SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2103.14635 · CVPR · 2021

PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Clouds

Xiaojuan Qi, Hengshuang Zhao, Runyu Ding, Mutian Xu

arXiv · PDF · Open in the Atlas

Code that ran

4 of 5 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; 1 honoured the contract we drafted, 0 violated it and 2 have no contract verdict; 1 failure of our instrument; 1 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/2103.14635.json · badge: /api/ran/2103.14635.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
CVMI-Lab/PAConv marked official in Papers with Code
Papers with Code archive
4 ran · 1 no recorded run
FunctionStatusWhere it lives
PAConv Ran
ran on a synthesized input · constructed an object; no result was computed
CVMI-Lab/PAConv/scene_seg/model/pointnet2/paconv.py
code served (permissive licence) · get_code("cf5db9eee12d79af")
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, PAConv: 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
import copy

torch.manual_seed(0)

# Create a minimal config dict with all required keys
config = {
    'score_input': 'identity',
    'score_norm': 'softmax',
    'temp': 1,
    'init': 'kaiming',
    'hidden': [16],
    'm': 8,
    'kernel_input': 'neighbor'
}

# Define minimal activation function
activation = nn.ReLU()

# Define parameters
input_dim = 4
output_dim = 3
bn = True

ARGS = {
    'input_dim': input_dim,
    'output_dim': output_dim,
    'bn': bn,
    'activation': activation,
    'config': config
}
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 PAConv — 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 PAConv 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
ScoreNet Ran
ran on a synthesized input · constructed an object; no result was computed
CVMI-Lab/PAConv/scene_seg/model/pointnet2/paconv.py
code served (permissive licence) · get_code("6adc61d2501faab9")
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, ScoreNet: 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)

# ScoreNet parameters
in_channel = 4
out_channel = 3
hidden_unit = [8, 8]
last_bn = False
temp = 1.0

ARGS = {
    'in_channel': in_channel,
    'out_channel': out_channel,
    'hidden_unit': hidden_unit,
    'last_bn': last_bn,
    'temp': temp
}
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 ScoreNet — 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 ScoreNet 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
assign_score Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
CVMI-Lab/PAConv/scene_seg/model/pointnet2/paconv.py
code served (permissive licence) · get_code("5e25a5682fab958e")
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, 6) 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)

# Analyze the function:
# - score: tensor with size (B, N, K, m)
# - point_input: tensor that will be multiplied with score reshaped to (B, N, K, 1, m)
# - matmul(score, point_input) requires point_input to have shape (B, N, K, m, d) 
#   to produce output (B, N, K, 1, d) which then gets flattened to (B, N, K, d)

B, N, K, m = 2, 3, 4, 5
d = 6

# Create score tensor with shape (B, N, K, m)
score = torch.randn(B, N, K, m)

# Create point_input tensor with shape (B, N, K, m, d)
# This will be multiplied with score.view(B, N, K, 1, m) to get (B, N, K, 1, d)
point_input = torch.randn(B, N, K, m, d)

ARGS = {
    "score": score,
    "point_input": point_input
}
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, 6) — shape (2, 3, 4, 6) 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
get_ed Ran
ran, honoured the contract we drafted
CVMI-Lab/PAConv/scene_seg/model/pointnet2/paconv.py
code served (permissive licence) · get_code("c314435661b0abc1")
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, 1) 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 for x and y
# x and y should have the same shape for the subtraction to work
# The function reshapes based on x.shape[0], so we need a batch dimension
# Using batch size 2 and feature dimension 4
x = torch.randn(2, 4)
y = torch.randn(2, 4)

ARGS = {
    "x": x,
    "y": y,
}
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, 1) — shape (2, 1) 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
weight_init Not yet run
unverified (harvested, no recorded run)
CVMI-Lab/PAConv/scene_seg/model/pointnet2/paconv.py
code served (permissive licence) · get_code("0db082ffd68d9baa")
How it ran

no invocation recorded.

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 5 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.

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

We introduce Position Adaptive Convolution (PAConv), a generic convolution operation for 3D point cloud processing. The key of PAConv is to construct the convolution kernel by dynamically assembling basic weight matrices stored in Weight Bank, where the coefficients of these weight matrices are self-adaptively learned from point positions through ScoreNet. In this way, the kernel is built in a data-driven manner, endowing PAConv with more flexibility than 2D convolutions to better handle the irregular and unordered point cloud data. Besides, the complexity of the learning process is reduced by combining weight matrices instead of brutally predicting kernels from point positions. Furthermore, different from the existing point convolution operators whose network architectures are often heavily engineered, we integrate our PAConv into classical MLP-based point cloud pipelines without changing network configurations. Even built on simple networks, our method still approaches or even surpasses the state-ofthe-art models, and significantly improves baseline performance on both classification and segmentation tasks, yet with decent efficiency. Thorough ablation studies and visualizations are provided to understand PAConv. Code is released on https://github.com/CVMI-Lab/PAConv.

For agents

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

get_harvested_code_for_paper("2103.14635")
get_code_for_paper("2103.14635")
have("2103.14635")

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

curl https://syntology.ai/api/ran/2103.14635.json

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

[![Syntology run record](https://syntology.ai/api/ran/2103.14635.svg)](https://syntology.ai/paper/2103.14635)

Connect an agent — have() is free.