SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2005.11084 · 2020

Point2Mesh: A Self-Prior for Deformable Meshes

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 (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 4 have no contract verdict; 0 failures 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/2005.11084.json · badge: /api/ran/2005.11084.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
ranahanocka/point2mesh canonical (classifier label)
classifier basis: census
4 ran · 1 no recorded run
FunctionStatusWhere it lives
load_obj Ran
ran on a synthesized input
ranahanocka/point2mesh/utils.py
code served (permissive licence) · get_code("ddbbf8d93d62ffc9")
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
import tempfile
import os

# Create a temporary OBJ file with valid content
temp_dir = tempfile.mkdtemp()
obj_file = os.path.join(temp_dir, "test.obj")

with open(obj_file, 'w') as f:
    f.write("# Simple triangle mesh\n")
    f.write("v 0.0 0.0 0.0\n")
    f.write("v 1.0 0.0 0.0\n")
    f.write("v 0.0 1.0 0.0\n")
    f.write("v 0.0 0.0 1.0\n")
    f.write("f 1 2 3\n")
    f.write("f 2 3 4\n")

ARGS = {
    "file": obj_file
}
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
local_nonuniform_penalty Ran
ran on a synthesized input
ranahanocka/point2mesh/models/networks.py
code served (permissive licence) · get_code("e3721020ab0b2569")
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 0, dtype family float, shape () 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)

class Mesh:
    def __init__(self):
        # vs: vertices tensor, shape [num_vertices, 3]
        self.vs = torch.randn(5, 3)
        
        # faces: face indices, shape [num_faces, 3]
        self.faces = torch.tensor([
            [0, 1, 2],
            [1, 2, 3],
            [2, 3, 4],
            [0, 2, 4]
        ], dtype=torch.long)
        
        # gfmm: group face mesh matrix, shape [num_faces, num_neighbors]
        # Used to index into area array: area[mesh.gfmm]
        # area has shape [num_faces], so gfmm should have shape [num_faces, k]
        # where each row contains valid indices into the area array
        self.gfmm = torch.tensor([
            [0, 1, 2],
            [1, 2, 3],
            [2, 3, 0],
            [3, 0, 1]
        ], dtype=torch.long)

mesh = Mesh()

ARGS = {
    "mesh": mesh
}
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 0, dtype family float, shape () — shape () 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
populate_e Ran
ran on a synthesized input
ranahanocka/point2mesh/models/networks.py
code served (permissive licence) · get_code("e0246954339b69df")
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, 6, 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)

class SimpleMesh:
    def __init__(self, num_vertices=4, num_edges=6):
        self.vs = torch.rand(num_vertices, 3)
        self.edges = torch.tensor([
            [0, 1],
            [1, 2],
            [2, 3],
            [3, 0],
            [0, 2],
            [1, 3]
        ], dtype=torch.long)
        self.edges_count = num_edges

mesh = SimpleMesh(num_vertices=4, num_edges=6)
meshes = [mesh, mesh]

ARGS = {
    "meshes": meshes,
    "verts": None
}
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, 6, 6) — shape (2, 6, 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
read_pts Ran
ran on a synthesized input
ranahanocka/point2mesh/utils.py
code served (permissive licence) · get_code("1abb87311101e28f")
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 numpy as np
import tempfile
import os

# Create a temporary file with point cloud data
temp_file = tempfile.NamedTemporaryFile(mode='w', delete=False, suffix='.xyz')
try:
    # Write 5 points with x, y, z, nx, ny, nz format
    temp_file.write("0.1 0.2 0.3 1.0 0.0 0.0\n")
    temp_file.write("0.4 0.5 0.6 0.0 1.0 0.0\n")
    temp_file.write("0.7 0.8 0.9 0.0 0.0 1.0\n")
    temp_file.write("1.0 1.1 1.2 0.5 0.5 0.0\n")
    temp_file.write("1.3 1.4 1.5 0.0 0.5 0.5\n")
    temp_file.flush()
    pts_file_path = temp_file.name
finally:
    temp_file.close()

ARGS = {
    'pts_file': pts_file_path
}
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, 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
build_v Not yet run
unverified (harvested, no recorded run)
ranahanocka/point2mesh/models/networks.py
code served (permissive licence) · get_code("45983641cf8ad1b2")
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

In this paper, we introduce Point2Mesh, a technique for reconstructing a surface mesh from an input point cloud. Instead of explicitly specifying a prior that encodes the expected shape properties, the prior is defined automatically using the input point cloud, which we refer to as a self-prior. The self-prior encapsulates reoccurring geometric repetitions from a single shape within the weights of a deep neural network. We optimize the network weights to deform an initial mesh to shrink-wrap a single input point cloud. This explicitly considers the entire reconstructed shape, since shared local kernels are calculated to fit the overall object. The convolutional kernels are optimized globally across the entire shape, which inherently encourages local-scale geometric self-similarity across the shape surface. We show that shrink-wrapping a point cloud with a self-prior converges to a desirable solution; compared to a prescribed smoothness prior, which often becomes trapped in undesirable local minima. While the performance of traditional reconstruction approaches degrades in non-ideal conditions that are often present in real world scanning, i.e., unoriented normals, noise and missing (low density) parts, Point2Mesh is robust to non-ideal conditions. We demonstrate the performance of Point2Mesh on a large variety of shapes with varying complexity.

For agents

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

get_harvested_code_for_paper("2005.11084")
get_code_for_paper("2005.11084")
have("2005.11084")

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

curl https://syntology.ai/api/ran/2005.11084.json

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

[![Syntology run record](https://syntology.ai/api/ran/2005.11084.svg)](https://syntology.ai/paper/2005.11084)

Connect an agent — have() is free.