SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2102.01929 · CVPR · 2021

Regularization Strategy for Point Cloud via Rigidly Mixed Sample

Sangyoun Lee, Hyeongmin Lee, Sungmin Woo, Minhyeok Lee, Dogyoon Lee, Jaeha Lee, Junhyeop Lee

arXiv · PDF · Open in the Atlas

Code that ran

2 of 3 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, 1 violated it and 0 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/2102.01929.json · badge: /api/ran/2102.01929.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
dogyoonlee/RSMix-official marked official in Papers with Code
Papers with Code archive
2 ran · 1 no recorded run
FunctionStatusWhere it lives
pts_num_ctrl Ran
ran, violated the contract we drafted
dogyoonlee/RSMix-official/pointnet2_rsmix/utils/rsmix_provider.py
code served (permissive licence) · get_code("18f6f2d15db91be7")
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 1, dtype family int, shape (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 numpy as np

# Set random seed for reproducibility
np.random.seed(0)

# Create sample index arrays
# pts_erase_idx: indices of points to erase
pts_erase_idx = np.array([0, 5, 10, 15, 20])

# pts_add_idx: indices of points to add
pts_add_idx = np.array([1, 3, 7, 9])

ARGS = {
    "pts_erase_idx": pts_erase_idx,
    "pts_add_idx": pts_add_idx,
}
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 1, dtype family int, shape (5,) — shape (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
rsmix Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
dogyoonlee/RSMix-official/pointnet2_rsmix/utils/rsmix_provider.py
code served (permissive licence) · get_code("6257fa3a790376c2")
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

# The function rsmix expects:
# - data_batch: numpy array of shape (B, N, C) containing point cloud data
# - label_batch: numpy array of shape (B,) or (B, 1) containing labels
# - beta: float parameter (default 1.0)
# - n_sample: int parameter (default 512, but will be overridden)

# Create small dummy data
B = 2  # batch size
N = 8  # number of points
C = 6  # channels (3 for xyz + 3 for normals)

# data_batch: (B, N, C) - batch of point clouds
data_batch = np.random.randn(B, N, C).astype(np.float32)

# label_batch: (B,) - batch of labels
label_batch = np.array([0, 1], dtype=np.int32)

# beta: controls the mixing ratio
beta = 1.0

# n_sample: number of samples (will be overridden to N//2 inside the function)
n_sample = 512

# Note: The function cut_points calls query_ball_point_for_point_mix which is not defined
# We need to mock it. Looking at the code, query_ball_point_for_point_mix is called with:
# (radius, nsample, data_batch[:, :, :3], query_points[:, :, :3])
# and should return group_idx of shape (B, nsample) or similar

# Create a mock for the missing function
def query_ball_point_for_point_mix(radius, nsample, xyz, query_points):
    """Mock function that returns indices of sampled points"""
    B = xyz.shape[0]
    # Return random indices (capped at N to avoid out of bounds)
    return np.random.randint(0, xyz.shape[1], size=(B, 1, nsample))

# Inject the mock into the module namespace where it will be called
import sys
current_module = sys.modules[__name__]
setattr(current_module, 'query_ball_point_for_point_mix', query_ball_point_for_point_mix)

ARGS = {
    "data_batch": data_batch,
    "label_batch": label_batch,
    "beta": beta,
    "n_sample": n_sample,
}
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 — 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
cut_points Not yet run
unverified (harvested, no recorded run)
dogyoonlee/RSMix-official/pointnet2_rsmix/utils/rsmix_provider.py
code served (permissive licence) · get_code("d7dd1c63c66ebefa")
How it ran

no invocation recorded.

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 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 3 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

Data augmentation is an effective regularization strategy to alleviate the overfitting, which is an inherent drawback of the deep neural networks. However, data augmentation is rarely considered for point cloud processing despite many studies proposing various augmentation methods for image data. Actually, regularization is essential for point clouds since lack of generality is more likely to occur in point cloud due to small datasets. This paper proposes a Rigid Subset Mix (RSMix) 1 , a novel data augmentation method for point clouds that generates a virtual mixed sample by replacing part of the sample with shape-preserved subsets from another sample. RSMix preserves structural information of the point cloud sample by extracting subsets from each sample without deformation using a neighboring function. The neighboring function was carefully designed considering unique properties of point cloud, unordered structure and non-grid. Experiments verified that RSMix successfully regularized the deep neural networks with remarkable improvement for shape classification. We also analyzed various combinations of data augmentations including RSMix with single and multi-view evaluations, based on abundant ablation studies.

For agents

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

get_harvested_code_for_paper("2102.01929")
get_code_for_paper("2102.01929")
have("2102.01929")

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

curl https://syntology.ai/api/ran/2102.01929.json

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

[![Syntology run record](https://syntology.ai/api/ran/2102.01929.svg)](https://syntology.ai/paper/2102.01929)

Connect an agent — have() is free.