SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2303.11328 · ICCV · 2023

Zero-1-to-3: Zero-shot One Image to 3D Object

Rundi Wu, Carl Vondrick, Ruoshi Liu, Sergey Zakharov, Basile Van Hoorick, Pavel Tokmakov

arXiv · PDF · Open in the Atlas

Code that ran

9 of 12 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, 3 violated it and 1 has no contract verdict; 5 failures of our instrument; 3 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/2303.11328.json · badge: /api/ran/2303.11328.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
cvlab-columbia/zero123 canonical (classifier label)
classifier basis not recorded on the link
9 ran · 3 no recorded run
FunctionStatusWhere it lives
add_margin Ran
ran; our contract draft was wrong, not the code
cvlab-columbia/zero123/zero123/ldm/util.py
code served (permissive licence) · get_code("c95e88aa409419d4")
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 Image. 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
from PIL import Image
import numpy as np

# Create a small PIL Image for testing
# Create a simple RGB image with size 100x80 (distinct dimensions for probing)
img_array = np.random.randint(0, 256, (80, 100, 3), dtype=np.uint8)
pil_img = Image.fromarray(img_array, mode='RGB')

# Define color as a tuple (RGB)
color = (255, 0, 0)  # Red

# Define size parameter
size = 256

ARGS = {
    'pil_img': pil_img,
    'color': color,
    'size': size
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Image — a Image output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Image output the recorded ndim 3 and dtype family int 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
always Ran
ran; our contract draft was wrong, not the code
cvlab-columbia/zero123/zero123/ldm/modules/x_transformer.py
code served (permissive licence) · get_code("fe5dd5258046898c")
How it ran

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

ARGS = {
    'val': 42
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type function — a function output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a function 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
default Ran
ran, violated the contract we drafted
cvlab-columbia/zero123/zero123/ldm/modules/attention.py
code served (permissive licence) · get_code("424012cb37b31172")
How it ran

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

from inspect import isfunction

def exists(val):
    return val is not None

def default(val, d):
    if exists(val):
        return val
    return d() if isfunction(d) else d

# Test case 1: val exists (not None), d is a regular value
ARGS_1 = {
    'val': 42,
    'd': 100
}

# Test case 2: val is None, d is a regular value
ARGS_2 = {
    'val': None,
    'd': 100
}

# Test case 3: val is None, d is a function
def default_func():
    return 200

ARGS_3 = {
    'val': None,
    'd': default_func
}

# Test case 4: val exists, d is a function
ARGS_4 = {
    'val': "existing_value",
    'd': lambda: "default_value"
}

# Use one of the test cases as the final ARGS
ARGS = ARGS_3
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
Imports
none outside the standard library — 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
disabled_train Ran
ran, violated the contract we drafted
cvlab-columbia/zero123/zero123/ldm/models/diffusion/classifier.py
code served (permissive licence) · get_code("4cb732f513d69dfd")
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 SimpleModel. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)
    
    def forward(self, x):
        return self.linear(x)

model = SimpleModel()

ARGS = {
    "self": model,
    "mode": True
}
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 SimpleModel — a SimpleModel output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a SimpleModel 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
exists Ran
ran, violated the contract we drafted
cvlab-columbia/zero123/zero123/ldm/modules/attention.py
pointer only (licence: MIT); the stored copy get_code serves, from ThomasMrY/VCT, is pointer only (licence: NONE) · get_code("aa5486a3650902d8")
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 ThomasMrY/VCT, 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.

load_and_preprocess Ran
ran; our contract draft was wrong, not the code
cvlab-columbia/zero123/zero123/ldm/util.py
code served (permissive licence) · get_code("1ee4e2eb0cf3a009")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned ndarray, ndim 3, dtype family int, shape (256, 256, 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
from PIL import Image
import cv2

class MockInterface:
    """Mock interface that takes an image and returns it with an alpha channel."""
    def __call__(self, images):
        result = []
        for img in images:
            # Convert to RGBA and return
            img_array = np.array(img.convert('RGBA'))
            result.append(Image.fromarray(img_array))
        return result

# Create a small test image (100x100 RGB)
test_image_array = np.ones((100, 100, 3), dtype=np.uint8) * 200
test_image_array[20:80, 20:80, :] = 50  # Add a darker square in the middle
test_pil_image = Image.fromarray(test_image_array, mode='RGB')

# Create the mock interface
mock_interface = MockInterface()

ARGS = {
    "interface": mock_interface,
    "input_im": test_pil_image
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, cv2, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 3, dtype family int, shape (256, 256, 3) — shape (256, 256, 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
load_im Ran
ran on a synthesized input
cvlab-columbia/zero123/3drec/run_zero123.py
code served (permissive licence) · get_code("48b81cc9777a2a5b")
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 (1, 3, 224, 224) 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 numpy as np
from PIL import Image
import tempfile
import os

torch.manual_seed(0)

# Create a temporary image file for testing
temp_dir = tempfile.mkdtemp()
temp_image_path = os.path.join(temp_dir, "test_image.png")

# Create a simple RGB image and save it
test_image = Image.new('RGB', (256, 256), color=(73, 109, 137))
test_image.save(temp_image_path)

ARGS = {
    'im_path': temp_image_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, numpy, requests, torch, torchvision — 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 (1, 3, 224, 224) — shape (1, 3, 224, 224) 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
tsr_stats Ran
ran; our contract draft was wrong, not the code
cvlab-columbia/zero123/3drec/run_zero123.py
pointer only (licence: MIT); the stored copy get_code serves, from pals-ttic/sjc, is pointer only (licence: NOASSERTION) · get_code("f3cf3784fb4488db")
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 pals-ttic/sjc, 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.

uniq Ran
ran; our contract draft was wrong, not the code
cvlab-columbia/zero123/zero123/ldm/modules/attention.py
pointer only (licence: MIT); the stored copy get_code serves, from JingWu321/MUNBa, is pointer only (licence: NONE) · get_code("9a299fe5ae09e407")
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 JingWu321/MUNBa, 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.

pil_rectangle_crop Not yet run
unverified (harvested, no recorded run)
cvlab-columbia/zero123/zero123/ldm/util.py
code served (permissive licence) · get_code("afe61ba472afc243")
How it ran

no invocation recorded.

sample_model Not yet run
unverified (harvested, no recorded run)
cvlab-columbia/zero123/zero123/gradio_new.py
code served (permissive licence) · get_code("5c2a4c571fbfbf59")
How it ran

no invocation recorded.

sample_model Not yet run
unverified (harvested, no recorded run)
cvlab-columbia/zero123/zero123/gradio_objaverse.py
code served (permissive licence) · get_code("c3ba377c1bbf1281")
How it ran

no invocation recorded.

Also present in other papers' code

Of 12 samples lifted from this paper's linked repositories, 12 carry a function identity and 0 do not. Of the 12 distinct functions with an identity, 9 are also present in other papers whose code we hold (6 with at least one paper dated earlier, 5 the same month, 9 later) and 3 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
exists 486 other papers
150 dated earlier, 15 the same month, 315 later, 4 same year, order not determinable, 2 undated · 78 only as an assembly brick
1603.08155 (2016-03)
Perceptual Losses for Real-Time Style Transfer and Super-Resolution
1611.07004 (2016-11)
Image-to-Image Translation with Conditional Adversarial Networks
1804.04637 (2018-04)
EMBER: An Open Dataset for Training Static PE Malware Machine Learning Models
and 483 more not named here
default 207 other papers
38 dated earlier, 6 the same month, 161 later, 2 same year, order not determinable · 41 only as an assembly brick
1711.11585 (2017-11)
High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs
2006.11239 (2020-06)
Denoising Diffusion Probabilistic Models
2010.08162 (2020-10)
SidechainNet: An All-Atom Protein Structure Dataset for Machine Learning
and 204 more not named here
disabled_train 173 other papers
17 dated earlier, 2 the same month, 154 later · 5 only as an assembly brick
2012.09841 (2020-12)
Taming Transformers for High-Resolution Image Synthesis
2102.05379 (2021-02)
Argmax Flows and Multinomial Diffusion: Learning Categorical Distributions
2104.07652 (2021-04)
Geometry-Free View Synthesis: Transformers and no 3D Priors
and 170 more not named here
uniq 115 other papers
9 dated earlier, 5 the same month, 99 later, 2 same year, order not determinable
2112.10752 (2021-12)
High-Resolution Image Synthesis with Latent Diffusion Models
2204.06125 (2022-04)
Hierarchical Text-Conditional Image Generation with CLIP Latents
2206.02779 (2022-06)
Blended Latent Diffusion
and 112 more not named here
always 56 other papers
9 dated earlier, 2 the same month, 44 later, 1 same year, order not determinable
2102.12092 (2021-02)
Zero-Shot Text-to-Image Generation
2107.03312 (2021-07)
SoundStream: An End-to-End Neural Audio Codec
2206.00100 (2022-06)
VALHALLA: Visual Hallucination for Machine Translation
and 53 more not named here
add_margin 3 other papers
3 later
2306.16928 (2023-06)
One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimization
2401.14398 (2024-01)
pix2gestalt: Amodal Segmentation by Synthesizing Wholes
2406.03720 (2024-06)
JIGMARK: A Black-Box Approach for Enhancing Image Watermarks against Diffusion Model Edits
pil_rectangle_crop 3 other papers
3 later
2306.16928 (2023-06)
One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimization
2401.14398 (2024-01)
pix2gestalt: Amodal Segmentation by Synthesizing Wholes
2406.03720 (2024-06)
JIGMARK: A Black-Box Approach for Enhancing Image Watermarks against Diffusion Model Edits
tsr_stats 3 other papers
2 dated earlier, 1 later
2206.00364 (2022-06)
Elucidating the Design Space of Diffusion-Based Generative Models
2212.00774 (2022-12)
Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generation
2304.10261 (2023-04)
Anything-3D: Towards Single-view Anything Reconstruction in the Wild
load_and_preprocess 2 other papers
2 later
2306.16928 (2023-06)
One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimization
2406.03720 (2024-06)
JIGMARK: A Black-Box Approach for Enhancing Image Watermarks against Diffusion Model Edits

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

Figure 1: Given a single RGB image of an object, we present Zero-1-to-3, a method to synthesize an image from a specified camera viewpoint. Our approach synthesizes views that contain rich details consistent with the input view for large relative transformations. It also achieves strong zero-shot performance on objects with complex geometry and artistic styles.

For agents

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

get_harvested_code_for_paper("2303.11328")
get_code_for_paper("2303.11328")
have("2303.11328")

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

curl https://syntology.ai/api/ran/2303.11328.json

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

[![Syntology run record](https://syntology.ai/api/ran/2303.11328.svg)](https://syntology.ai/paper/2303.11328)

Connect an agent — have() is free.