Papers › Adversarial Diffusion Compression for Real-World Image Super-Resolution

Adversarial Diffusion Compression for Real-World Image Super-Resolution

20 Nov 2024CVPR 2025 1arXiv:2411.13383archive 2025-07-28

Bin Chen, Gehui Li, Rongyuan Wu, Xindong Zhang, Jie Chen, Jian Zhang, Lei Zhang

Real-world image super-resolution (Real-ISR) aims to reconstruct high-resolution images from low-resolution inputs degraded by complex, unknown processes. While many Stable Diffusion (SD)-based Real-ISR methods have achieved remarkable success, their slow, multi-step inference hinders practical deployment. Recent SD-based one-step networks like OSEDiff and S3Diff alleviate this issue but still incur high computational costs due to their reliance on large pretrained SD models. This paper proposes a novel Real-ISR method, AdcSR, by distilling the one-step diffusion network OSEDiff into a streamlined diffusion-GAN model under our Adversarial Diffusion Compression (ADC) framework. We meticulously examine the modules of OSEDiff, categorizing them into two types: (1) Removable (VAE encoder, prompt extractor, text encoder, etc.) and (2) Prunable (denoising UNet and VAE decoder). Since direct removal and pruning can degrade the model's generation capability, we pretrain our pruned VAE decoder to restore its ability to decode images and employ adversarial distillation to compensate for performance loss. This ADC-based diffusion-GAN hybrid design effectively reduces complexity by 73% in inference time, 78% in computation, and 74% in parameters, while preserving the model's generation capability. Experiments manifest that our proposed AdcSR achieves competitive recovery quality on both synthetic and real-world datasets, offering up to 9.3× speedup over previous one-step diffusion-based methods. Code and models are available at https://github.com/Guaishou74851/AdcSR.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2411.13383")

Code

Syntology Ran 2 of 14 code samples harvested from 1 repository linked to this paper; 12 have no recorded run. Of those that ran: 1 ran · our draft was wrong; 1 ran · fixture could not drive it.

By repository: official repository: 14 samples from 1 repository, 2 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

guaishou74851/adcsr officialmentioned in papermentioned on GitHubpytorchApache-2.0 report
cswry/osediff mentioned on GitHubpytorchApache-2.0 report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

14 samples harvested; 2 ran; 0 honoured the contract we drafted; 12 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · our draft was wrong
1ran · fixture could not drive it
12unverified

Licence: 0 of the 14 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from guaishou74851/adcsr. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

window_partition guaishou74851/adcsr/ram/models/swin_transformer.py official repository ran · fixture could not drive it fingerprinted Apache-2.0 (permissive) · 144d10b49baeb8a6 · report
window_reverse guaishou74851/adcsr/ram/models/swin_transformer.py official repository ran · our draft was wrong Apache-2.0 (permissive) · 61bf152e6a42a184 · report
MyCrossAttnDownBlock2D_SD_forward guaishou74851/adcsr/forward.py official repository unverified Apache-2.0 (permissive) · 5829c1d21a42343b · report
MyCrossAttnUpBlock2D_SD_forward guaishou74851/adcsr/forward.py official repository unverified Apache-2.0 (permissive) · 2c09b61bfac07a93 · report
MyUNet2DConditionModel_SD_forward guaishou74851/adcsr/forward.py official repository unverified Apache-2.0 (permissive) · 2b84a8c797f8334c · report
add_lora_to_unet guaishou74851/adcsr/utils.py official repository unverified Apache-2.0 (permissive) · 969db462072820db · report
augment guaishou74851/adcsr/bsr/transforms.py official repository unverified Apache-2.0 (permissive) · 7f124cd33fb750ee · report
find_parent guaishou74851/adcsr/model.py official repository unverified Apache-2.0 (permissive) · ce5c70c01a429c15 · report
interpolate_relative_pos_embed guaishou74851/adcsr/ram/models/swin_transformer.py official repository unverified Apache-2.0 (permissive) · 199b2766250bd139 · report
mesh_grid guaishou74851/adcsr/bsr/degradations.py official repository unverified Apache-2.0 (permissive) · 794d4f7fc184e7e5 · report
mod_crop guaishou74851/adcsr/bsr/transforms.py official repository unverified Apache-2.0 (permissive) · 223d0788b0725dfb · report
paired_random_crop guaishou74851/adcsr/bsr/transforms.py official repository unverified Apache-2.0 (permissive) · 64cd160c586b1bef · report
pdf2 guaishou74851/adcsr/bsr/degradations.py official repository unverified Apache-2.0 (permissive) · 321b9c73d589eb9e · report
sigma_matrix2 guaishou74851/adcsr/bsr/degradations.py official repository unverified Apache-2.0 (permissive) · e3444ff2b9d24600 · report

Tasks

DecoderDenoisingImage Super-ResolutionSuper-Resolution

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

DiffusionPruning

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections