Papers › Invertible Image Rescaling

Invertible Image Rescaling

12 May 2020ECCV 2020 8arXiv:2005.05650archive 2025-07-28

Mingqing Xiao, Shuxin Zheng, Chang Liu, Yaolong Wang, Di He, Guolin Ke, Jiang Bian, Zhouchen Lin, Tie-Yan Liu

High-resolution digital images are usually downscaled to fit various display screens or save the cost of storage and bandwidth, meanwhile the post-upscaling is adpoted to recover the original resolutions or the details in the zoom-in images. However, typical image downscaling is a non-injective mapping due to the loss of high-frequency information, which leads to the ill-posed problem of the inverse upscaling procedure and poses great challenges for recovering details from the downscaled low-resolution images. Simply upscaling with image super-resolution methods results in unsatisfactory recovering performance. In this work, we propose to solve this problem by modeling the downscaling and upscaling processes from a new perspective, i.e. an invertible bijective transformation, which can largely mitigate the ill-posed nature of image upscaling. We develop an Invertible Rescaling Net (IRN) with deliberately designed framework and objectives to produce visually-pleasing low-resolution images and meanwhile capture the distribution of the lost information using a latent variable following a specified distribution in the downscaling process. In this way, upscaling is made tractable by inversely passing a randomly-drawn latent variable with the low-resolution image through the network. Experimental results demonstrate the significant improvement of our model over existing methods in terms of both quantitative and qualitative evaluations of image upscaling reconstruction from downscaled images.

PaperPDFConference PDFCodeCode Syntology ran

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 17 code samples harvested from 4 repositories linked to this paper: 15 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 2 honoured, 0 violated, 12 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 3 samples from 1 repository, 3 ran (3 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 14 samples from 3 repositories, 12 ran (11 with no instrument failure; 1 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.

No sample is linked to this paper from 2 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

pkuxmq/Invertible-Image-Rescaling officialmentioned on GitHubpytorchApache-2.0Syntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
LCM1999/VolumeRescaling mentioned on GitHubpytorchApache-2.0Syntology: 2 samples, 1 ran (0 instrument-failed) · 1 unverified report
2023-MindSpore-4/Code-5 mindsporeSyntology: not harvested report
Ash-Lee233/IRN mindsporenot reachable when probed 2026-09-17 — repositories for recent papers often appear after camera-readySyntology: not harvested report
JoegameZhou/ms-irn mindsporeApache-2.0Syntology: 9 samples, 8 ran (1 instrument-failed) · 1 unverified report
Mind23-2/MindCode-101 mindsporeSyntology: not harvested report
Mind23-2/MindCode-3 mindsporeSyntology: not harvested report
andreasfloros/IRN pytorchMITSyntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
jiean001/models_m mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to HyperText: Endowing FastText with Hyperbolic Geometry (arXiv:2010.16143; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
mindspore-ai/models mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to AdaBin: Improving Binary Neural Networks with Adaptive Binary Sets (arXiv:2208.08084; that paper's own run record: 4 ran (of which 0 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); nothing checks that they implement this paper's method. report
smc-x/ms-irn mindsporeApache-2.0Syntology: not harvested 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

17 samples harvested: 15 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 2 honoured, 0 violated, 12 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · honoured contract
1ran · our draft was wrong
12ran
2unverified

Licence: 3 of the 17 samples are pointer only, meaning Syntology does not serve that copy's text. For 3 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 4 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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”. “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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

pkuxmq/Invertible-Image-Rescaling official repository 3 samples, 3 ran (0 instrument-failed) · 0 unverified
calculate_psnr in 51 papers metrics/calculate_PSNR_SSIM.py ran · honoured contract fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · 9394ff2c25b8a988 · report fixture: signature img1:ndarray/3/int, img2:ndarray/3/int · returned float · level recorded 2026-09-24
calculate_ssim in 24 papers metrics/calculate_PSNR_SSIM.py ran fingerprinted Apache-2.0 (permissive) · 5aef99e58703c44a · report fixture: signature img1:ndarray/3/int, img2:ndarray/3/int · returned float64 · level recorded 2026-09-25
ssim in 112 papers metrics/calculate_PSNR_SSIM.py ran · honoured contract fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · ba721aeacc165234 · report fixture: signature img1:ndarray/2/int, img2:ndarray/2/int · returned float64 · level recorded 2026-09-24
LCM1999/VolumeRescaling community (archive-listed) 2 samples, 1 ran (0 instrument-failed) · 1 unverified
float_distance codes/models/modules/DistanceField.py ran fingerprinted Apache-2.0 (permissive) · 3516a45279831991 · report fixture: signature v1:ndarray/1/float, v2:ndarray/1/float · returned float64 · level recorded 2026-09-24
define_IDN codes/models/networks.py unverified Apache-2.0 (permissive) · 4045b447f74b1b70 · report
JoegameZhou/ms-irn community (archive-listed) 9 samples, 8 ran (1 instrument-failed) · 1 unverified
dict2str in 30 papers src/options/options.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · 40c52ad98161c17b · report fixture: signature opt:dict/0/?, indent_l:int/0/int · returned str · level recorded 2026-09-22
dict_to_nonedict in 22 papers src/options/options.py ran Apache-2.0 (permissive) · f729c1e42588847e · report fixture: signature opt:dict/0/? · returned NoneDict · level recorded 2026-09-24
linear_warmup_lr in 10 papers src/optim/warmup_cosine_annealing_lr.py ran fingerprinted Apache-2.0 (permissive) · 168634e8dabebd81 · report fixture: signature current_step:int/0/int, warmup_steps:int/0/int, base_lr:float/0/float, init_lr:float/0/float · returned float · level recorded 2026-09-24
linear_warmup_lr in 10 papers src/optim/warmup_multisteplr.py ran fingerprinted Apache-2.0 (permissive) · e333b3db3a301339 · report fixture: signature current_step:int/0/int, warmup_steps:int/0/int, base_lr:float/0/float, init_lr:float/0/float · returned float · level recorded 2026-09-24
lr_steps src/optim/warmup_multisteplr.py ran Apache-2.0 (permissive) · a6bff4162d391ed8 · report fixture: signature global_step:int/0/int, lr_init:float/0/float, lr_max:float/0/float, warmup_epochs:int/0/int, total_epochs:int/0/int, steps_per_epoch:int/0/int · returned ndarray · level recorded 2026-09-24
make_grid in 27 papers src/utils/util.py ran fingerprinted Apache-2.0 (permissive) · 13d4333fb600dfdc · report fixture: signature tensor:Tensor/4/float · returned ndarray · level recorded 2026-09-24
warmup_cosine_annealing_lr in 5 papers src/optim/warmup_cosine_annealing_lr.py ran Apache-2.0 (permissive) · e12f338ec31cda18 · report fixture: signature lr:float/0/float, steps_per_epoch:int/0/int, warmup_epochs:int/0/int, max_epoch:int/0/int, T_max:int/0/int, eta_min:float/0/float · returned ndarray · level recorded 2026-09-24
warmup_step_lr in 7 papers src/optim/warmup_multisteplr.py ran Apache-2.0 (permissive) · 85f7744dc00ae425 · report fixture: signature lr:float/0/float, lr_epochs:list/1/int, steps_per_epoch:int/0/int, warmup_epochs:int/0/int, max_epoch:int/0/int, gamma:float/0/float · returned ndarray · level recorded 2026-09-24
parse in 85 papers src/options/options.py unverified Apache-2.0 (permissive) · df072befe275ec6a · report
andreasfloros/IRN community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
count_parameters in 278 papers utils.py ran MIT (permissive) · 01aa7bd3d5f55770 · report fixture: signature model:callable/0/? · returned int · level recorded 2026-09-24
quantize in 70 papers
census: 8 implementations from 11 papers, 6 distinct outputs across 3 buckets, one shared input per bucket
utils.py ran fingerprinted MIT (permissive) · 852a7c9de098c70e · report fixture: signature inpt:Tensor/2/float · returned Tensor · level recorded 2026-09-24
rgb2y utils.py ran fingerprinted MIT (permissive) · f64366aa6addd1e3 · report fixture: signature inpt:Tensor/4/float · returned Tensor · level recorded 2026-09-24

Tasks

Image RescalingImage Super-ResolutionSuper-Resolution

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Rescaling BSD100-2x IRN PSNR 41.32 #2 of 2 Archive leaderboard report
Image Rescaling BSD100-2x IRN SSIM 0.9876 #2 of 2 Archive leaderboard report
Image Rescaling BSD100-4x IRN PSNR 31.64 #2 of 2 Archive leaderboard report
Image Rescaling BSD100-4x IRN SSIM 0.8826 #2 of 2 Archive leaderboard report
Image Rescaling DIV2K val-2x IRN PSNR 44.32 #2 of 2 Archive leaderboard report
Image Rescaling DIV2K val-2x IRN SSIM 0.9908 #2 of 2 Archive leaderboard report
Image Rescaling DIV2K val-4x IRN PSNR 35.07 #2 of 2 Archive leaderboard report
Image Rescaling DIV2K val-4x IRN SSIM 0.9318 #2 of 2 Archive leaderboard report
Image Rescaling DIV2K val-q30-2x IRN PSNR 29.24 #3 of 3 Archive leaderboard report
Image Rescaling DIV2K val-q30-2x IRN SSIM 0.8051 #3 of 3 Archive leaderboard report
Image Rescaling DIV2K val-q30-4x IRN PSNR 25.98 #3 of 4 Archive leaderboard report
Image Rescaling DIV2K val-q30-4x IRN SSIM 0.6867 #3 of 4 Archive leaderboard report
Image Rescaling DIV2K val-q50-2x IRN PSNR 30.20 #3 of 3 Archive leaderboard report
Image Rescaling DIV2K val-q50-2x IRN SSIM 0.8342 #3 of 3 Archive leaderboard report
Image Rescaling DIV2K val-q50-4x IRN PSNR 26.62 #3 of 4 Archive leaderboard report
Image Rescaling DIV2K val-q50-4x IRN SSIM 0.7096 #3 of 4 Archive leaderboard report
Image Rescaling DIV2K val-q70-2x IRN PSNR 31.14 #3 of 3 Archive leaderboard report
Image Rescaling DIV2K val-q70-2x IRN SSIM 0.8604 #3 of 3 Archive leaderboard report
Image Rescaling DIV2K val-q70-4x IRN PSNR 27.24 #3 of 4 Archive leaderboard report
Image Rescaling DIV2K val-q70-4x IRN SSIM 0.7328 #3 of 4 Archive leaderboard report
Image Rescaling DIV2K val-q90-2x IRN PSNR 32.91 #3 of 3 Archive leaderboard report
Image Rescaling DIV2K val-q90-2x IRN SSIM 0.9023 #3 of 3 Archive leaderboard report
Image Rescaling DIV2K val-q90-4x IRN PSNR 28.42 #3 of 4 Archive leaderboard report
Image Rescaling DIV2K val-q90-4x IRN SSIM 0.7777 #3 of 4 Archive leaderboard report
Image Rescaling Set14-2x IRN PSNR 40.79 #2 of 2 Archive leaderboard report
Image Rescaling Set14-2x IRN SSIM 0.9778 #2 of 2 Archive leaderboard report
Image Rescaling Set14-4x IRN PSNR 32.67 #2 of 2 Archive leaderboard report
Image Rescaling Set14-4x IRN SSIM 0.9015 #2 of 2 Archive leaderboard report
Image Rescaling Set5-2x IRN PSNR 43.99 #2 of 2 Archive leaderboard report
Image Rescaling Set5-2x IRN SSIM 0.9871 #2 of 2 Archive leaderboard report
Image Rescaling Set5-4x IRN PSNR 36.19 #2 of 2 Archive leaderboard report
Image Rescaling Set5-4x IRN SSIM 0.9451 #2 of 2 Archive leaderboard report
Image Rescaling Urban100-2x IRN PSNR 39.92 #2 of 2 Archive leaderboard report
Image Rescaling Urban100-2x IRN SSIM 0.9865 #2 of 2 Archive leaderboard report
Image Rescaling Urban100-4x IRN PSNR 31.41 #1 of 2 Archive leaderboard report
Image Rescaling Urban100-4x IRN SSIM 0.9157 #1 of 2 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.

Methods

IRN

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