SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2407.19451 · ICLR · 2025

Perm: A Parametric Representation for Multi-Style 3D Hair Modeling

Yi Zhou, Chengan He, Holly Rushmeier, Xin Sun, Meng Zhang, Zhixin Shu, Sören Pirk, Fujun Luan, Jorge Amador Herrera, Dominik Michels, Tuanfeng Wang, Njust

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; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 3 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/2407.19451.json · badge: /api/ran/2407.19451.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
c-he/perm canonical (classifier label)
classifier basis: classifier_2025
3 ran · 1 no recorded run
copy not recorded community
not in the paper's declared repositories
1 ran · 0 no recorded run
FunctionStatusWhere it lives
blend Ran
ran; our contract draft was wrong, not the code
c-he/perm/src/models/strand_codec.py
code served (permissive licence) · get_code("73acdf58ce42ea61")
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, 3, 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 blend shape coefficients: (batch_size=2, num_blend_shapes=4)
coeff = torch.randn(2, 4)

# Create blend shapes basis: (num_blend_shapes=4, feature_dim=3, spatial_dim=5)
# Using distinct sizes to make dimensions unambiguous
basis = torch.randn(4, 3, 5)

ARGS = {
    "coeff": coeff,
    "basis": basis,
}
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, 3, 5) — shape (2, 3, 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
parse_comma_separated_list Ran
ran; our contract draft was wrong, not the code
this paper's copy was not recorded; identical code first harvested from nv-tlabs/GET3D
pointer only; the stored copy get_code serves, from nv-tlabs/GET3D, is pointer only (licence: NOASSERTION) · get_code("d01b68a634f71551")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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.

parse_range Ran
ran, honoured the contract we drafted
c-he/perm/src/gen_samples.py
code served (permissive licence) · get_code("cf174a2982be5a1e")
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 list, ndim 1, dtype family int; 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 re
from typing import List, Union

def parse_range(s: Union[str, List]) -> List[int]:
    """Parse a comma separated list of numbers or ranges and return a list of ints.

    Example: '1,2,5-10' returns [1, 2, 5, 6, 7]
    """
    if isinstance(s, list):
        return s
    ranges = []
    range_re = re.compile('^(\\d+)-(\\d+)$')
    for p in s.split(','):
        if (m := range_re.match(p)):
            ranges.extend(range(int(m.group(1)), int(m.group(2)) + 1))
        else:
            ranges.append(int(p))
    return ranges


# Test case 1: string input with ranges and individual numbers
ARGS = {
    "s": "1,2,5-10"
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, dtype family int — a list 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
project Ran
ran; our contract draft was wrong, not the code
c-he/perm/src/models/strand_codec.py
code served (permissive licence) · get_code("8000b097a46cc6b8")
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 2, dtype family float, shape (2, 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 tensors with distinct dimensions
# data: (batch_size=2, feature_dim=4) - represents hair data
data = torch.randn(2, 4)

# basis: (num_blend_shapes=3, feature_dim=4) - represents blend shapes
basis = torch.randn(3, 4)

ARGS = {
    "data": data,
    "basis": basis,
}
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 2, dtype family float, shape (2, 3) — shape (2, 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
StrandCodec Not yet run
unverified (harvested, no recorded run)
c-he/perm/src/models/strand_codec.py
code served (permissive licence) · get_code("43ed06aa4202f64a")
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, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 1 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.

FunctionAlso present inEarliest-datedOthers named
parse_comma_separated_list 13 other papers
11 dated earlier, 2 later
2112.07945 (2021-12)
Efficient Geometry-aware 3D Generative Adversarial Networks
2202.00273 (2022-02)
StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasets
2206.07695 (2022-06)
VoxGRAF: Fast 3D-Aware Image Synthesis with Sparse Voxel Grids
and 10 more not named here
parse_range 3 other papers
3 dated earlier
2112.07945 (2021-12)
Efficient Geometry-aware 3D Generative Adversarial Networks
2311.17857 (2023-11)
Gaussian Shell Maps for Efficient 3D Human Generation
2404.10394 (2024-04)
Portrait3D: Text-Guided High-Quality 3D Portrait Generation Using Pyramid Representation and GANs Prior

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 present PERM, a learned parametric representation of 3D human hair designed to facilitate various hair-related applications. Unlike previous work that jointly models the global hair structure and local curl patterns, we propose to disentangle them using a PCA-based strand representation in the frequency domain, thereby allowing more precise editing and output control. Specifically, we leverage our strand representation to fit and decompose hair geometry textures into low-to high-frequency hair structures, termed guide textures and residual textures, respectively. These decomposed textures are later parameterized with different generative models, emulating common stages in the hair grooming process. We conduct extensive experiments to validate the architecture design of PERM, and finally deploy the trained model as a generic prior to solve task-agnostic problems, further showcasing its flexibility and superiority in tasks such as single-view hair reconstruction, hairstyle editing, and hair-conditioned image generation. More details can be found on our project page: https: //cs.yale.edu/homes/che/projects/perm/.

For agents

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

get_harvested_code_for_paper("2407.19451")
get_code_for_paper("2407.19451")
have("2407.19451")

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

curl https://syntology.ai/api/ran/2407.19451.json

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

[![Syntology run record](https://syntology.ai/api/ran/2407.19451.svg)](https://syntology.ai/paper/2407.19451)

Connect an agent — have() is free.