, ndim 3, 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
calculate_unit Ran
ran; our contract draft was wrong, not the code
cszyzhang/RISurConv/models/risurconv_utils.py
code served (permissive licence) · get_code("3c5cec821dd98f4a")
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)

# Create small tensors with distinct dimensions
# new_xi: shape (2, 4) - batch of 2, dimension 4
# x1: shape (2, 4) - batch of 2, dimension 4
new_xi = torch.randn(2, 4)
x1 = torch.randn(2, 4)

ARGS = {
    "new_xi": new_xi,
    "x1": x1,
}
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
compute_LRA_one Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
cszyzhang/RISurConv/models/risurconv_utils.py
code served (permissive licence) · get_code("23d2fbe28c8f69fd")
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)

# The function expects:
# - group_xyz: tensor of shape (B, S, N, C)
#   B = batch size
#   S = number of groups
#   N = number of points in group
#   C = coordinate dimension (3 for xyz)
# - weighting: boolean flag

# Create a small valid tensor
# Using distinct dimensions: B=2, S=3, N=4, C=3
group_xyz = torch.randn(2, 3, 4, 3)

ARGS = {
    "group_xyz": group_xyz,
    "weighting": False,
}
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
group_index Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
cszyzhang/RISurConv/models/risurconv_utils.py
code served (permissive licence) · get_code("d95836fa7aed2ad6")
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 int, shape (2, 3, 2) 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)

# Small tensors with distinct dimensions for batch, points, and coordinates
B = 2  # batch size
N = 5  # number of points in xyz
S = 3  # number of query points in new_xyz
C = 4  # coordinate dimension
nsample = 2  # max sample number in local region
radius = 1.0  # radius for ball query (not used in knn mode)

# Create sample point clouds
xyz = torch.randn(B, N, C)  # [B, N, C] - all points
new_xyz = torch.randn(B, S, C)  # [B, S, C] - query points

ARGS = {
    'nsample': nsample,
    'radius': radius,
    'xyz': xyz,
    'new_xyz': new_xyz,
    'group': 'knn'
}
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 int, shape (2, 3, 2) — shape (2, 3, 2) 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
knn_point Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
cszyzhang/RISurConv/models/risurconv_utils.py
code served (permissive licence) · get_code("004f60206cdb3858")
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 int, 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 torch

torch.manual_seed(0)

# Create small test tensors
# xyz: all points [B, N, C] where B=batch, N=num_points, C=coordinates
xyz = torch.randn(2, 5, 3)

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

# nsample: max sample number in local region
nsample = 3

ARGS = {
    "nsample": nsample,
    "xyz": xyz,
    "new_xyz": new_xyz,
}
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 int, 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
square_distance Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
cszyzhang/RISurConv/models/risurconv_utils.py
code served (permissive licence) · get_code("bba5dc7caf857cd2")
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 float, shape (2, 4, 5) 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 source points: [B, N, C]
# B=2 (batch), N=4 (num source points), C=3 (coordinates)
src = torch.randn(2, 4, 3)

# Create target points: [B, M, C]
# B=2 (batch), M=5 (num target points), C=3 (coordinates)
dst = torch.randn(2, 5, 3)

ARGS = {
    "src": src,
    "dst": dst,
}
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 float, shape (2, 4, 5) — shape (2, 4, 5) 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
RISurConvSetAbstraction Not yet run
unverified (harvested, no recorded run)
cszyzhang/RISurConv/models/risurconv_utils.py
code served (permissive licence) · get_code("2307abca234405a4")
How it ran

no invocation recorded.

order_index Not yet run
unverified (harvested, no recorded run)
cszyzhang/RISurConv/models/risurconv_utils.py
code served (permissive licence) · get_code("48ba9ee2d2d9ee39")
How it ran

no invocation recorded.

sample Not yet run
unverified (harvested, no recorded run)
cszyzhang/RISurConv/models/risurconv_utils.py
code served (permissive licence) · get_code("349f491c52f4f205")
How it ran

no invocation recorded.

sample_and_group Not yet run
unverified (harvested, no recorded run)
cszyzhang/RISurConv/models/risurconv_utils.py
code served (permissive licence) · get_code("78296b62cc2e5ef7")
How it ran

no invocation recorded.

sample_and_group_all Not yet run
unverified (harvested, no recorded run)
cszyzhang/RISurConv/models/risurconv_utils.py
code served (permissive licence) · get_code("5ff6e719b0d1ec24")
How it ran

no invocation recorded.

Also present in other papers' code

Of 16 samples lifted from this paper's linked repositories, 16 carry a function identity and 0 do not. Of the 16 distinct functions with an identity, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 1 the same month, 2 later) and 14 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
square_distance
brick of this paper's assembly: helper
75 other papers
59 dated earlier, 1 the same month, 13 later, 2 same year, order not determinable · 9 only as an assembly brick
1706.02413 (2017-06)
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space
1811.07246 (2018-11)
PointConv: Deep Convolutional Networks on 3D Point Clouds
2003.00410 (2020-03)
PF-Net: Point Fractal Network for 3D Point Cloud Completion
and 72 more not named here
knn_point
brick of this paper's assembly: helper
21 other papers
12 dated earlier, 8 later, 1 same year, order not determinable · 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

Despite the progress on 3D point cloud deep learning, most prior works focus on learning features that are invariant to translation and point permutation, and very limited efforts have been devoted for rotation invariant property. Several recent studies achieve rotation invariance at the cost of lower accuracies. In this work, we close this gap by proposing a novel yet effective rotation invariant architecture for 3D point cloud classification and segmentation. Instead of traditional pointwise operations, we construct local triangle surfaces to capture more detailed surface structure, based on which we can extract highly expressive rotation invariant surface properties which are then integrated into an attention-augmented convolution operator named RISurConv to generate refined attention features via self-attention layers. Based on RISur-Conv we build an effective neural network for 3D point cloud analysis that is invariant to arbitrary rotations while maintaining high accuracy. We verify the performance on various benchmarks with supreme results obtained surpassing the previous state-of-the-art by a large margin. We achieve an overall accuracy of 96.0% (+4.7%) on ModelNet40, 93.1% (+12.8%) on ScanObjectNN, and class accuracies of 91.5% (+3.6%), 82.7% (+5.1%), and 78.5% (+9.2%) on the three categories of the FG3D dataset for the fine-grained classification task. Additionally, we achieve 81.5% (+1.0%) mIoU on ShapeNet for the segmentation task.

For agents

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

get_harvested_code_for_paper("2408.06110")
get_code_for_paper("2408.06110")
have("2408.06110")

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

curl https://syntology.ai/api/ran/2408.06110.json

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

[![Syntology run record](https://syntology.ai/api/ran/2408.06110.svg)](https://syntology.ai/paper/2408.06110)

Connect an agent — have() is free.