SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · Chung_Solving_3D_Inverse_Problems_Using_Pre-Trained_2D_Diffusion_Models_CVPR_2023_paper · CVPR · 2023

Solving 3D Inverse Problems using Pre-trained 2D Diffusion Models

Jong Ye, Hyungjin Chung, Dohoon Ryu, Michael Mccann, Marc Klasky

Open in the Atlas

Code that ran

10 of 15 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 0 have no contract verdict; 10 failures of our instrument; 5 no recorded run), measured 2026-11-21; 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/Chung_Solving_3D_Inverse_Problems_Using_Pre-Trained_2D_Diffusion_Models_CVPR_2023_paper.json · badge: /api/ran/Chung_Solving_3D_Inverse_Problems_Using_Pre-Trained_2D_Diffusion_Models_CVPR_2023_paper.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
HJ-harry/DiffusionMBIR canonical (classifier label)
classifier basis: census
10 ran · 5 no recorded run
FunctionStatusWhere it lives
classifier_fn_from_tfhub Ran
ran; our contract draft was wrong, not the code
HJ-harry/DiffusionMBIR/evaluation.py
code served (permissive licence) · get_code("6568062089fc0f63")
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 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.

import torch
import torch.nn as nn
import six

torch.manual_seed(0)

class MockInceptionModel(nn.Module):
    """Mock inception model that outputs a dictionary with multiple fields."""
    def __init__(self):
        super(MockInceptionModel, self).__init__()
        self.linear1 = nn.Linear(3, 4)
        self.linear2 = nn.Linear(3, 5)
    
    def forward(self, images):
        # Return a dictionary with multiple output fields
        batch_size = images.shape[0]
        feat1 = self.linear1(images)
        feat2 = self.linear2(images)
        return {
            'logits': feat1,
            'features': feat2,
            'extra': torch.randn(batch_size, 2)
        }

class MockTFNestModule:
    """Mock tf.nest module for testing."""
    @staticmethod
    def map_structure(func, structure):
        if isinstance(structure, dict):
            return {k: func(v) for k, v in structure.items()}
        elif isinstance(structure, (list, tuple)):
            return type(structure)(func(v) for v in structure)
        else:
            return func(structure)

class MockTFCompat:
    """Mock tf.compat module."""
    class v1:
        class layers:
            @staticmethod
            def flatten(x):
                if isinstance(x, torch.Tensor):
                    return x.reshape(x.shape[0], -1)
                return x

class MockTF:
    """Mock TensorFlow module for the function."""
    nest = MockTFNestModule()
    compat = MockTFCompat()

# Monkey patch tf module for the function context
import sys
sys.modules['tensorflow'] = MockTF()

# Create test inputs
inception_model = MockInceptionModel()

# Test case 1: single output field as string
output_fields_str = 'logits'

# Test case 2: multiple output fields as list
output_fields_list = ['logits', 'features']

# Test case 3: None output fields
output_fields_none = None

# Create sample image tensor (batch_size=2, channels=3, height=4, width=4 flattened to 3)
sample_images = torch.randn(2, 3)

ARGS = {
    'output_fields': 'logits',
    'inception_model': inception_model,
    'return_tensor': False
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
six, torch — 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
fft2c_new Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
HJ-harry/DiffusionMBIR/fastmri_utils.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from yazidjanati/mgps, is pointer only (licence: NONE) · get_code("dc2dcfd069e89041")
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 yazidjanati/mgps, 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.

get_act Ran
ran; our contract draft was wrong, not the code
HJ-harry/DiffusionMBIR/models/layers.py
code served (permissive licence) · get_code("db5f935a1d6b4c2c")
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 ReLU. 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 Config:
    def __init__(self, nonlinearity):
        self.model = self
        self.nonlinearity = nonlinearity

# Test with 'relu' as the nonlinearity
config = Config('relu')

ARGS = {
    'config': config
}
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 ReLU — a ReLU output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ReLU 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_data_inverse_scaler Ran
ran; our contract draft was wrong, not the code
HJ-harry/DiffusionMBIR/datasets.py
code served (permissive licence) · get_code("6c419026e778dee2")
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 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.

import torch
import numpy as np
from types import SimpleNamespace

torch.manual_seed(0)

# Build a minimal config object with a data attribute that has a 'centered' field
config = SimpleNamespace()
config.data = SimpleNamespace()
config.data.centered = True

ARGS = {
    "config": config
}
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 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
get_data_scaler Ran
ran; our contract draft was wrong, not the code
HJ-harry/DiffusionMBIR/datasets.py
code served (permissive licence) · get_code("346d2e6cc8b48a5d")
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 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.

import torch
from types import SimpleNamespace

torch.manual_seed(0)

# Create a minimal config object with the data.centered attribute
config = SimpleNamespace(
    data=SimpleNamespace(
        centered=True
    )
)

ARGS = {
    "config": config
}
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 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
get_div_fn Ran
ran; our contract draft was wrong, not the code
HJ-harry/DiffusionMBIR/likelihood.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from rarazafin/score_diffusion_ensemble, is pointer only (licence: NONE) · get_code("0bfcb6b2d940e393")
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 rarazafin/score_diffusion_ensemble, 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.

get_optimizer Ran
ran; our contract draft was wrong, not the code
HJ-harry/DiffusionMBIR/losses.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from hfmei/idc, is pointer only (licence: NONE) · get_code("8ff7c24dade9904c")
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 hfmei/idc, 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.

ncsn_conv1x1 Ran
ran; our contract draft was wrong, not the code
HJ-harry/DiffusionMBIR/models/layers.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from SusanneSchaub/TPDM_Implant_Inpainting, is pointer only (licence: NONE) · get_code("85b2235eb7afaa4f")
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 SusanneSchaub/TPDM_Implant_Inpainting, 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.

optimization_manager Ran
ran; our contract draft was wrong, not the code
HJ-harry/DiffusionMBIR/losses.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from hfmei/idc, is pointer only (licence: NONE) · get_code("366bb8c7035a2fc8")
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 hfmei/idc, 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.

variance_scaling Ran
ran; our contract draft was wrong, not the code
HJ-harry/DiffusionMBIR/models/layers.py
code served (permissive licence) · get_code("3ac11bfe0ae80195")
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 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.

import torch
import numpy as np

torch.manual_seed(0)

ARGS = {
    'scale': 2.0,
    'mode': 'fan_in',
    'distribution': 'normal',
    'in_axis': 1,
    'out_axis': 0,
    'dtype': torch.float32,
    'device': 'cpu'
}
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 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
crop_resize Not yet run
unverified (harvested, no recorded run)
HJ-harry/DiffusionMBIR/datasets.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from hj-harry/ddip3d, is pointer only (licence: NONE) · get_code("8279187d1539ad53")
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 hj-harry/ddip3d, 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. No invocation recorded.

fft2c_old Not yet run
unverified (harvested, no recorded run)
HJ-harry/DiffusionMBIR/fastmri_utils.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from yazidjanati/mgps, is pointer only (licence: NONE) · get_code("d5d761740edb12db")
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 yazidjanati/mgps, 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. No invocation recorded.

get_inception_model Not yet run
unverified (harvested, no recorded run)
HJ-harry/DiffusionMBIR/evaluation.py
code served (permissive licence) · get_code("a139eaf606049a22")
How it ran

no invocation recorded.

ifft2c_old Not yet run
unverified (harvested, no recorded run)
HJ-harry/DiffusionMBIR/fastmri_utils.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from yazidjanati/mgps, is pointer only (licence: NONE) · get_code("d63efa5d2fd536e2")
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 yazidjanati/mgps, 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. No invocation recorded.

load_dataset_stats Not yet run
unverified (harvested, no recorded run)
HJ-harry/DiffusionMBIR/evaluation.py
code served (permissive licence) · get_code("58a6128e1c09da2d")
How it ran

no invocation recorded.

Also present in other papers' code

Of 15 samples lifted from this paper's linked repositories, 15 carry a function identity and 0 do not. Of the 15 distinct functions with an identity, 14 are also present in other papers whose code we hold (14 with at least one paper dated earlier, 0 the same month, 14 later) and 1 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
variance_scaling 28 other papers
6 dated earlier, 14 later, 8 same year, order not determinable
2106.05527 (2021-06)
Soft Truncation: A Universal Training Technique of Score-based Diffusion Model for High Precision Score Estimation
2110.05243 (2021-10)
Score-based diffusion models for accelerated MRI
2205.01490 (2022-05)
Subspace Diffusion Generative Models
and 25 more not named here
ncsn_conv1x1 19 other papers
4 dated earlier, 11 later, 4 same year, order not determinable
2106.05527 (2021-06)
Soft Truncation: A Universal Training Technique of Score-based Diffusion Model for High Precision Score Estimation
2110.05243 (2021-10)
Score-based diffusion models for accelerated MRI
2205.01490 (2022-05)
Subspace Diffusion Generative Models
and 16 more not named here
get_data_inverse_scaler 17 other papers
7 dated earlier, 5 later, 5 same year, order not determinable
2106.05527 (2021-06)
Soft Truncation: A Universal Training Technique of Score-based Diffusion Model for High Precision Score Estimation
2110.05243 (2021-10)
Score-based diffusion models for accelerated MRI
2205.01490 (2022-05)
Subspace Diffusion Generative Models
and 14 more not named here
get_data_scaler 17 other papers
7 dated earlier, 5 later, 5 same year, order not determinable
2106.05527 (2021-06)
Soft Truncation: A Universal Training Technique of Score-based Diffusion Model for High Precision Score Estimation
2110.05243 (2021-10)
Score-based diffusion models for accelerated MRI
2205.01490 (2022-05)
Subspace Diffusion Generative Models
and 14 more not named here
get_act 16 other papers
4 dated earlier, 8 later, 4 same year, order not determinable
2106.05527 (2021-06)
Soft Truncation: A Universal Training Technique of Score-based Diffusion Model for High Precision Score Estimation
2110.05243 (2021-10)
Score-based diffusion models for accelerated MRI
2205.01490 (2022-05)
Subspace Diffusion Generative Models
and 13 more not named here
optimization_manager 16 other papers
8 dated earlier, 4 later, 4 same year, order not determinable
2106.05527 (2021-06)
Soft Truncation: A Universal Training Technique of Score-based Diffusion Model for High Precision Score Estimation
2110.05243 (2021-10)
Score-based diffusion models for accelerated MRI
2205.01490 (2022-05)
Subspace Diffusion Generative Models
and 13 more not named here
get_optimizer 15 other papers
6 dated earlier, 4 later, 5 same year, order not determinable
2110.05243 (2021-10)
Score-based diffusion models for accelerated MRI
2205.01490 (2022-05)
Subspace Diffusion Generative Models
2209.12753 (2022-09)
On Investigating the Conservative Property of Score-Based Generative Models
and 12 more not named here
crop_resize 13 other papers
6 dated earlier, 3 later, 4 same year, order not determinable
2106.05527 (2021-06)
Soft Truncation: A Universal Training Technique of Score-based Diffusion Model for High Precision Score Estimation
2110.05243 (2021-10)
Score-based diffusion models for accelerated MRI
2205.01490 (2022-05)
Subspace Diffusion Generative Models
and 10 more not named here
fft2c_new 12 other papers
1 dated earlier, 10 later, 1 same year, order not determinable
2110.05243 (2021-10)
Score-based diffusion models for accelerated MRI
2303.05754 (2023-03)
Decomposed Diffusion Sampler for Accelerating Large-Scale Inverse Problems
2402.16907 (2024-02)
Diffusion Posterior Proximal Sampling for Image Restoration
and 9 more not named here
get_div_fn 11 other papers
6 dated earlier, 3 later, 2 same year, order not determinable
2106.05527 (2021-06)
Soft Truncation: A Universal Training Technique of Score-based Diffusion Model for High Precision Score Estimation
2205.01490 (2022-05)
Subspace Diffusion Generative Models
2205.13699 (2022-05)
Maximum Likelihood Training of Implicit Nonlinear Diffusion Models
and 8 more not named here
classifier_fn_from_tfhub 9 other papers
4 dated earlier, 3 later, 2 same year, order not determinable
2106.05527 (2021-06)
Soft Truncation: A Universal Training Technique of Score-based Diffusion Model for High Precision Score Estimation
2205.13699 (2022-05)
Maximum Likelihood Training of Implicit Nonlinear Diffusion Models
2206.05564 (2022-06)
gDDIM: Generalized denoising diffusion implicit models
and 6 more not named here
fft2c_old 8 other papers
1 dated earlier, 7 later
2110.05243 (2021-10)
Score-based diffusion models for accelerated MRI
2402.16907 (2024-02)
Diffusion Posterior Proximal Sampling for Image Restoration
2403.17042 (2024-03)
Provably Robust Score-Based Diffusion Posterior Sampling for Plug-and-Play Image Reconstruction
and 5 more not named here
ifft2c_old 8 other papers
1 dated earlier, 7 later
2110.05243 (2021-10)
Score-based diffusion models for accelerated MRI
2402.16907 (2024-02)
Diffusion Posterior Proximal Sampling for Image Restoration
2403.17042 (2024-03)
Provably Robust Score-Based Diffusion Posterior Sampling for Plug-and-Play Image Reconstruction
and 5 more not named here
load_dataset_stats 5 other papers
2 dated earlier, 3 later
2205.01490 (2022-05)
Subspace Diffusion Generative Models
2210.04296 (2022-10)
FP-Diffusion: Improving Score-based Diffusion Models by Enforcing the Underlying Score Fokker-Planck Equation
2405.18816 (2024-05)
Flow Priors for Linear Inverse Problems via Iterative Corrupted Trajectory Matching
and 2 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 2026-11-21.

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. 3D reconstruction results with DiffusionMBIR. First row: measurement, second row: our method, third row: ground truth. Yellow inset: measurement process. Sparse-view tomography: 8-view measurement, Limited-angle tomography: [0 90] • out of [0 180] • angle measurement, Compressed-sensing MRI: 1D uniform sub-sampling of ×2 acceleration. (In-distribution): test data aligned with training data, (Out-of-distribution): test data vastly different from training data.

For agents

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

get_harvested_code_for_paper("Chung_Solving_3D_Inverse_Problems_Using_Pre-Trained_2D_Diffusion_Models_CVPR_2023_paper")
get_code_for_paper("Chung_Solving_3D_Inverse_Problems_Using_Pre-Trained_2D_Diffusion_Models_CVPR_2023_paper")
have("Chung_Solving_3D_Inverse_Problems_Using_Pre-Trained_2D_Diffusion_Models_CVPR_2023_paper")

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

curl https://syntology.ai/api/ran/Chung_Solving_3D_Inverse_Problems_Using_Pre-Trained_2D_Diffusion_Models_CVPR_2023_paper.json

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

[![Syntology run record](https://syntology.ai/api/ran/Chung_Solving_3D_Inverse_Problems_Using_Pre-Trained_2D_Diffusion_Models_CVPR_2023_paper.svg)](https://syntology.ai/paper/Chung_Solving_3D_Inverse_Problems_Using_Pre-Trained_2D_Diffusion_Models_CVPR_2023_paper)

Connect an agent — have() is free.