Papers › High-Resolution Photorealistic Image Translation in Real-Time: A Laplacian Pyramid...

High-Resolution Photorealistic Image Translation in Real-Time: A Laplacian Pyramid Translation Network

19 May 2021CVPR 2021 1arXiv:2105.09188archive 2025-07-28

Jie Liang, Hui Zeng, Lei Zhang

Existing image-to-image translation (I2IT) methods are either constrained to low-resolution images or long inference time due to their heavy computational burden on the convolution of high-resolution feature maps. In this paper, we focus on speeding-up the high-resolution photorealistic I2IT tasks based on closed-form Laplacian pyramid decomposition and reconstruction. Specifically, we reveal that the attribute transformations, such as illumination and color manipulation, relate more to the low-frequency component, while the content details can be adaptively refined on high-frequency components. We consequently propose a Laplacian Pyramid Translation Network (LPTN) to simultaneously perform these two tasks, where we design a lightweight network for translating the low-frequency component with reduced resolution and a progressive masking strategy to efficiently refine the high-frequency ones. Our model avoids most of the heavy computation consumed by processing high-resolution feature maps and faithfully preserves the image details. Extensive experimental results on various tasks demonstrate that the proposed method can translate 4K images in real-time using one normal GPU while achieving comparable transformation performance against existing methods. Datasets and codes are available: https://github.com/csjliang/LPTN.

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="2105.09188")

Code

Syntology Ran 3 of 5 code samples harvested from 1 repository linked to this paper; 2 have no recorded run. Of those that ran: 3 ran with no contract checked.

By repository: official repository: 5 samples from 1 repository, 3 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

csjliang/LPTN officialmentioned in papermentioned on GitHubpytorch 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; 3 ran; 0 honoured the contract we drafted; 2 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.

3ran
2unverified

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 csjliang/LPTN. “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.

ResidualBlock csjliang/LPTN/codes/models/archs/LPTN_arch.py official repository ran · metamorphic tier: invariant Apache-2.0 (permissive) · a40fefd4ac78d15a · report
Trans_high csjliang/LPTN/codes/models/archs/LPTN_arch.py official repository ran Apache-2.0 (permissive) · 4d7ba437b9821d9d · report
Trans_low csjliang/LPTN/codes/models/archs/LPTN_arch.py official repository ran · metamorphic tier: invariant fingerprinted Apache-2.0 (permissive) · f65067dbfac1d4b4 · report
LPTN csjliang/LPTN/codes/models/archs/LPTN_arch.py official repository unverified Apache-2.0 (permissive) · b666168472c0a667 · report
Lap_Pyramid_Conv csjliang/LPTN/codes/models/archs/LPTN_arch.py official repository unverified Apache-2.0 (permissive) · 72fd4a39def792cf · report

Tasks

4kAttributeColor ManipulationImage EnhancementImage-to-Image TranslationPhoto RetouchingTranslation

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Photo Retouching MIT-Adobe 5k LPTN (L=3) PSNR 22.02 #5 of 5 Archive leaderboard report
Photo Retouching MIT-Adobe 5k LPTN (L=3) SSIM 0.879 #5 of 5 Archive leaderboard report
Photo Retouching MIT-Adobe 5k (1080p) LPTN (L=3) PSNR 22.09 #1 of 2 Archive leaderboard report
Photo Retouching MIT-Adobe 5k (1080p) LPTN (L=3) SSIM 0.883 #1 of 2 Archive leaderboard report
Photo Retouching MIT-Adobe 5k (1080p) DPE PSNR 21.94 #2 of 2 Archive leaderboard report
Photo Retouching MIT-Adobe 5k (1080p) DPE SSIM 0.885 #2 of 2 Archive leaderboard report
Photo Retouching MIT-Adobe 5k (480p) LPTN (L=3) PSNR 22.12 #1 of 2 Archive leaderboard report
Photo Retouching MIT-Adobe 5k (480p) LPTN (L=3) SSIM 0.878 #1 of 2 Archive leaderboard report
Photo Retouching MIT-Adobe 5k (480p) DPE PSNR 21.99 #2 of 2 Archive leaderboard report
Photo Retouching MIT-Adobe 5k (480p) DPE SSIM 0.875 #2 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

Convolution

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