SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2303.13873 · ICCV · 2023

Fantasia3D: Disentangling Geometry and Appearance for High-quality Text-to-3D Content Creation

Kui Jia, Rui Chen, Yongwei Chen, Ningxin Jiao

arXiv · PDF · Open in the Atlas

Code that ran

11 of 18 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 7 have no contract verdict; 3 failures of our instrument; 7 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/2303.13873.json · badge: /api/ran/2303.13873.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
Gorilla-Lab-SCUT/Fantasia3D canonical (classifier label)
classifier basis not recorded on the link
6 ran · 6 no recorded run
ashawkey/fantasia3d.unofficial community
Papers with Code archive
5 ran · 1 no recorded run
FunctionStatusWhere it lives
DMTet Ran
ran on a synthesized input
ashawkey/fantasia3d.unofficial/geometry/dmtet.py
code served (permissive licence) · get_code("a0ba8a5bd18f91f0")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, class construct-then-call prompt, model not recorded) and returned tuple. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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

INIT_ARGS = {}

ARGS = {
    'pos_nx3': torch.randn(8, 3),
    'sdf_n': torch.randn(8),
    'tet_fx4': torch.tensor([[0, 1, 2, 3], [1, 2, 3, 4], [2, 3, 4, 5]], dtype=torch.long),
}

METHOD = '__call__'
Setup block drafted by
a language model, class construct-then-call prompt, model not recorded
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: torch and numpy seeded to 0 by the harness immediately before the class was constructed from INIT_ARGS (fixture_check.py)
FreqEncoder_torch Ran
ran on a synthesized input
ashawkey/fantasia3d.unofficial/geometry/dmtet.py
code served (permissive licence) · get_code("e76a68ae1ed8a29d")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, class construct-then-call prompt, model not recorded) and returned Tensor, ndim 2, dtype family float, shape (2, 20) 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

class FreqEncoder_torch(nn.Module):

    def __init__(self, input_dim, max_freq_log2, N_freqs, log_sampling=True, include_input=True, periodic_fns=(torch.sin, torch.cos)):
        super().__init__()
        self.input_dim = input_dim
        self.include_input = include_input
        self.periodic_fns = periodic_fns
        self.output_dim = 0
        if self.include_input:
            self.output_dim += self.input_dim
        self.output_dim += self.input_dim * N_freqs * len(self.periodic_fns)
        if log_sampling:
            self.freq_bands = 2.0 ** torch.linspace(0.0, max_freq_log2, N_freqs)
        else:
            self.freq_bands = torch.linspace(2.0 ** 0.0, 2.0 ** max_freq_log2, N_freqs)
        self.freq_bands = self.freq_bands.numpy().tolist()

    def forward(self, input, **kwargs):
        out = []
        if self.include_input:
            out.append(input)
        for i in range(len(self.freq_bands)):
            freq = self.freq_bands[i]
            for p_fn in self.periodic_fns:
                out.append(p_fn(input * freq))
        out = torch.cat(out, dim=-1)
        return out


INIT_ARGS = {
    'input_dim': 4,
    'max_freq_log2': 3,
    'N_freqs': 2,
    'log_sampling': True,
    'include_input': True,
    'periodic_fns': (torch.sin, torch.cos)
}

ARGS = {
    'input': torch.randn(2, 4)
}

if __name__ == '__main__':
    encoder = FreqEncoder_torch(**INIT_ARGS)
    output = encoder(**ARGS)
    print(f"Output shape: {output.shape}")
    print(f"Expected output dim: {encoder.output_dim}")
    print(f"Output:\n{output}")
Setup block drafted by
a language model, class construct-then-call prompt, model not recorded
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, 20) — shape (2, 20) 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: torch and numpy seeded to 0 by the harness immediately before the class was constructed from INIT_ARGS (fixture_check.py)
MLP Ran
ran on a synthesized input
ashawkey/fantasia3d.unofficial/geometry/dmtet.py
code served (permissive licence) · get_code("56ccae93d7c449fb")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, class construct-then-call prompt, model not recorded) 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
import torch.nn as nn

INIT_ARGS = {
    'dim_in': 4,
    'dim_out': 3,
    'dim_hidden': 8,
    'num_layers': 2,
    'bias': True,
}

ARGS = {
    'x': torch.randn(2, 4),
}

if __name__ == '__main__':
    from torch.nn import Module
    
    class MLP(nn.Module):

        def __init__(self, dim_in, dim_out, dim_hidden, num_layers, bias=True):
            super().__init__()
            self.dim_in = dim_in
            self.dim_out = dim_out
            self.dim_hidden = dim_hidden
            self.num_layers = num_layers
            net = []
            for l in range(num_layers):
                net.append(nn.Linear(self.dim_in if l == 0 else self.dim_hidden, self.dim_out if l == num_layers - 1 else self.dim_hidden, bias=bias))
            self.net = nn.ModuleList(net)

        def forward(self, x):
            for l in range(self.num_layers):
                x = self.net[l](x)
                if l != self.num_layers - 1:
                    x = torch.nn.functional.relu(x, inplace=True)
            return x

    model = MLP(**INIT_ARGS)
    output = model(**ARGS)
    print(f"Output shape: {output.shape}")
    print(f"Output: {output}")
Setup block drafted by
a language model, class construct-then-call prompt, model not recorded
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: torch and numpy seeded to 0 by the harness immediately before the class was constructed from INIT_ARGS (fixture_check.py)
aabb Ran
ran on a synthesized input
Gorilla-Lab-SCUT/Fantasia3D/render/mesh.py
code served (permissive licence) · get_code("71588ea43749ba8a")
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

torch.manual_seed(0)

class Mesh:
    def __init__(self):
        self.v_pos = torch.randn(2, 4)

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 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
compute_edges Ran
ran on a synthesized input
Gorilla-Lab-SCUT/Fantasia3D/render/mesh.py
code served (permissive licence) · get_code("3ef6a94495262ff2")
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 2, dtype family int, shape (5, 2) 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)

# attr_idx should be a tensor with shape (batch, 3)
# The function accesses attr_idx[:, 0], attr_idx[:, 1], attr_idx[:, 2]
# so it needs at least 3 columns (indices into vertices)
attr_idx = torch.tensor([
    [0, 1, 2],
    [1, 2, 3]
], dtype=torch.long)

ARGS = {
    "attr_idx": attr_idx,
    "return_inverse": False
}
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 2, dtype family int, shape (5, 2) — shape (5, 2) 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
dot Ran
ran; our contract draft was wrong, not the code
Gorilla-Lab-SCUT/Fantasia3D/geometry/dmtet.py
code served (permissive licence) · get_code("072f2ec9852bb19f")
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 2, dtype family float, shape (2, 1) 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 two small tensors for the dot product function
# x and y should be broadcastable and support element-wise multiplication
# The function computes sum(x * y, -1, keepdim=True)
# Using batch size 2 and dimension 4 as specified
x = torch.randn(2, 4)
y = torch.randn(2, 4)

ARGS = {
    "x": x,
    "y": y,
}
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 2, dtype family float, shape (2, 1) — shape (2, 1) 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_encoder Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
ashawkey/fantasia3d.unofficial/geometry/dmtet.py
code served (permissive licence) · get_code("404590cea670d79b")
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 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 torch.nn as nn

torch.manual_seed(0)

ARGS = {
    'encoding': 'frequency_torch',
    'input_dim': 3,
    'multires': 6,
    'degree': 4,
    'num_levels': 16,
    'level_dim': 2,
    'base_resolution': 16,
    'log2_hashmap_size': 19,
    'desired_resolution': 2048,
    'align_corners': False,
    'interpolation': 'linear',
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
freqencoder, gridencoder, shencoder, 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
get_view_direction Ran
ran, honoured the contract we drafted
Gorilla-Lab-SCUT/Fantasia3D/dataset/dataset_mesh.py
code served (permissive licence) · get_code("a8bc83685fe7cac9")
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 numpy as np
import torch

torch.manual_seed(0)

# Analyze the function:
# - thetas: used in comparison (>=, <) with scalars, so should be a scalar float
# - phis: used in comparison (>=, <) with scalars and np.pi, so should be a scalar float
# - front: used in comparison as a threshold value, should be a scalar float

# The function compares phis against thresholds involving front and np.pi
# Let's create valid values that will execute without error

thetas_val = 0.5  # scalar angle in radians
phis_val = 0.3    # scalar angle in radians, will match first condition: -front <= phis < front
front_val = 0.5   # scalar threshold

ARGS = {
    "thetas": thetas_val,
    "phis": phis_val,
    "front": front_val,
}
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 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
laplace_regularizer_const Ran
ran on a synthesized input
Gorilla-Lab-SCUT/Fantasia3D/render/regularizer.py
code served (permissive licence) · get_code("ca971f4330165a64")
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)

# v_pos: vertex positions, shape (num_vertices, 3)
# Each vertex has x, y, z coordinates
v_pos = torch.randn(4, 3)

# t_pos_idx: triangle indices, shape (num_triangles, 3)
# Each row contains indices of 3 vertices forming a triangle
# All indices must be valid (< num_vertices)
t_pos_idx = torch.tensor([
    [0, 1, 2],
    [1, 2, 3],
], dtype=torch.long)

ARGS = {
    "v_pos": v_pos,
    "t_pos_idx": t_pos_idx,
}
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
length Ran
ran; our contract draft was wrong, not the code
Gorilla-Lab-SCUT/Fantasia3D/geometry/dmtet.py
code served (permissive licence) · get_code("de6b9750cabc6a63")
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 2, dtype family float, shape (2, 1) 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 `length` takes a tensor x and an optional eps parameter
# It computes the length (norm) of x by calling dot(x, x) and taking sqrt
# x should be a tensor of any shape (the function uses -1 dimension indexing)

x = torch.randn(2, 4)
eps = 1e-20

ARGS = {
    "x": x,
    "eps": eps,
}
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 2, dtype family float, shape (2, 1) — shape (2, 1) 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
sdf_reg_loss Ran
ran on a synthesized input
ashawkey/fantasia3d.unofficial/geometry/dmtet.py
code served (permissive licence) · get_code("139b2d31a351a647")
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)

# Analyze the function:
# - sdf: a 1D tensor of SDF values that gets indexed by all_edges.reshape(-1)
# - all_edges: a 2D tensor that will be reshaped to 1D for indexing, then reshaped back to (-1, 2)
# 
# The function does:
# 1. sdf[all_edges.reshape(-1)].reshape(-1, 2) - indexes sdf and reshapes to pairs
# 2. Compares signs to create a mask
# 3. Filters by mask
# 4. Computes binary cross entropy on the filtered pairs

# Let's construct minimal tensors:
# - sdf needs to be 1D with enough elements to index
# - all_edges needs to be reshaped such that all_edges.reshape(-1) gives valid indices
#   and the result can be reshaped to (-1, 2)

# Simple setup: 
# Create an SDF tensor with 8 values (indices 0-7)
sdf = torch.randn(8)

# Create all_edges: if we reshape to (-1, 2), we need an even number of elements
# Let's use shape (2, 2, 2) which reshapes to 8 elements, then to (4, 2)
all_edges = torch.tensor([
    [[0, 1], [2, 3]],
    [[4, 5], [6, 7]]
], dtype=torch.long)

ARGS = {
    "sdf": sdf,
    "all_edges": all_edges,
}
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
DMTetGeometry Not yet run
unverified (harvested, no recorded run)
ashawkey/fantasia3d.unofficial/geometry/dmtet.py
code served (permissive licence) · get_code("8cff6a793f33c676")
How it ran

no invocation recorded.

avg_edge_length Not yet run
unverified (harvested, no recorded run)
Gorilla-Lab-SCUT/Fantasia3D/render/regularizer.py
code served (permissive licence) · get_code("c7d017fd024e3f4c")
How it ran

no invocation recorded.

load_mesh Not yet run
unverified (harvested, no recorded run)
Gorilla-Lab-SCUT/Fantasia3D/render/mesh.py
code served (permissive licence) · get_code("baeca74a977c91d2")
How it ran

no invocation recorded.

load_mtl Not yet run
unverified (harvested, no recorded run)
Gorilla-Lab-SCUT/Fantasia3D/render/material.py
code served (permissive licence) · get_code("f53d96b8290bec06")
How it ran

no invocation recorded.

load_obj Not yet run
unverified (harvested, no recorded run)
Gorilla-Lab-SCUT/Fantasia3D/render/obj.py
code served (permissive licence) · get_code("1a6391f70cbc085a")
How it ran

no invocation recorded.

merge_materials Not yet run
unverified (harvested, no recorded run)
Gorilla-Lab-SCUT/Fantasia3D/render/material.py
code served (permissive licence) · get_code("b6cb3e737729b530")
How it ran

no invocation recorded.

shade Not yet run
unverified (harvested, no recorded run)
Gorilla-Lab-SCUT/Fantasia3D/render/render.py
code served (permissive licence) · get_code("f5d5934ddb419abe")
How it ran

no invocation recorded.

Also present in other papers' code

Of 18 samples lifted from this paper's linked repositories, 18 carry a function identity and 0 do not. Of the 18 distinct functions with an identity, 5 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 4 later) and 13 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
dot 2 other papers
2 later
2304.13348 (2023-04)
TextDeformer: Geometry Manipulation using Text Guidance
2406.09850 (2024-06)
GradeADreamer: Enhanced Text-to-3D Generation Using Gaussian Splatting and Multi-View Diffusion
length 2 other papers
2 later
2304.13348 (2023-04)
TextDeformer: Geometry Manipulation using Text Guidance
2406.09850 (2024-06)
GradeADreamer: Enhanced Text-to-3D Generation Using Gaussian Splatting and Multi-View Diffusion
aabb 1 other paper
1 later
2304.13348 (2023-04)
TextDeformer: Geometry Manipulation using Text Guidance
get_view_direction 1 other paper
1 later
2406.09850 (2024-06)
GradeADreamer: Enhanced Text-to-3D Generation Using Gaussian Splatting and Multi-View Diffusion
sdf_reg_loss
brick of this paper's assembly: loss
1 other paper
1 dated earlier
2211.13220 (2022-11)
TetraDiffusion: Tetrahedral Diffusion Models for 3D Shape Generation

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

Automatic 3D content creation has achieved rapid progress recently due to the availability of pre-trained, large language models and image diffusion models, forming the emerging topic of text-to-3D content creation. Existing text-to-3D methods commonly use implicit scene representations, which couple the geometry and appearance via volume rendering and are suboptimal in terms of recovering finer geometries and achieving photorealistic rendering; consequently, they are less effective for generating highquality 3D assets. In this work, we propose a new method of Fantasia3D for high-quality text-to-3D content creation. Key to Fantasia3D is the disentangled modeling and learning of geometry and appearance. For geometry learning, we rely on a hybrid scene representation, and propose to encode surface normal extracted from the representation as the input of the image diffusion model. For appearance modeling, we introduce the spatially varying bidirectional reflectance distribution function (BRDF) into the text-to-3D task, and learn the surface material for photorealistic rendering of the generated surface. Our disentangled framework is more compatible with popular graphics engines, supporting relighting, editing, and physical simulation of the generated 3D assets. We conduct thorough experiments that show the advantages of our method over existing ones under different text-to-3D task settings. Project page and source codes: https://fantasia3d.github.io/.

For agents

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

get_harvested_code_for_paper("2303.13873")
get_code_for_paper("2303.13873")
have("2303.13873")

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

curl https://syntology.ai/api/ran/2303.13873.json

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

[![Syntology run record](https://syntology.ai/api/ran/2303.13873.svg)](https://syntology.ai/paper/2303.13873)

Connect an agent — have() is free.