Papers › OSRT: Omnidirectional Image Super-Resolution with Distortion-aware Transformer

OSRT: Omnidirectional Image Super-Resolution with Distortion-aware Transformer

7 Feb 2023CVPR 2023 1arXiv:2302.03453archive 2025-07-28

Fanghua Yu, Xintao Wang, Mingdeng Cao, Gen Li, Ying Shan, Chao Dong

Omnidirectional images (ODIs) have obtained lots of research interest for immersive experiences. Although ODIs require extremely high resolution to capture details of the entire scene, the resolutions of most ODIs are insufficient. Previous methods attempt to solve this issue by image super-resolution (SR) on equirectangular projection (ERP) images. However, they omit geometric properties of ERP in the degradation process, and their models can hardly generalize to real ERP images. In this paper, we propose Fisheye downsampling, which mimics the real-world imaging process and synthesizes more realistic low-resolution samples. Then we design a distortion-aware Transformer (OSRT) to modulate ERP distortions continuously and self-adaptively. Without a cumbersome process, OSRT outperforms previous methods by about 0.2dB on PSNR. Moreover, we propose a convenient data augmentation strategy, which synthesizes pseudo ERP images from plain images. This simple strategy can alleviate the over-fitting problem of large networks and significantly boost the performance of ODISR. Extensive experiments have demonstrated the state-of-the-art performance of our OSRT. Codes and models will be available at https://github.com/Fanghua-Yu/OSRT.

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="2302.03453")

Code

Syntology Ran 6 of 12 code samples harvested from 1 repository linked to this paper; 6 have no recorded run. Of those that ran: 1 ran · fixture could not drive it; 5 ran with no contract checked.

By repository: official repository: 12 samples from 1 repository, 6 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

fanghua-yu/osrt officialmentioned in papermentioned on GitHubpytorchMIT 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

12 samples harvested; 6 ran; 0 honoured the contract we drafted; 6 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 · fixture could not drive it
5ran
6unverified

Licence: 0 of the 12 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 fanghua-yu/osrt. “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.

drop_path fanghua-yu/osrt/odisr/archs/osrt_arch.py official repository ran · fixture could not drive it MIT (permissive) · 9ea4d5b8b4d5ef2f · report
erp_downsample_fisheye fanghua-yu/osrt/odisr/utils/erp_downsample.py official repository ran MIT (permissive) · 5e1d924a740460bd · report
genERP fanghua-yu/osrt/odisr/metrics/odi_metric.py official repository ran fingerprinted MIT (permissive) · 5753656385b79840 · report
make_coord fanghua-yu/osrt/odisr/utils/erp_downsample.py official repository ran MIT (permissive) · 0eb884d36fb9be8b · report
u fanghua-yu/osrt/odisr/utils/erp_downsample.py official repository ran fingerprinted MIT (permissive) · 7e200e5d7630e13b · report
worker fanghua-yu/osrt/odisr/utils/extract_subimage.py official repository ran MIT (permissive) · d6a27ce76783f4d2 · report
default_conv fanghua-yu/osrt/odisr/archs/launet_arch.py official repository unverified MIT (permissive) · 0e1c2934ef064fde · report
make_model fanghua-yu/osrt/odisr/archs/launet_arch.py official repository unverified MIT (permissive) · 12ec7fbd4ce6cf35 · report
pers2erp fanghua-yu/osrt/odisr/utils/pers2erp.py official repository unverified MIT (permissive) · ecf6f60a59e10643 · report
test_TLC fanghua-yu/osrt/odisr/models/rcan_model.py official repository unverified MIT (permissive) · 77ed7cd07319a3e6 · report
window_partition fanghua-yu/osrt/odisr/archs/osrt_arch.py official repository unverified MIT (permissive) · f9c4a5ff2a55d09f · report
window_reverse fanghua-yu/osrt/odisr/archs/osrt_arch.py official repository unverified MIT (permissive) · e641230dff80d607 · report

Tasks

Data AugmentationERPImage Super-ResolutionSuper-Resolution

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

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