SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2303.09472 · ICCV · 2023

DiffIR: Efficient Diffusion Model for Image Restoration

Yulun Zhang, Luc Gool, Yapeng Tian, Bin Xia, Wenming Yang, Xinglong Wu, Yitong Wang, Shiyin Wang

arXiv · PDF · Open in the Atlas

Code that ran

2 of 4 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 1 has no contract verdict; 1 failure of our instrument; 2 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/2303.09472.json · badge: /api/ran/2303.09472.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
Zj-BinXia/DiffIR canonical (classifier label)
classifier basis not recorded on the link
2 ran · 2 no recorded run
FunctionStatusWhere it lives
get_model_activation Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
Zj-BinXia/DiffIR/DiffIR-SRGAN/utils_modelsummary.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from guanys-dar/mgdn, is pointer only (licence: NONE) · get_code("236d44054916d8c6")
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 guanys-dar/mgdn, 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.

pad_test Ran
ran on a synthesized input
Zj-BinXia/DiffIR/DiffIR-RealSR/inference_diffir.py
code served (permissive licence) · get_code("72c02bbb03c1e4e1")
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. 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)

# Construct arguments for pad_test function
# The function expects:
# - lq: a tensor with shape (batch, channels, height, width)
# - scale: an integer (1, 2, or other)

lq = torch.randn(2, 3, 15, 20)  # batch=2, channels=3, height=15, width=20
scale = 2

ARGS = {
    'lq': lq,
    '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 tuple — a tuple output has no array shape of its own; none is 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_model_complexity_info Not yet run
unverified (harvested, no recorded run)
Zj-BinXia/DiffIR/DiffIR-SRGAN/utils_modelsummary.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from guanys-dar/mgdn, is pointer only (licence: NONE) · get_code("6ef91108ba92f025")
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 guanys-dar/mgdn, 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_model_flops Not yet run
unverified (harvested, no recorded run)
Zj-BinXia/DiffIR/DiffIR-SRGAN/utils_modelsummary.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from guanys-dar/mgdn, is pointer only (licence: NONE) · get_code("e39e724b057d5bec")
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 guanys-dar/mgdn, 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.

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 3 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
get_model_activation 4 other papers
3 dated earlier, 1 later
2205.05675 (2022-05)
NTIRE 2022 Challenge on Efficient Super-Resolution: Methods and Results
2207.13784 (2022-07)
AvatarPoser: Articulated Full-Body Pose Tracking from Sparse Motion Sensing
2211.05910 (2022-11)
Efficient and Accurate Quantized Image Super-Resolution on Mobile NPUs, Mobile AI & AIM 2022 challenge: Report
and 1 more not named here
get_model_complexity_info 4 other papers
3 dated earlier, 1 later
2205.05675 (2022-05)
NTIRE 2022 Challenge on Efficient Super-Resolution: Methods and Results
2207.13784 (2022-07)
AvatarPoser: Articulated Full-Body Pose Tracking from Sparse Motion Sensing
2211.05910 (2022-11)
Efficient and Accurate Quantized Image Super-Resolution on Mobile NPUs, Mobile AI & AIM 2022 challenge: Report
and 1 more not named here
get_model_flops 4 other papers
3 dated earlier, 1 later
2201.06776 (2022-01)
Pruning-aware Sparse Regularization for Network Pruning
2205.05675 (2022-05)
NTIRE 2022 Challenge on Efficient Super-Resolution: Methods and Results
2207.13784 (2022-07)
AvatarPoser: Articulated Full-Body Pose Tracking from Sparse Motion Sensing
and 1 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

Diffusion model (DM) has achieved SOTA performance by modeling the image synthesis process into a sequential application of a denoising network. However, different from image synthesis, image restoration (IR) has a strong constraint to generate results in accordance with ground-truth. Thus, for IR, traditional DMs running massive iterations on a large model to estimate whole images or feature maps is inefficient. To address this issue, we propose an efficient DM for IR (DiffIR), which consists of a compact IR prior extraction network (CPEN), dynamic IR transformer (DIRformer), and denoising network. Specifically, DiffIR has two training stages: pretraining and training DM. In pretraining, we input ground-truth images into CPEN S1 to capture a compact IR prior representation (IPR) to guide DIRformer. In the second stage, we train the DM to directly estimate the same IRP as pretrained CPEN S1 only using LQ images. We observe that since the IPR is only a compact vector, DiffIR can use fewer iterations than traditional DM to obtain accurate estimations and generate more stable and realistic results. Since the iterations are few, our Dif-fIR can adopt a joint optimization of CPEN S2 , DIRformer, and denoising network, which can further reduce the estimation error influence. We conduct extensive experiments on several IR tasks and achieve SOTA performance while consuming less computational costs. Code is available at https://github.com/Zj-BinXia/DiffIR.

For agents

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

get_harvested_code_for_paper("2303.09472")
get_code_for_paper("2303.09472")
have("2303.09472")

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

curl https://syntology.ai/api/ran/2303.09472.json

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

[![Syntology run record](https://syntology.ai/api/ran/2303.09472.svg)](https://syntology.ai/paper/2303.09472)

Connect an agent — have() is free.