SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2303.13071 · 2023

PanoHead: Geometry-Aware 3D Full-Head Synthesis in 360$^{\circ}$

arXiv · PDF · Open in the Atlas

Code that ran

6 of 6 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; 3 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 3 failures 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/2303.13071.json · badge: /api/ran/2303.13071.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
sizhean/panohead canonical (classifier label)
classifier basis: classifier_2025
6 ran · 0 no recorded run
FunctionStatusWhere it lives
create_samples Ran
ran; our contract draft was wrong, not the code
sizhean/panohead/gen_videos.py
code served (permissive licence) · get_code("eae3d419e3bac1bb")
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 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 numpy as np

torch.manual_seed(0)

ARGS = {
    "N": 4,
    "voxel_origin": [0, 0, 0],
    "cube_length": 2.0,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy, 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
layout_grid Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
sizhean/panohead/gen_videos.py
code served (permissive licence) · get_code("456c172851946697")
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 ndarray, ndim 3, dtype family int, shape (4, 10, 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 a small batch of images
# batch_size=2, channels=3, height=4, width=5
img = torch.randn(2, 3, 4, 5)

# Normalize to roughly [-1, 1] range for float_to_uint8 conversion
img = img / 10.0

ARGS = {
    "img": img,
    "grid_w": None,
    "grid_h": 1,
    "float_to_uint8": True,
    "chw_to_hwc": True,
    "to_numpy": True,
}
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 ndarray, ndim 3, dtype family int, shape (4, 10, 3) — shape (4, 10, 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
make_transform Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
sizhean/panohead/gen_samples.py
code served (permissive licence) · get_code("f47dff4b7b27bba7")
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 ndarray, ndim 2, dtype family float, shape (3, 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 numpy as np

ARGS = {
    "translate": (1.5, 2.5),
    "angle": 45.0
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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 2, dtype family float, shape (3, 3) — shape (3, 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
parse_range Ran
ran, honoured the contract we drafted
sizhean/panohead/gen_samples.py
code served (permissive licence) · get_code("236de8614a178382")
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, Optional, Tuple, 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(','):
        m = range_re.match(p)
        if m:
            ranges.extend(range(int(m.group(1)), int(m.group(2)) + 1))
        else:
            ranges.append(int(p))
    return ranges


# Test case 1: string 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
parse_range Ran
ran, honoured the contract we drafted
sizhean/panohead/gen_videos.py
code served (permissive licence) · get_code("025e4c7cda618f25")
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, Optional, Tuple, Union

def parse_range(s: Union[str, List[int]]) -> 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(','):
        m = range_re.match(p)
        if m:
            ranges.extend(range(int(m.group(1)), int(m.group(2)) + 1))
        else:
            ranges.append(int(p))
    return ranges


# Test with string input
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
parse_vec2 Ran
ran, honoured the contract we drafted
sizhean/panohead/gen_samples.py
code served (permissive licence) · get_code("180016b9227381b1")
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 tuple, ndim 1, 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 numpy as np
from typing import Union, Tuple

torch.manual_seed(0)

# The function parse_vec2 takes a single parameter 's' which can be either:
# - a string in format 'a,b' (e.g., '0,1')
# - a tuple of two floats (e.g., (0.0, 1.0))
# 
# The function either returns the tuple directly if input is tuple,
# or parses the string and returns a tuple of floats.

# Test case 1: string input
test_string = "0.5,1.5"

# Test case 2: tuple input
test_tuple = (2.0, 3.5)

# We'll use the string case as the primary test
ARGS = {
    "s": "0.5,1.5"
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 1, 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 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 6 are also present in other papers whose code we hold (6 with at least one paper dated earlier, 0 the same month, 6 later) and 0 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_vec2 11 other papers
5 dated earlier, 6 later
2106.12423 (2021-06)
Alias-Free Generative Adversarial Networks
2112.07945 (2021-12)
Efficient Geometry-aware 3D Generative Adversarial Networks
2202.00273 (2022-02)
StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasets
and 8 more not named here
parse_range 9 other papers
4 dated earlier, 5 later
2106.12423 (2021-06)
Alias-Free 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 6 more not named here
make_transform 8 other papers
3 dated earlier, 5 later
2106.12423 (2021-06)
Alias-Free Generative Adversarial Networks
2112.07945 (2021-12)
Efficient Geometry-aware 3D Generative Adversarial Networks
2202.00273 (2022-02)
StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasets
and 5 more not named here
layout_grid 6 other papers
2 dated earlier, 4 later
2202.00273 (2022-02)
StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasets
2211.11208 (2022-11)
Next3D: Generative Neural Texture Rasterization for 3D-Aware Head Avatars
2306.04675 (2023-06)
Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion models
and 3 more not named here
create_samples 5 other papers
4 dated earlier, 1 later
2110.09788 (2021-10)
CIPS-3D: A 3D-Aware Generator of GANs Based on Conditionally-Independent Pixel Synthesis
2110.15678 (2021-10)
A Shading-Guided Generative Implicit Model for Shape-Accurate 3D-Aware Image Synthesis
2111.00969 (2021-11)
Generative Occupancy Fields for 3D Surface-Aware Image Synthesis
and 2 more not named here
parse_range 3 other papers
1 dated earlier, 2 later
2202.00273 (2022-02)
StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasets
2306.04675 (2023-06)
Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion models
2502.06349 (2025-02)
Provably Near-Optimal Federated Ensemble Distillation with Negligible Overhead

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

Synthesis and reconstruction of 3D human head has gained increasing interests in computer vision and computer graphics recently. Existing state-of-the-art 3D generative adversarial networks (GANs) for 3D human head synthesis are either limited to near-frontal views or hard to preserve 3D consistency in large view angles. We propose PanoHead, the first 3D-aware generative model that enables high-quality view-consistent image synthesis of full heads in $360^\circ$ with diverse appearance and detailed geometry using only in-the-wild unstructured images for training. At its core, we lift up the representation power of recent 3D GANs and bridge the data alignment gap when training from in-the-wild images with widely distributed views. Specifically, we propose a novel two-stage self-adaptive image alignment for robust 3D GAN training. We further introduce a tri-grid neural volume representation that effectively addresses front-face and back-head feature entanglement rooted in the widely-adopted tri-plane formulation. Our method instills prior knowledge of 2D image segmentation in adversarial learning of 3D neural scene structures, enabling compositable head synthesis in diverse backgrounds. Benefiting from these designs, our method significantly outperforms previous 3D GANs, generating high-quality 3D heads with accurate geometry and diverse appearances, even with long wavy and afro hairstyles, renderable from arbitrary poses. Furthermore, we show that our system can reconstruct full 3D heads from single input images for personalized realistic 3D avatars.

For agents

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

get_harvested_code_for_paper("2303.13071")
get_code_for_paper("2303.13071")
have("2303.13071")

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

curl https://syntology.ai/api/ran/2303.13071.json

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

[![Syntology run record](https://syntology.ai/api/ran/2303.13071.svg)](https://syntology.ai/paper/2303.13071)

Connect an agent — have() is free.