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 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="2005.05650")

Code

Syntology Ran 3 of 17 code samples harvested from 4 repositories linked to this paper; 14 have no recorded run. Of those that ran: 1 ran · our draft was wrong; 2 ran with no contract checked.

By repository: official repository: 3 samples from 1 repository, 2 ran; community (archive-listed): 14 samples from 3 repositories, 1 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

pkuxmq/Invertible-Image-Rescaling officialmentioned on GitHubpytorchApache-2.0 report
LCM1999/VolumeRescaling mentioned on GitHubpytorchApache-2.0 report
Ash-Lee233/IRN mindsporenot reachable when probed 2026-09-17 — repositories for recent papers often appear after camera-ready report
JoegameZhou/ms-irn mindsporeApache-2.0 report
smc-x/ms-irn mindsporeApache-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

17 samples harvested; 3 ran; 0 honoured the contract we drafted; 14 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
2ran
14unverified

Licence: 0 of the 17 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 4 repositories linked to this paper, official or community; each sample names its own and says which. “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.

calculate_psnr pkuxmq/Invertible-Image-Rescaling/metrics/calculate_PSNR_SSIM.py official repository ran fingerprinted Apache-2.0 (permissive) · 9394ff2c25b8a988 · report
ssim pkuxmq/Invertible-Image-Rescaling/metrics/calculate_PSNR_SSIM.py official repository ran fingerprinted Apache-2.0 (permissive) · ba721aeacc165234 · report
calculate_ssim pkuxmq/Invertible-Image-Rescaling/metrics/calculate_PSNR_SSIM.py official repository unverified Apache-2.0 (permissive) · 5aef99e58703c44a · report
dict2str JoegameZhou/ms-irn/src/options/options.py community (archive-listed) ran · our draft was wrong Apache-2.0 (permissive) · 40c52ad98161c17b · report
count_parameters andreasfloros/IRN/utils.py community (archive-listed) unverified MIT (permissive) · 01aa7bd3d5f55770 · report
define_IDN LCM1999/VolumeRescaling/codes/models/networks.py community (archive-listed) unverified Apache-2.0 (permissive) · 4045b447f74b1b70 · report
dict_to_nonedict JoegameZhou/ms-irn/src/options/options.py community (archive-listed) unverified Apache-2.0 (permissive) · f729c1e42588847e · report
float_distance LCM1999/VolumeRescaling/codes/models/modules/DistanceField.py community (archive-listed) unverified Apache-2.0 (permissive) · 3516a45279831991 · report
linear_warmup_lr JoegameZhou/ms-irn/src/optim/warmup_cosine_annealing_lr.py community (archive-listed) unverified Apache-2.0 (permissive) · 168634e8dabebd81 · report
linear_warmup_lr JoegameZhou/ms-irn/src/optim/warmup_multisteplr.py community (archive-listed) unverified Apache-2.0 (permissive) · e333b3db3a301339 · report
lr_steps JoegameZhou/ms-irn/src/optim/warmup_multisteplr.py community (archive-listed) unverified Apache-2.0 (permissive) · a6bff4162d391ed8 · report
make_grid JoegameZhou/ms-irn/src/utils/util.py community (archive-listed) unverified Apache-2.0 (permissive) · 13d4333fb600dfdc · report
parse JoegameZhou/ms-irn/src/options/options.py community (archive-listed) unverified Apache-2.0 (permissive) · df072befe275ec6a · report
quantize andreasfloros/IRN/utils.py community (archive-listed) unverified MIT (permissive) · 852a7c9de098c70e · report
rgb2y andreasfloros/IRN/utils.py community (archive-listed) unverified MIT (permissive) · f64366aa6addd1e3 · report
warmup_cosine_annealing_lr JoegameZhou/ms-irn/src/optim/warmup_cosine_annealing_lr.py community (archive-listed) unverified Apache-2.0 (permissive) · e12f338ec31cda18 · report
warmup_step_lr JoegameZhou/ms-irn/src/optim/warmup_multisteplr.py community (archive-listed) unverified Apache-2.0 (permissive) · 85f7744dc00ae425 · report

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