SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2406.13897 · 2024

CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assets

arXiv · PDF · Open in the Atlas

Code that ran

7 of 8 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 1 has no contract verdict; 4 failures of our instrument; 1 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/2406.13897.json · badge: /api/ran/2406.13897.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
yixunliang/unitex community (classifier label)
classifier basis not recorded on the link
7 ran · 1 no recorded run
FunctionStatusWhere it lives
AttentionBlock Ran
ran; our contract draft was wrong, not the code
yixunliang/unitex/TSD_SR/basicsr/archs/dfdnet_util.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from RuoyuGuo/P-PatchDiff, is pointer only (licence: NONE) · get_code("8d3cd21cd5c3181a")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from RuoyuGuo/P-PatchDiff, 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.

adaptive_instance_normalization Ran
ran; our contract draft was wrong, not the code
yixunliang/unitex/TSD_SR/basicsr/archs/dfdnet_util.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from RuoyuGuo/P-PatchDiff, is pointer only (licence: NONE) · get_code("b7c6741eed724350")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from RuoyuGuo/P-PatchDiff, 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.

calc_mean_std Ran
ran; our contract draft was wrong, not the code
yixunliang/unitex/TSD_SR/basicsr/archs/dfdnet_util.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from RuoyuGuo/P-PatchDiff, is pointer only (licence: NONE) · get_code("a7e8af4ef5efc131")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from RuoyuGuo/P-PatchDiff, 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.

gaussian Ran
ran, honoured the contract we drafted
yixunliang/unitex/LTM/craftsman/utils/loss.py
code served (permissive licence) · get_code("c56b7ef16f309a45")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned Tensor, ndim 1, dtype family float, shape (5,) 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
from math import exp

torch.manual_seed(0)

ARGS = {
    "window_size": 5,
    "sigma": 1.0,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 1, dtype family float, shape (5,) — shape (5,) 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
l1_loss Ran
ran; our contract draft was wrong, not the code
yixunliang/unitex/LTM/craftsman/utils/loss.py
code served (permissive licence) · get_code("ac0e42d6fbcfbbe6")
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 network output and ground truth
# Both should have the same shape for the subtraction and mean operations
network_output = torch.randn(2, 4)  # batch size 2, 4 dimensions
gt = torch.randn(2, 4)  # batch size 2, 4 dimensions

ARGS = {
    "network_output": network_output,
    "gt": gt,
}
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
l2_loss Ran
ran, honoured the contract we drafted
yixunliang/unitex/LTM/craftsman/utils/loss.py
code served (permissive licence) · get_code("8c3b0f873ba11813")
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
import torch.nn as nn

torch.manual_seed(0)

# Create small tensors for network output and ground truth
# Both should have the same shape for the loss computation
# Using batch size 2, feature dimension 4
network_output = torch.randn(2, 4)
gt = torch.randn(2, 4)

ARGS = {
    "network_output": network_output,
    "gt": gt,
}
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
tile_sample Ran
ran on a synthesized input
yixunliang/unitex/TSD_SR/sr_pipeline.py
code served (permissive licence) · get_code("13812c4cff22d2f4")
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, 4, 6, 6) 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

torch.manual_seed(0)

# Build a minimal transformer mock that satisfies the interface
class MinimalTransformer(nn.Module):
    def __init__(self):
        super().__init__()
        self.device = torch.device('cpu')
        self.config = type('Config', (), {'in_channels': 4})()
        self.linear = nn.Linear(4, 4)
    
    def forward(self, hidden_states, timestep, encoder_hidden_states, pooled_projections, return_dict=False):
        # Return output matching input shape
        batch, channels, h, w = hidden_states.shape
        output = self.linear(hidden_states.permute(0, 2, 3, 1)).permute(0, 3, 1, 2)
        if return_dict:
            return type('Output', (), {'sample': output})()
        return (output,)

# Build args config object
class ArgsConfig:
    def __init__(self):
        self.latent_tiled_size = 8
        self.latent_tiled_overlap = 2
        self.device = torch.device('cpu')

# Create instances
transformer = MinimalTransformer()
args = ArgsConfig()

# Create minimal tensors
lq_latent = torch.randn(2, 4, 6, 6)  # batch=2, channels=4, h=6, w=6
lq = torch.randn(2, 3, 12, 12)  # dummy lq image
timesteps = torch.tensor([500, 500])  # 2 timesteps
prompt_embeds = torch.randn(2, 7, 8)  # batch=2, seq_len=7, dim=8
pooled_prompt_embeds = torch.randn(2, 9)  # batch=2, pooled_dim=9
weight_dtype = torch.float32

ARGS = {
    'lq_latent': lq_latent,
    'lq': lq,
    'transformer': transformer,
    'timesteps': timesteps,
    'prompt_embeds': prompt_embeds,
    'pooled_prompt_embeds': pooled_prompt_embeds,
    'weight_dtype': weight_dtype,
    'args': args,
}
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 Tensor, ndim 4, dtype family float, shape (2, 4, 6, 6) — shape (2, 4, 6, 6) 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
build_ltm Not yet run
unverified (harvested, no recorded run)
yixunliang/unitex/pipeline.py
code served (permissive licence) · get_code("5fe25138e6151526")
How it ran

no invocation recorded.

Also present in other papers' code

Of 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 distinct functions with an identity, 6 are also present in other papers whose code we hold (6 with at least one paper dated earlier, 3 the same month, 6 later) and 2 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
gaussian 160 other papers
100 dated earlier, 8 the same month, 51 later, 1 same year, order not determinable · 7 only as an assembly brick
1812.11941 (2018-12)
High Quality Monocular Depth Estimation via Transfer Learning
1904.01538 (2019-04)
Spatial Attentive Single-Image Deraining with a High Quality Real Rain Dataset
1907.11628 (2019-07)
Unsupervised Learning for Optical Flow Estimation Using Pyramid Convolution LSTM
and 157 more not named here
l1_loss 93 other papers
45 dated earlier, 5 the same month, 43 later
2308.04079 (2023-08)
3D Gaussian Splatting for Real-Time Radiance Field Rendering
2309.13101 (2023-09)
Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstruction
2310.08528 (2023-10)
4D Gaussian Splatting for Real-Time Dynamic Scene Rendering
and 90 more not named here
l2_loss 90 other papers
44 dated earlier, 5 the same month, 41 later
2308.04079 (2023-08)
3D Gaussian Splatting for Real-Time Radiance Field Rendering
2309.13101 (2023-09)
Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstruction
2310.08528 (2023-10)
4D Gaussian Splatting for Real-Time Dynamic Scene Rendering
and 87 more not named here
adaptive_instance_normalization 16 other papers
8 dated earlier, 7 later, 1 same year, order not determinable
Wang_Deep_Arbitrary-Scale_Image_Super-Resolution_via_Scale-Equivariance_Pursuit_CVPR_2023_paper (2023 (year only))
Deep Arbitrary-Scale Image Super-Resolution via Scale-Equivariance Pursuit
2303.04970 (2023-03)
LMR: A Large-Scale Multi-Reference Dataset for Reference-based Super-Resolution
2304.01064 (2023-04)
Real-time 6K Image Rescaling with Rate-distortion Optimization
and 13 more not named here
AttentionBlock 14 other papers
6 dated earlier, 7 later, 1 same year, order not determinable
Wang_Deep_Arbitrary-Scale_Image_Super-Resolution_via_Scale-Equivariance_Pursuit_CVPR_2023_paper (2023 (year only))
Deep Arbitrary-Scale Image Super-Resolution via Scale-Equivariance Pursuit
2303.04970 (2023-03)
LMR: A Large-Scale Multi-Reference Dataset for Reference-based Super-Resolution
2304.01064 (2023-04)
Real-time 6K Image Rescaling with Rate-distortion Optimization
and 11 more not named here
calc_mean_std 14 other papers
6 dated earlier, 7 later, 1 same year, order not determinable
Wang_Deep_Arbitrary-Scale_Image_Super-Resolution_via_Scale-Equivariance_Pursuit_CVPR_2023_paper (2023 (year only))
Deep Arbitrary-Scale Image Super-Resolution via Scale-Equivariance Pursuit
2303.04970 (2023-03)
LMR: A Large-Scale Multi-Reference Dataset for Reference-based Super-Resolution
2304.01064 (2023-04)
Real-time 6K Image Rescaling with Rate-distortion Optimization
and 11 more not named here

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

In the realm of digital creativity, our potential to craft intricate 3D worlds from imagination is often hampered by the limitations of existing digital tools, which demand extensive expertise and efforts. To narrow this disparity, we introduce CLAY, a 3D geometry and material generator designed to effortlessly transform human imagination into intricate 3D digital structures. CLAY supports classic text or image inputs as well as 3D-aware controls from diverse primitives (multi-view images, voxels, bounding boxes, point clouds, implicit representations, etc). At its core is a large-scale generative model composed of a multi-resolution Variational Autoencoder (VAE) and a minimalistic latent Diffusion Transformer (DiT), to extract rich 3D priors directly from a diverse range of 3D geometries. Specifically, it adopts neural fields to represent continuous and complete surfaces and uses a geometry generative module with pure transformer blocks in latent space. We present a progressive training scheme to train CLAY on an ultra large 3D model dataset obtained through a carefully designed processing pipeline, resulting in a 3D native geometry generator with 1.5 billion parameters. For appearance generation, CLAY sets out to produce physically-based rendering (PBR) textures by employing a multi-view material diffusion model that can generate 2K resolution textures with diffuse, roughness, and metallic modalities. We demonstrate using CLAY for a range of controllable 3D asset creations, from sketchy conceptual designs to production ready assets with intricate details. Even first time users can easily use CLAY to bring their vivid 3D imaginations to life, unleashing unlimited creativity.

For agents

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

get_harvested_code_for_paper("2406.13897")
get_code_for_paper("2406.13897")
have("2406.13897")

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

curl https://syntology.ai/api/ran/2406.13897.json

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

[![Syntology run record](https://syntology.ai/api/ran/2406.13897.svg)](https://syntology.ai/paper/2406.13897)

Connect an agent — have() is free.