SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2203.13333 · 2022

CLIP-Mesh: Generating textured meshes from text using pretrained image-text models

arXiv · PDF · Open in the Atlas

Code that ran

10 of 14 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, 0 violated it and 4 have no contract verdict; 4 failures of our instrument; 4 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/2203.13333.json · badge: /api/ran/2203.13333.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
NasirKhalid24/CLIP-Mesh canonical (classifier label)
classifier basis not recorded on the link
5 ran · 3 no recorded run
autodeskailab/clip-forge canonical (classifier label)
classifier basis: classifier_2025
5 ran · 1 no recorded run
FunctionStatusWhere it lives
compute_iou Ran
ran, honoured the contract we drafted
autodeskailab/clip-forge/train_autoencoder.py
pointer only (licence: NONE) · get_code("50f9537db6e67f4b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, autodeskailab/clip-forge 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.

cosine_avg Ran
ran on a synthesized input
NasirKhalid24/CLIP-Mesh/utils/helpers.py
code served (permissive licence) · get_code("962534ee79098e80")
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)

# Create small tensors for features and targets
# Both need to be compatible with CosineSimilarity
# CosineSimilarity computes cosine similarity along a dimension
# Default dim=1, so input shape should be (batch_size, embedding_dim)
features = torch.randn(2, 4)
targets = torch.randn(2, 4)

ARGS = {
    "features": features,
    "targets": targets,
}
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
cosine_sample Ran
ran on a synthesized input
NasirKhalid24/CLIP-Mesh/utils/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
cosine_sum Ran
ran on a synthesized input
NasirKhalid24/CLIP-Mesh/utils/helpers.py
code served (permissive licence) · get_code("d60e9b6ed1449683")
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)

# Create small tensors for features and targets
# CosineSimilarity expects two tensors of shape (batch_size, feature_dim)
# Using batch_size=2, feature_dim=4 as per requirements
features = torch.randn(2, 4)
targets = torch.randn(2, 4)

ARGS = {
    "features": features,
    "targets": targets,
}
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
experiment_name Ran
ran; our contract draft was wrong, not the code
autodeskailab/clip-forge/train_autoencoder.py
pointer only (licence: NONE) · get_code("80b53444e72a8019")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, autodeskailab/clip-forge 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.

experiment_name2 Ran
ran; our contract draft was wrong, not the code
autodeskailab/clip-forge/train_post_clip.py
pointer only (licence: NONE) · get_code("e3b28d0d8e8c03e3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, autodeskailab/clip-forge 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.

generate_all_queries_2 Ran
ran; our contract draft was wrong, not the code
autodeskailab/clip-forge/test_post_clip.py
pointer only (licence: NONE) · get_code("c0d3dde3e9b7d587")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, autodeskailab/clip-forge 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.

get_true_voxels Ran
ran, honoured the contract we drafted
autodeskailab/clip-forge/test_post_clip.py
pointer only (licence: NONE) · get_code("b871d08539ee0af7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, autodeskailab/clip-forge 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.

persp_proj Ran
ran on a synthesized input
NasirKhalid24/CLIP-Mesh/utils/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
support_sz Ran
ran; our contract draft was wrong, not the code
NasirKhalid24/CLIP-Mesh/utils/resize_right.py
pointer only (licence: MIT); the stored copy get_code serves, from merlresearch/SteeredDiffusion, is pointer only (licence: AGPL-3.0) · get_code("eb3584d528a35911")
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 merlresearch/SteeredDiffusion, and AGPL-3.0, as GitHub detects it on that repository, is not in the permissive set Syntology serves inline. 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.

bool_flag Not yet run
unverified (harvested, no recorded run)
autodeskailab/clip-forge/train_autoencoder.py
pointer only (licence: NONE) · get_code("5759b733d1deef88")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, autodeskailab/clip-forge 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. No invocation recorded.

cubic Not yet run
unverified (harvested, no recorded run)
NasirKhalid24/CLIP-Mesh/utils/resize_right.py
pointer only (licence: MIT); the stored copy get_code serves, from merlresearch/SteeredDiffusion, is pointer only (licence: AGPL-3.0) · get_code("69f91d76e488739d")
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 merlresearch/SteeredDiffusion, and AGPL-3.0, as GitHub detects it on that repository, is not in the permissive set Syntology serves inline. 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. No invocation recorded.

get_random_bg Not yet run
unverified (harvested, no recorded run)
NasirKhalid24/CLIP-Mesh/utils/camera.py
code served (permissive licence) · get_code("3bcc8dfd178266d2")
How it ran

no invocation recorded.

set_framework_dependencies Not yet run
unverified (harvested, no recorded run)
NasirKhalid24/CLIP-Mesh/utils/resize_right.py
pointer only (licence: MIT); the stored copy get_code serves, from merlresearch/SteeredDiffusion, is pointer only (licence: AGPL-3.0) · get_code("ae962b80c12bc789")
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 merlresearch/SteeredDiffusion, and AGPL-3.0, as GitHub detects it on that repository, is not in the permissive set Syntology serves inline. 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. No invocation recorded.

Also present in other papers' code

Of 14 samples lifted from this paper's linked repositories, 14 carry a function identity and 0 do not. Of the 14 distinct functions with an identity, 7 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 0 the same month, 7 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
compute_iou 9 other papers
3 dated earlier, 6 later
2003.04618 (2020-03)
Convolutional Occupancy Networks
2104.01148 (2021-04)
Decomposing 3D Scenes into Objects via Unsupervised Volume Segmentation
2107.01899 (2021-07)
Ray-ONet: Efficient 3D Reconstruction From A Single RGB Image
and 6 more not named here
bool_flag 3 other papers
3 later
2210.03403 (2022-10)
TAN Without a Burn: Scaling Laws of DP-SGD
2306.02583 (2023-06)
Stable Diffusion is Unstable
2404.09632 (2024-04)
Bridging Vision and Language Spaces with Assignment Prediction
cubic 2 other papers
1 dated earlier, 1 later
2105.05233 (2021-05)
Diffusion Models Beat GANs on Image Synthesis
2310.00224 (2023-10)
Steered Diffusion: A Generalized Framework for Plug-and-Play Conditional Image Synthesis
set_framework_dependencies 2 other papers
1 dated earlier, 1 later
2105.05233 (2021-05)
Diffusion Models Beat GANs on Image Synthesis
2310.00224 (2023-10)
Steered Diffusion: A Generalized Framework for Plug-and-Play Conditional Image Synthesis
support_sz 2 other papers
1 dated earlier, 1 later
2105.05233 (2021-05)
Diffusion Models Beat GANs on Image Synthesis
2310.00224 (2023-10)
Steered Diffusion: A Generalized Framework for Plug-and-Play Conditional Image Synthesis
cosine_sample 1 other paper
1 later
2304.13348 (2023-04)
TextDeformer: Geometry Manipulation using Text Guidance
persp_proj 1 other paper
1 later
2304.13348 (2023-04)
TextDeformer: Geometry Manipulation using Text Guidance

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 zero-shot generation of a 3D model using only a target text prompt. Without any 3D supervision our method deforms the control shape of a limit subdivided surface along with its texture map and normal map to obtain a 3D asset that corresponds to the input text prompt and can be easily deployed into games or modeling applications. We rely only on a pre-trained CLIP model that compares the input text prompt with differentiably rendered images of our 3D model. While previous works have focused on stylization or required training of generative models we perform optimization on mesh parameters directly to generate shape, texture or both. To constrain the optimization to produce plausible meshes and textures we introduce a number of techniques using image augmentations and the use of a pretrained prior that generates CLIP image embeddings given a text embedding.

For agents

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

get_harvested_code_for_paper("2203.13333")
get_code_for_paper("2203.13333")
have("2203.13333")

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

curl https://syntology.ai/api/ran/2203.13333.json

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

[![Syntology run record](https://syntology.ai/api/ran/2203.13333.svg)](https://syntology.ai/paper/2203.13333)

Connect an agent — have() is free.