SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2207.03111 · 2022

Masked Surfel Prediction for Self-Supervised Point Cloud Learning

arXiv · PDF · Open in the Atlas

Code that ran

8 of 8 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; 2 honoured the contract we drafted, 0 violated it and 5 have no contract verdict; 1 failure of our instrument; 0 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/2207.03111.json · badge: /api/ran/2207.03111.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
ybzh/masksurf canonical (classifier label)
classifier basis not recorded on the link
8 ran · 0 no recorded run
FunctionStatusWhere it lives
compute_ci95 Ran
ran, honoured the contract we drafted
ybzh/masksurf/parse_test_res.py
code served (permissive licence) · get_code("ba26afd892405335")
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 float64, ndim 0, 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

# compute_ci95 takes a single parameter 'res' which is used with:
# - np.std(res) - needs array-like
# - np.sqrt(len(res)) - needs len() to work
# A simple numpy array or list works perfectly

res = np.array([1.2, 2.3, 3.1, 4.5, 5.2, 6.1, 7.3, 8.9])

ARGS = {
    "res": res
}
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 float64, ndim 0, dtype family float — no output shape is stated: observe_signature.py recorded float ndim 0, which disagrees with the fixture run
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
farthest_point_sample Ran
ran; our contract draft was wrong, not the code
ybzh/masksurf/datasets/ModelNetDataset.py
pointer only (licence: MIT); the stored copy get_code serves, from Yuzhe-Fu/FlashFPS, is pointer only (licence: NOASSERTION) · get_code("f80066a00e7156a2")
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 Yuzhe-Fu/FlashFPS, and GitHub could not classify the licence of that repository (NOASSERTION). 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.

generate_surfel_mesh Ran
ran on a synthesized input
ybzh/masksurf/vis_masksurf.py
code served (permissive licence) · get_code("43ec5bfc69add751")
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
import math

torch.manual_seed(0)

# The function generate_surfel_mesh takes:
# - points: a tensor of shape (N, 3) containing 3D points
# - normals: a tensor of shape (N, 3) containing normal vectors

# Create small test tensors
# Using batch size 2, dimension 3 for both points and normals (they're 3D coordinates)
points = torch.randn(2, 3)
normals = torch.randn(2, 3)

ARGS = {
    "points": points,
    "normals": normals
}
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
map_taxonomy_to_label Ran
ran on a synthesized input
ybzh/masksurf/datasets/ShapeNet55DatasetClass.py
code served (permissive licence) · get_code("263bef2e90f8204e")
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 str. 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

class_dict = {'02691156': 'airplane', '02747177': 'trash bin', '02773838': 'bag', '02801938': 'basket', '02808440': 'bathtub', '02818832': 'bed', '02828884': 'bench', '02843684': 'birdhouse', '02871439': 'bookshelf', '02876657': 'bottle', '02880940': 'bowl', '02924116': 'bus', '02933112': 'cabinet', '02942699': 'camera', '02946921': 'can', '02954340': 'cap', '02958343': 'car', '02992529': 'cellphone', '03001627': 'chair', '03046257': 'clock', '03085013': 'keyboard', '03207941': 'dishwasher', '03211117': 'display', '03261776': 'earphone', '03325088': 'faucet', '03337140': 'file cabinet', '03467517': 'guitar', '03513137': 'helmet', '03593526': 'jar', '03624134': 'knife', '03636649': 'lamp', '03642806': 'laptop', '03691459': 'loudspeaker', '03710193': 'mailbox', '03759954': 'microphone', '03761084': 'microwaves', '03790512': 'motorbike', '03797390': 'mug', '03928116': 'piano', '03938244': 'pillow', '03948459': 'pistol', '03991062': 'flowerpot', '04004475': 'printer', '04074963': 'remote', '04090263': 'rifle', '04099429': 'rocket', '04225987': 'skateboard', '04256520': 'sofa', '04330267': 'stove', '04379243': 'table', '04401088': 'telephone', '04460130': 'tower', '04468005': 'train', '04530566': 'watercraft', '04554684': 'washer'}

def map_taxonomy_to_label(taxonomy):
    return class_dict[taxonomy]

ARGS = {
    'taxonomy': '02691156'
}
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 str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
mesh_normalize Ran
ran on a synthesized input
ybzh/masksurf/point2normal_curve.py
code served (permissive licence) · get_code("2de246840a64b9f4")
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 SimpleMesh. 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 numpy as np

class SimpleMesh:
    def __init__(self, vertices):
        self.vertices = vertices

# Create a simple mesh with vertices that need normalization
vertices = np.array([
    [0.0, 1.0, 2.0],
    [3.0, 4.0, 5.0],
    [1.5, 2.5, 3.5],
    [0.5, 1.5, 2.5]
], dtype=np.float32)

mesh = SimpleMesh(vertices)

ARGS = {
    "mesh": mesh
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type SimpleMesh — a SimpleMesh output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a SimpleMesh 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
pc_normalize Ran
ran, honoured the contract we drafted
ybzh/masksurf/datasets/ModelNetDataset.py
pointer only (licence: MIT); the stored copy get_code serves, from ajhamdi/MVTN, is pointer only (licence: NONE) · get_code("4783fbece52f500e")
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 ajhamdi/MVTN, 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.

rotation_vector_around_vector Ran
ran on a synthesized input
ybzh/masksurf/vis_masksurf.py
code served (permissive licence) · get_code("657783f7ef816fa7")
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 1, dtype family float, shape (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 rotates an input_vector around an anchor_vector by a rotation_degree angle
# It expects:
# - input_vector: a 3D vector (will be reshaped to 3x1)
# - anchor_vector: a 3D vector (the axis of rotation, should be normalized)
# - rotation_degree: a scalar (angle in radians)

input_vector = torch.tensor([1.0, 0.0, 0.0])

# Normalized anchor vector (axis of rotation)
anchor_vector = torch.tensor([0.0, 0.0, 1.0])

# Rotation angle in radians (45 degrees)
rotation_degree = torch.tensor(3.14159 / 4.0)

ARGS = {
    "input_vector": input_vector,
    "anchor_vector": anchor_vector,
    "rotation_degree": rotation_degree
}
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 1, dtype family float, shape (3,) — shape (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
tri_with_center_and_normal Ran
ran on a synthesized input
ybzh/masksurf/vis_masksurf.py
code served (permissive licence) · get_code("8047c6a3d9f63648")
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 2, 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 math

torch.manual_seed(0)

# Analyze the function tri_with_center_and_normal:
# - center: used with addition, should be a 1D tensor of shape (3,)
# - normal: used with .float(), torch.norm with dim=-1, torch.cross with dim=-1
#   When used in torch.cross with dim=-1, it needs to be compatible
#   Looking at the logic, normal appears to be a 1D tensor of shape (3,)
# - r: used with multiplication (*), should be a scalar

center = torch.tensor([1.0, 2.0, 3.0])
normal = torch.tensor([0.1, 0.2, 0.9])
r = 0.5

ARGS = {
    "center": center,
    "normal": normal,
    "r": r
}
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 2, 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

Also present in other papers' code

Of 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 3 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.

FunctionAlso present inEarliest-datedOthers named
pc_normalize 47 other papers
13 dated earlier, 34 later
1811.07246 (2018-11)
PointConv: Deep Convolutional Networks on 3D Point Clouds
1912.12098 (2019-12)
Quaternion Equivariant Capsule Networks for 3D Point Clouds
2003.00492 (2020-03)
PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Sampling
and 44 more not named here
farthest_point_sample 43 other papers
10 dated earlier, 33 later
1811.07246 (2018-11)
PointConv: Deep Convolutional Networks on 3D Point Clouds
2003.00492 (2020-03)
PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Sampling
2010.05272 (2020-10)
IF-Defense: 3D Adversarial Point Cloud Defense via Implicit Function based Restoration
and 40 more not named here
compute_ci95 37 other papers
3 dated earlier, 33 later, 1 undated
2106.00592 (2021-06)
Semi-Supervised Domain Generalization with Stochastic StyleMatch
2203.05557 (2022-03)
Conditional Prompt Learning for Vision-Language Models
2203.07740 (2022-03)
Exact Feature Distribution Matching for Arbitrary Style Transfer and Domain Generalization
and 34 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

Masked auto-encoding is a popular and effective self-supervised learning approach to point cloud learning. However, most of the existing methods reconstruct only the masked points and overlook the local geometry information, which is also important to understand the point cloud data. In this work, we make the first attempt, to the best of our knowledge, to consider the local geometry information explicitly into the masked auto-encoding, and propose a novel Masked Surfel Prediction (MaskSurf) method. Specifically, given the input point cloud masked at a high ratio, we learn a transformer-based encoder-decoder network to estimate the underlying masked surfels by simultaneously predicting the surfel positions (i.e., points) and per-surfel orientations (i.e., normals). The predictions of points and normals are supervised by the Chamfer Distance and a newly introduced Position-Indexed Normal Distance in a set-to-set manner. Our MaskSurf is validated on six downstream tasks under three fine-tuning strategies. In particular, MaskSurf outperforms its closest competitor, Point-MAE, by 1.2\% on the real-world dataset of ScanObjectNN under the OBJ-BG setting, justifying the advantages of masked surfel prediction over masked point cloud reconstruction. Codes will be available at https://github.com/YBZh/MaskSurf.

For agents

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

get_harvested_code_for_paper("2207.03111")
get_code_for_paper("2207.03111")
have("2207.03111")

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

curl https://syntology.ai/api/ran/2207.03111.json

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

[![Syntology run record](https://syntology.ai/api/ran/2207.03111.svg)](https://syntology.ai/paper/2207.03111)

Connect an agent — have() is free.