SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2211.11208 · 2022

Next3D: Generative Neural Texture Rasterization for 3D-Aware Head Avatars

arXiv · PDF · Open in the Atlas

Code that ran

16 of 21 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, 1 violated it and 7 have no contract verdict; 6 failures of our instrument; 5 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/2211.11208.json · badge: /api/ran/2211.11208.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
MrTornado24/FENeRF canonical (classifier label)
classifier basis not recorded on the link
11 ran · 5 no recorded run
mrtornado24/next3d canonical (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
copy not recorded community
not in the paper's declared repositories
3 ran · 0 no recorded run
FunctionStatusWhere it lives
conv3x3 Ran
ran; our contract draft was wrong, not the code
MrTornado24/FENeRF/generators/encoder_model.py
code served (permissive licence) · get_code("dbcb53696bc43ef9")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned Conv2d. 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 torch.nn as nn

torch.manual_seed(0)

# The function conv3x3 creates a Conv2d layer
# Parameters:
# - in_planes: number of input channels (int)
# - out_planes: number of output channels (int)
# - stride: stride for convolution (int, default=1)
# - has_bias: whether to use bias (bool, default=False)

ARGS = {
    'in_planes': 3,
    'out_planes': 8,
    'stride': 2,
    'has_bias': True
}
Setup block drafted by
a language model, Claude Sonnet 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 Conv2d — a Conv2d output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Conv2d 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
conv3x3_bn_relu Ran
ran; our contract draft was wrong, not the code
MrTornado24/FENeRF/generators/encoder_model.py
pointer only (licence: MIT); the stored copy get_code serves, from ZhengyaoFang/WeCromCL, is pointer only (licence: NONE) · get_code("fca7e85d958618dd")
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 ZhengyaoFang/WeCromCL, 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.

create_samples Ran
ran; our contract draft was wrong, not the code
this paper's copy was not recorded; identical code first harvested from sizhean/panohead
pointer only · get_code("eae3d419e3bac1bb")
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.

create_samples Ran
ran; our contract draft was wrong, not the code
MrTornado24/FENeRF/extract_double_semantic_shapes.py
code served (permissive licence) · get_code("306b4b17e95e50e5")
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 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, 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 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
get_current_step Ran
ran on a synthesized input
MrTornado24/FENeRF/curriculums.py
code served (permissive licence) · get_code("a551faf28fc86a9f")
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 int, ndim 0, dtype family int, 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)

ARGS = {
    'curriculum': {
        'update_epochs': [0, 5, 10, 15]
    },
    'epoch': 7
}
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 int, ndim 0, dtype family int, 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
last_upsample_step Ran
ran on a synthesized input
MrTornado24/FENeRF/curriculums.py
code served (permissive licence) · get_code("31312e8e88c4d95c")
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 int, ndim 0, dtype family int, 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

# Construct a curriculum dict with integer keys and metadata
curriculum = {
    0: {
        'img_size': 64,
        'learning_rate': 0.001,
    },
    10: {
        'img_size': 128,
        'learning_rate': 0.0005,
    },
    20: {
        'img_size': 256,
        'learning_rate': 0.0001,
    },
    'constant_param': 'some_value',
    'another_constant': 42,
}

current_step = 15

ARGS = {
    'curriculum': curriculum,
    'current_step': current_step,
}
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 int, ndim 0, dtype family int, 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
layout_grid Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
this paper's copy was not recorded; identical code first harvested from sizhean/panohead
pointer only · get_code("456c172851946697")
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.

make_kernel Ran
ran, violated the contract we drafted
MrTornado24/FENeRF/generators/networks.py
pointer only (licence: MIT); the stored copy get_code serves, from dkn16/multi-fidel-gan-21cm, is pointer only (licence: NOASSERTION) · get_code("6f65e378a4313f87")
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 dkn16/multi-fidel-gan-21cm, 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.

mask2color Ran
ran on a synthesized input
MrTornado24/FENeRF/fid_evaluation.py
code served (permissive licence) · get_code("fb2d4af592689be4")
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 4, dtype family float, shape (2, 3, 4, 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 expects masks to be a tensor that:
# 1. Has at least 2 dimensions (uses argmax on dim=1)
# 2. Will be converted to float after argmax
# 3. Should have shape (batch, num_classes, height, width) based on the argmax(dim=1) operation
# 4. Values should be class indices that match keys in COLOR_MAP (0-18)

# Create a small masks tensor: batch_size=2, num_classes=19, height=4, width=3
masks = torch.randint(0, 19, (2, 19, 4, 3), dtype=torch.long).float()

ARGS = {
    "masks": masks
}
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 4, dtype family float, shape (2, 3, 4, 3) — shape (2, 3, 4, 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
next_upsample_step Ran
ran on a synthesized input
MrTornado24/FENeRF/curriculums.py
code served (permissive licence) · get_code("738ade559b76771c")
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 int, ndim 0, dtype family int, 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

# Construct a curriculum dictionary that the function expects
curriculum = {
    # Integer keys represent curriculum steps with metadata
    0: {
        'img_size': 64,
        'other_param': 'value0'
    },
    10: {
        'img_size': 128,
        'other_param': 'value10'
    },
    20: {
        'img_size': 256,
        'other_param': 'value20'
    },
    30: {
        'img_size': 512,
        'other_param': 'value30'
    },
    # Non-integer keys are global metadata
    'global_setting': 'shared_value',
    'model_type': 'test_model'
}

# current_step should be an integer representing the current training step
current_step = 15

ARGS = {
    'curriculum': curriculum,
    'current_step': current_step
}
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 int, ndim 0, dtype family int, 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
noise_regularize Ran
ran on a synthesized input
MrTornado24/FENeRF/generators/losses.py
code served (permissive licence) · get_code("f307b6ca92d07582")
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)

# The function expects 'noises' to be a list of tensors
# Each tensor should have shape [batch_size, channels, height, width]
# The function uses:
# - noises[0].shape[0] to get batch_size
# - noise.shape[2] to get size (height dimension)
# - torch.roll operations on dims 2 and 3
# - reshape and mean operations

batch_size = 2
num_noises = 3

# Create a list of noise tensors with shape [batch_size, 1, size, size]
# Using size=16 so it can be repeatedly halved down to 8
noises = [
    torch.randn(batch_size, 1, 16, 16),
    torch.randn(batch_size, 1, 16, 16),
    torch.randn(batch_size, 1, 16, 16),
]

ARGS = {
    "noises": noises,
}
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
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
mrtornado24/next3d/gen_videos_next3d.py
pointer only (licence: NONE) · get_code("0cb0302229a63afb")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, mrtornado24/next3d 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.

parse_tuple Ran
ran, honoured the contract we drafted
mrtornado24/next3d/reenact_avatar_next3d.py
pointer only (licence: NONE) · get_code("15bdf97a9d941e33")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, mrtornado24/next3d 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.

sample_generator Ran
ran on a synthesized input
MrTornado24/FENeRF/extract_shapes.py
code served (permissive licence) · get_code("5eb31a5a13c399e0")
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 3, dtype family float, shape (4, 4, 4) 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
import torch.nn as nn
import numpy as np

torch.manual_seed(0)

class SimpleMapping(nn.Module):
    def __init__(self, z_dim=4, freq_dim=3):
        super().__init__()
        self.z_dim = z_dim
        self.freq_dim = freq_dim
        self.linear = nn.Linear(z_dim, freq_dim * 2)
    
    def forward(self, z):
        x = self.linear(z)
        return x[:, :self.freq_dim], x[:, self.freq_dim:]

class SimpleSiren(nn.Module):
    def __init__(self):
        super().__init__()
        self.mapping_network = SimpleMapping(z_dim=4, freq_dim=3)
        self.linear = nn.Linear(3, 4)
    
    def forward_with_frequencies_phase_shifts(self, samples, frequencies, phase_shifts, ray_directions=None):
        batch_size = samples.shape[0]
        num_samples = samples.shape[1]
        output = self.linear(samples.reshape(-1, 3))
        output = output.reshape(batch_size, num_samples, 4)
        return output

class SimpleGenerator(nn.Module):
    def __init__(self):
        super().__init__()
        self.siren = SimpleSiren()
    
    def generate_avg_frequencies(self):
        pass

generator = SimpleGenerator()
z = torch.randn(2, 4)

ARGS = {
    "generator": generator,
    "z": z,
    "max_batch": 100000,
    "voxel_resolution": 4,
    "voxel_origin": [0, 0, 0],
    "cube_length": 2.0,
    "psi": 0.5
}
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 ndarray, ndim 3, dtype family float, shape (4, 4, 4) — shape (4, 4, 4) 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
sample_generator_wth_frequencies_phase_shifts Ran
ran on a synthesized input
MrTornado24/FENeRF/extract_double_semantic_shapes.py
code served (permissive licence) · get_code("dedcc2eab15ec9cb")
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 3, dtype family float, shape (4, 4, 4) 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
import torch.nn as nn
import numpy as np

torch.manual_seed(0)

class SirenNet(nn.Module):
    def __init__(self, input_dim=3, output_dim=22):
        super().__init__()
        self.fc1 = nn.Linear(input_dim, 8)
        self.fc2 = nn.Linear(8, output_dim)
    
    def forward_with_frequencies_phase_shifts(self, samples, truncated_frequencies_geo, truncated_frequencies_app, truncated_phase_shifts_geo, truncated_phase_shifts_app, ray_directions=None):
        batch_size = samples.shape[0]
        seq_len = samples.shape[1]
        # Simple forward pass that returns (batch, seq_len, N_CHANNELS)
        x = self.fc1(samples)
        x = torch.relu(x)
        x = self.fc2(x)
        return x

class Generator(nn.Module):
    def __init__(self):
        super().__init__()
        self.siren = SirenNet(input_dim=3, output_dim=22)
        self.device = torch.device('cpu')
    
    def to(self, device):
        self.device = device
        return super().to(device)

generator = Generator()
generator.device = torch.device('cpu')

meta = {
    'truncated_frequencies_geo': torch.randn(4, 3),
    'truncated_frequencies_app': torch.randn(4, 3),
    'truncated_phase_shifts_geo': torch.randn(4),
    'truncated_phase_shifts_app': torch.randn(4),
}

ARGS = {
    'generator': generator,
    'meta': meta,
    'max_batch': 100000,
    'voxel_resolution': 4,
    'voxel_origin': [0, 0, 0],
    'cube_length': 2.0,
    'psi': 0.5,
}
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 ndarray, ndim 3, dtype family float, shape (4, 4, 4) — shape (4, 4, 4) 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
get_cls_loss Not yet run
unverified (harvested, no recorded run)
MrTornado24/FENeRF/losses.py
code served (permissive licence) · get_code("6dadb6b73a1b7906")
How it ran

no invocation recorded.

get_dataset Not yet run
unverified (harvested, no recorded run)
MrTornado24/FENeRF/datasets.py
code served (permissive licence) · get_code("df709247c665b337")
How it ran

no invocation recorded.

get_dataset_distributed Not yet run
unverified (harvested, no recorded run)
MrTornado24/FENeRF/datasets.py
code served (permissive licence) · get_code("99cf38950bfe4017")
How it ran

no invocation recorded.

sample_generator Not yet run
unverified (harvested, no recorded run)
MrTornado24/FENeRF/extract_double_semantic_shapes.py
code served (permissive licence) · get_code("669cd994f61f01b0")
How it ran

no invocation recorded.

setup_evaluation Not yet run
unverified (harvested, no recorded run)
MrTornado24/FENeRF/fid_evaluation.py
code served (permissive licence) · get_code("e20918a25fe4c6c6")
How it ran

no invocation recorded.

Also present in other papers' code

Of 21 samples lifted from this paper's linked repositories, 21 carry a function identity and 0 do not. Of the 20 distinct functions with an identity, 13 are also present in other papers whose code we hold (11 with at least one paper dated earlier, 1 the same month, 8 later) and 7 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
make_kernel 40 other papers
29 dated earlier, 1 the same month, 10 later · 10 only as an assembly brick
1812.04948 (2018-12)
A Style-Based Generator Architecture for Generative Adversarial Networks
1912.04958 (2019-12)
Analyzing and Improving the Image Quality of StyleGAN
2007.06600 (2020-07)
Closed-Form Factorization of Latent Semantics in GANs
and 37 more not named here
parse_comma_separated_list 13 other papers
4 dated earlier, 9 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
conv3x3 7 other papers
6 dated earlier, 1 later
1804.08864 (2018-04)
Learning to See the Invisible: End-to-End Trainable Amodal Instance Segmentation
1807.10221 (2018-07)
Unified Perceptual Parsing for Scene Understanding
1807.11590 (2018-07)
Acquisition of Localization Confidence for Accurate Object Detection
and 4 more not named here
layout_grid 6 other papers
1 dated earlier, 5 later
2202.00273 (2022-02)
StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasets
2303.13071 (2023-03)
PanoHead: Geometry-Aware 3D Full-Head Synthesis in 360$^{\circ}$
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
3 dated earlier, 2 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
conv3x3_bn_relu 3 other papers
2 dated earlier, 1 later
1810.04650 (2018-10)
Multi-Task Learning as Multi-Objective Optimization
2206.01934 (2022-06)
Stochastic Multiple Target Sampling Gradient Descent
2407.19507 (2024-07)
WeCromCL: Weakly Supervised Cross-Modality Contrastive Learning for Transcription-only Supervised Text Spotting
get_current_step 3 other papers
3 dated earlier
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
last_upsample_step 3 other papers
3 dated earlier
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
next_upsample_step 3 other papers
3 dated earlier
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
get_dataset 1 other paper
1 dated earlier
2110.15678 (2021-10)
A Shading-Guided Generative Implicit Model for Shape-Accurate 3D-Aware Image Synthesis
get_dataset_distributed 1 other paper
1 dated earlier
2110.15678 (2021-10)
A Shading-Guided Generative Implicit Model for Shape-Accurate 3D-Aware Image Synthesis
parse_range 1 other paper
1 later
2406.02968 (2024-06)
GSGAN: Adversarial Learning for Hierarchical Generation of 3D Gaussian Splats
parse_tuple 1 other paper
1 later
2406.02968 (2024-06)
GSGAN: Adversarial Learning for Hierarchical Generation of 3D Gaussian Splats

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

3D-aware generative adversarial networks (GANs) synthesize high-fidelity and multi-view-consistent facial images using only collections of single-view 2D imagery. Towards fine-grained control over facial attributes, recent efforts incorporate 3D Morphable Face Model (3DMM) to describe deformation in generative radiance fields either explicitly or implicitly. Explicit methods provide fine-grained expression control but cannot handle topological changes caused by hair and accessories, while implicit ones can model varied topologies but have limited generalization caused by the unconstrained deformation fields. We propose a novel 3D GAN framework for unsupervised learning of generative, high-quality and 3D-consistent facial avatars from unstructured 2D images. To achieve both deformation accuracy and topological flexibility, we propose a 3D representation called Generative Texture-Rasterized Tri-planes. The proposed representation learns Generative Neural Textures on top of parametric mesh templates and then projects them into three orthogonal-viewed feature planes through rasterization, forming a tri-plane feature representation for volume rendering. In this way, we combine both fine-grained expression control of mesh-guided explicit deformation and the flexibility of implicit volumetric representation. We further propose specific modules for modeling mouth interior which is not taken into account by 3DMM. Our method demonstrates state-of-the-art 3D-aware synthesis quality and animation ability through extensive experiments. Furthermore, serving as 3D prior, our animatable 3D representation boosts multiple applications including one-shot facial avatars and 3D-aware stylization.

For agents

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

get_harvested_code_for_paper("2211.11208")
get_code_for_paper("2211.11208")
have("2211.11208")

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

curl https://syntology.ai/api/ran/2211.11208.json

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

[![Syntology run record](https://syntology.ai/api/ran/2211.11208.svg)](https://syntology.ai/paper/2211.11208)

Connect an agent — have() is free.