Papers › Self-Asymmetric Invertible Network for Compression-Aware Image Rescaling

Self-Asymmetric Invertible Network for Compression-Aware Image Rescaling

4 Mar 2023arXiv:2303.02353archive 2025-07-28

Jinhai Yang, Mengxi Guo, Shijie Zhao, Junlin Li, Li Zhang

High-resolution (HR) images are usually downscaled to low-resolution (LR) ones for better display and afterward upscaled back to the original size to recover details. Recent work in image rescaling formulates downscaling and upscaling as a unified task and learns a bijective mapping between HR and LR via invertible networks. However, in real-world applications (e.g., social media), most images are compressed for transmission. Lossy compression will lead to irreversible information loss on LR images, hence damaging the inverse upscaling procedure and degrading the reconstruction accuracy. In this paper, we propose the Self-Asymmetric Invertible Network (SAIN) for compression-aware image rescaling. To tackle the distribution shift, we first develop an end-to-end asymmetric framework with two separate bijective mappings for high-quality and compressed LR images, respectively. Then, based on empirical analysis of this framework, we model the distribution of the lost information (including downscaling and compression) using isotropic Gaussian mixtures and propose the Enhanced Invertible Block to derive high-quality/compressed LR images in one forward pass. Besides, we design a set of losses to regularize the learned LR images and enhance the invertibility. Extensive experiments demonstrate the consistent improvements of SAIN across various image rescaling datasets in terms of both quantitative and qualitative evaluation under standard image compression formats (i.e., JPEG and WebP).

PaperPDFCodeCode Syntology ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 5 code samples harvested from 1 repository linked to this paper: 4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 4 samples that ran constructed an object rather than computing a result. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 5 samples from 1 repository, 4 ran (4 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

yang-jin-hai/sain officialmentioned in papermentioned on GitHubpytorchSyntology: 5 samples, 4 ran (0 instrument-failed) · 1 unverified 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

5 samples harvested: 4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 4 samples that ran constructed an object rather than computing a result. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

4ran
1unverified

Licence: 0 of the 5 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 yang-jin-hai/sain. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. For 3 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

yang-jin-hai/sain official repository 5 samples, 4 ran (0 instrument-failed) · 1 unverified
EnhancedInvBlock codes/models/modules/inv_arch.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · c48aa122343168e6 · report fixture: returned EnhancedInvBlock · level recorded 2026-09-22
GaussianMixture codes/models/modules/inv_arch.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 8bcb0eacf71fa11c · report fixture: returned GaussianMixture · level recorded 2026-09-22
HaarDownsampling codes/models/modules/inv_arch.py ran · metamorphic tier: deterministic fingerprinted Apache-2.0 (permissive) · 6638ca9310bdc7bb · report fixture: returned HaarDownsampling · level recorded 2026-09-22
VanillaInvBlock codes/models/modules/inv_arch.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · edd575de9595285c · report fixture: returned VanillaInvBlock · level recorded 2026-09-22
SAINet codes/models/modules/inv_arch.py unverified Apache-2.0 (permissive) · 4b2376db15a9ca0c · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for Self-Asymmetric Invertible Network (SAIN) (graph method: Self-Asymmetric Invertible Network (SAIN)). 5 bricks; individually on a fixture: 4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 4 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

  1. SAINet entry · level 0 · unverified · 4b2376db15a9ca0c
  2. EnhancedInvBlock helper · level 1 · ran · c48aa122343168e6
  3. GaussianMixture helper · level 1 · ran · 8bcb0eacf71fa11c
  4. HaarDownsampling helper · level 1 · ran · 6638ca9310bdc7bb
  5. VanillaInvBlock helper · level 1 · ran · edd575de9595285c

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2303.02353") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Image CompressionImage Rescaling

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Rescaling DIV2K val-q30-2x SAIN PSNR 31.47 #2 of 3 Archive leaderboard report
Image Rescaling DIV2K val-q30-2x SAIN SSIM 0.8747 #2 of 3 Archive leaderboard report
Image Rescaling DIV2K val-q30-4x SAIN PSNR 27.90 #2 of 4 Archive leaderboard report
Image Rescaling DIV2K val-q30-4x SAIN SSIM 0.7745 #2 of 4 Archive leaderboard report
Image Rescaling DIV2K val-q50-2x SAIN PSNR 33.17 #2 of 3 Archive leaderboard report
Image Rescaling DIV2K val-q50-2x SAIN SSIM 0.9082 #2 of 3 Archive leaderboard report
Image Rescaling DIV2K val-q50-4x SAIN PSNR 29.05 #2 of 4 Archive leaderboard report
Image Rescaling DIV2K val-q50-4x SAIN SSIM 0.8088 #2 of 4 Archive leaderboard report
Image Rescaling DIV2K val-q70-2x SAIN PSNR 34.73 #2 of 3 Archive leaderboard report
Image Rescaling DIV2K val-q70-2x SAIN SSIM 0.9296 #2 of 3 Archive leaderboard report
Image Rescaling DIV2K val-q70-4x SAIN PSNR 29.83 #2 of 4 Archive leaderboard report
Image Rescaling DIV2K val-q70-4x SAIN SSIM 0.8272 #2 of 4 Archive leaderboard report
Image Rescaling DIV2K val-q90-2x SAIN PSNR 35.96 #2 of 3 Archive leaderboard report
Image Rescaling DIV2K val-q90-2x SAIN SSIM 0.9419 #2 of 3 Archive leaderboard report
Image Rescaling DIV2K val-q90-4x SAIN PSNR 30.31 #2 of 4 Archive leaderboard report
Image Rescaling DIV2K val-q90-4x SAIN SSIM 0.8367 #2 of 4 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

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