SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2304.13348 · 2023

TextDeformer: Geometry Manipulation using Text Guidance

arXiv · PDF · Open in the Atlas

Code that ran

11 of 16 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 8 have no contract verdict; 3 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/2304.13348.json · badge: /api/ran/2304.13348.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
threedle/TextDeformer canonical (classifier label)
classifier basis: census
11 ran · 5 no recorded run
FunctionStatusWhere it lives
aabb Ran
ran on a synthesized input
threedle/TextDeformer/nvdiffmodeling/src/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
avg_edge_length Ran
ran on a synthesized input
threedle/TextDeformer/nvdiffmodeling/src/regularizer.py
code served (permissive licence) · get_code("997e97bfa3b50b09")
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 float, ndim 0, dtype family float, shape () as a later run recorded it. 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, 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

torch.manual_seed(0)

class MockMesh(nn.Module):
    def __init__(self):
        super().__init__()
        # v_pos: vertex positions, shape (num_verts, 3)
        self.register_buffer('v_pos', torch.randn(5, 3))
        # t_pos_idx: triangle indices, shape (num_tris, 3)
        self.register_buffer('t_pos_idx', torch.tensor([
            [0, 1, 2],
            [1, 2, 3],
            [2, 3, 4]
        ], dtype=torch.int64))
    
    def eval(self):
        return super().eval()

opt_mesh = MockMesh()

ARGS = {
    'opt_mesh': opt_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 float, 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
center_by_reference Ran
ran on a synthesized input
threedle/TextDeformer/nvdiffmodeling/src/mesh.py
code served (permissive licence) · get_code("b8b5019045a6e3ce")
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 Mesh. 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

torch.manual_seed(0)

class Mesh:
    def __init__(self, v_pos=None, t_pos_idx=None, v_nrm=None, t_nrm_idx=None, v_tex=None, t_tex_idx=None, v_tng=None, t_tng_idx=None, v_weights=None, bone_mtx=None, material=None, base=None):
        self.v_pos = v_pos
        self.v_weights = v_weights
        self.v_nrm = v_nrm
        self.v_tex = v_tex
        self.v_tng = v_tng
        self.t_pos_idx = t_pos_idx
        self.t_nrm_idx = t_nrm_idx
        self.t_tex_idx = t_tex_idx
        self.t_tng_idx = t_tng_idx
        self.material = material
        self.bone_mtx = bone_mtx
        if base is not None:
            self.copy_none(base)

    def copy_none(self, other):
        if self.v_pos is None:
            self.v_pos = other.v_pos
        if self.v_weights is None:
            self.v_weights = other.v_weights
        if self.t_pos_idx is None:
            self.t_pos_idx = other.t_pos_idx
        if self.v_nrm is None:
            self.v_nrm = other.v_nrm
        if self.t_nrm_idx is None:
            self.t_nrm_idx = other.t_nrm_idx
        if self.v_tex is None:
            self.v_tex = other.v_tex
        if self.t_tex_idx is None:
            self.t_tex_idx = other.t_tex_idx
        if self.v_tng is None:
            self.v_tng = other.v_tng
        if self.t_tng_idx is None:
            self.t_tng_idx = other.t_tng_idx
        if self.material is None:
            self.material = other.material
        if self.bone_mtx is None:
            self.bone_mtx = other.bone_mtx

# Create base mesh with vertex positions
base_v_pos = torch.randn(5, 3)
base_mesh = Mesh(v_pos=base_v_pos)

# Create reference AABB (axis-aligned bounding box)
ref_aabb = torch.tensor([
    [-1.0, -1.0, -1.0],
    [1.0, 1.0, 1.0]
])

# Scale parameter
scale = 2.0

ARGS = {
    "base_mesh": base_mesh,
    "ref_aabb": ref_aabb,
    "scale": scale
}
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 Mesh — a Mesh output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Mesh 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
cosine_sample Ran
ran on a synthesized input
threedle/TextDeformer/utilities/camera.py
code served (permissive licence) · get_code("46b27476b8041014")
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 1, dtype family float, shape (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

np.random.seed(0)

# N should be a 3D vector (3,) shape
# The function normalizes it, computes orthogonal vectors via cross products,
# and uses it for sampling a direction around that vector
N = np.array([1.0, 2.0, 3.0])

ARGS = {
    "N": N
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 1, dtype family float, shape (3,) — shape (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
dot Ran
ran; our contract draft was wrong, not the code
threedle/TextDeformer/nvdiffmodeling/src/util.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
edge_length_regularizer Ran
ran on a synthesized input
threedle/TextDeformer/nvdiffmodeling/src/regularizer.py
code served (permissive licence) · get_code("9d1d964d8e4e5e48")
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 mesh_op_edge_length_regularizer. 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 torch.nn as nn

torch.manual_seed(0)

class SimpleMesh(nn.Module):
    def __init__(self):
        super().__init__()
        # v_pos: vertex positions, shape [num_verts, 3]
        self.v_pos = nn.Parameter(torch.randn(4, 3))
        # t_pos_idx: triangle indices, shape [num_tris, 3]
        # Each row is indices into v_pos for the 3 vertices of a triangle
        self.t_pos_idx = torch.tensor([
            [0, 1, 2],
            [1, 2, 3],
            [0, 2, 3]
        ], dtype=torch.int64)
    
    def eval(self, params=None):
        return self

mesh_instance = SimpleMesh()

ARGS = {
    "mesh": mesh_instance
}
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 mesh_op_edge_length_regularizer — a mesh_op_edge_length_regularizer output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a mesh_op_edge_length_regularizer 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
length Ran
ran; our contract draft was wrong, not the code
threedle/TextDeformer/nvdiffmodeling/src/util.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
persp_proj Ran
ran on a synthesized input
threedle/TextDeformer/utilities/camera.py
code served (permissive licence) · get_code("b5152d98492bb987")
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 2, dtype family int, shape (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 numpy as np

ARGS = {
    'fov_x': 45,
    'ar': 1.0,
    'near': 1.0,
    'far': 50.0,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 2, dtype family int, shape (4, 4) — shape (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
reflect Ran
ran on a synthesized input
threedle/TextDeformer/nvdiffmodeling/src/util.py
code served (permissive licence) · get_code("f8332e15b46ba812")
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, 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

torch.manual_seed(0)

# Create two small tensors for the reflect function
# x: input vector, shape (2, 4) - batch of 2, dimension 4
# n: normal vector, shape (2, 4) - batch of 2, dimension 4
x = torch.randn(2, 4)
n = torch.randn(2, 4)

ARGS = {
    "x": x,
    "n": n,
}
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, 4) — shape (2, 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
shade Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
threedle/TextDeformer/nvdiffmodeling/src/render.py
pointer only (licence: MIT); the stored copy get_code serves, from NVlabs/nvdiffmodeling, is pointer only (licence: NOASSERTION) · get_code("e5155d851cbebb5a")
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 NVlabs/nvdiffmodeling, 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.

unit_size Ran
ran on a synthesized input
threedle/TextDeformer/nvdiffmodeling/src/mesh.py
code served (permissive licence) · get_code("b545da6137bd6930")
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 Mesh. 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

torch.manual_seed(0)

class Mesh:

    def __init__(self, v_pos=None, t_pos_idx=None, v_nrm=None, t_nrm_idx=None, v_tex=None, t_tex_idx=None, v_tng=None, t_tng_idx=None, v_weights=None, bone_mtx=None, material=None, base=None):
        self.v_pos = v_pos
        self.v_weights = v_weights
        self.v_nrm = v_nrm
        self.v_tex = v_tex
        self.v_tng = v_tng
        self.t_pos_idx = t_pos_idx
        self.t_nrm_idx = t_nrm_idx
        self.t_tex_idx = t_tex_idx
        self.t_tng_idx = t_tng_idx
        self.material = material
        self.bone_mtx = bone_mtx
        if base is not None:
            self.copy_none(base)

    def copy_none(self, other):
        if self.v_pos is None:
            self.v_pos = other.v_pos
        if self.v_weights is None:
            self.v_weights = other.v_weights
        if self.t_pos_idx is None:
            self.t_pos_idx = other.t_pos_idx
        if self.v_nrm is None:
            self.v_nrm = other.v_nrm
        if self.t_nrm_idx is None:
            self.t_nrm_idx = other.t_nrm_idx
        if self.v_tex is None:
            self.v_tex = other.v_tex
        if self.t_tex_idx is None:
            self.t_tex_idx = other.t_tex_idx
        if self.v_tng is None:
            self.v_tng = other.v_tng
        if self.t_tng_idx is None:
            self.t_tng_idx = other.t_tng_idx
        if self.material is None:
            self.material = other.material
        if self.bone_mtx is None:
            self.bone_mtx = other.bone_mtx

    def get_frames(self):
        return self.bone_mtx.shape[0] if self.bone_mtx is not None else 1

    def clone(self):
        out = Mesh(base=self)
        if out.v_pos is not None:
            out.v_pos = out.v_pos.clone()
        if out.v_weights is not None:
            out.v_weights = out.v_weights.clone()
        if out.t_pos_idx is not None:
            out.t_pos_idx = out.t_pos_idx.clone()
        if out.v_nrm is not None:
            out.v_nrm = out.v_nrm.clone()
        if out.t_nrm_idx is not None:
            out.t_nrm_idx = out.t_nrm_idx.clone()
        if out.v_tex is not None:
            out.v_tex = out.v_tex.clone()
        if out.t_tex_idx is not None:
            out.t_tex_idx = out.t_tex_idx.clone()
        if out.v_tng is not None:
            out.v_tng = out.v_tng.clone()
        if out.t_tng_idx is not None:
            out.t_tng_idx = out.t_tng_idx.clone()
        if out.bone_mtx is not None:
            out.bone_mtx = out.bone_mtx.clone()
        return out

    def eval(self, params={}):
        return self

def aabb(mesh):
    return (torch.min(mesh.v_pos, dim=0).values, torch.max(mesh.v_pos, dim=0).values)

def unit_size(mesh):
    with torch.no_grad():
        vmin, vmax = aabb(mesh)
        scale = 2 / torch.max(vmax - vmin).item()
        v_pos = mesh.v_pos - (vmax + vmin) / 2
        v_pos = v_pos * scale
        return Mesh(v_pos, base=mesh)

# Create a simple mesh with vertex positions
v_pos = torch.tensor([
    [-1.0, -1.0, -1.0],
    [1.0, 1.0, 1.0],
], dtype=torch.float32)

# Create base mesh
base_mesh = Mesh(
    v_pos=v_pos,
    t_pos_idx=torch.tensor([[0, 1, 0]], dtype=torch.long),
    v_nrm=torch.randn(2, 3),
    v_tex=torch.randn(2, 2),
    material=None
)

ARGS = {
    "mesh": base_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 Mesh — a Mesh output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Mesh 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
get_random_bg Not yet run
unverified (harvested, no recorded run)
threedle/TextDeformer/utilities/camera.py
code served (permissive licence) · get_code("74ff9251845fb16e")
How it ran

no invocation recorded.

laplace_regularizer_const Not yet run
unverified (harvested, no recorded run)
threedle/TextDeformer/nvdiffmodeling/src/regularizer.py
code served (permissive licence) · get_code("31e09d3a07b8180c")
How it ran

no invocation recorded.

load_mtl Not yet run
unverified (harvested, no recorded run)
threedle/TextDeformer/nvdiffmodeling/src/material.py
code served (permissive licence) · get_code("36562037e3dea340")
How it ran

no invocation recorded.

load_obj Not yet run
unverified (harvested, no recorded run)
threedle/TextDeformer/nvdiffmodeling/src/obj.py
code served (permissive licence) · get_code("9932280d3974e132")
How it ran

no invocation recorded.

merge_materials Not yet run
unverified (harvested, no recorded run)
threedle/TextDeformer/nvdiffmodeling/src/material.py
code served (permissive licence) · get_code("70b072c635219a5c")
How it ran

no invocation recorded.

Also present in other papers' code

Of 16 samples lifted from this paper's linked repositories, 16 carry a function identity and 0 do not. Of the 16 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, 2 later) and 10 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
1 dated earlier, 1 later
2303.13873 (2023-03)
Fantasia3D: Disentangling Geometry and Appearance for High-quality Text-to-3D Content Creation
2406.09850 (2024-06)
GradeADreamer: Enhanced Text-to-3D Generation Using Gaussian Splatting and Multi-View Diffusion
length 2 other papers
1 dated earlier, 1 later
2303.13873 (2023-03)
Fantasia3D: Disentangling Geometry and Appearance for High-quality Text-to-3D Content Creation
2406.09850 (2024-06)
GradeADreamer: Enhanced Text-to-3D Generation Using Gaussian Splatting and Multi-View Diffusion
aabb 1 other paper
1 dated earlier
2303.13873 (2023-03)
Fantasia3D: Disentangling Geometry and Appearance for High-quality Text-to-3D Content Creation
cosine_sample 1 other paper
1 dated earlier
2203.13333 (2022-03)
CLIP-Mesh: Generating textured meshes from text using pretrained image-text models
persp_proj 1 other paper
1 dated earlier
2203.13333 (2022-03)
CLIP-Mesh: Generating textured meshes from text using pretrained image-text models
shade 1 other paper
1 dated earlier
2104.03989 (2021-04)
Appearance-Driven Automatic 3D Model Simplification

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 a technique for automatically producing a deformation of an input triangle mesh, guided solely by a text prompt. Our framework is capable of deformations that produce both large, low-frequency shape changes, and small high-frequency details. Our framework relies on differentiable rendering to connect geometry to powerful pre-trained image encoders, such as CLIP and DINO. Notably, updating mesh geometry by taking gradient steps through differentiable rendering is notoriously challenging, commonly resulting in deformed meshes with significant artifacts. These difficulties are amplified by noisy and inconsistent gradients from CLIP. To overcome this limitation, we opt to represent our mesh deformation through Jacobians, which updates deformations in a global, smooth manner (rather than locally-sub-optimal steps). Our key observation is that Jacobians are a representation that favors smoother, large deformations, leading to a global relation between vertices and pixels, and avoiding localized noisy gradients. Additionally, to ensure the resulting shape is coherent from all 3D viewpoints, we encourage the deep features computed on the 2D encoding of the rendering to be consistent for a given vertex from all viewpoints. We demonstrate that our method is capable of smoothly-deforming a wide variety of source mesh and target text prompts, achieving both large modifications to, e.g., body proportions of animals, as well as adding fine semantic details, such as shoe laces on an army boot and fine details of a face.

For agents

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

get_harvested_code_for_paper("2304.13348")
get_code_for_paper("2304.13348")
have("2304.13348")

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

curl https://syntology.ai/api/ran/2304.13348.json

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

[![Syntology run record](https://syntology.ai/api/ran/2304.13348.svg)](https://syntology.ai/paper/2304.13348)

Connect an agent — have() is free.