Papers › HEAL-SWIN: A Vision Transformer On The Sphere

HEAL-SWIN: A Vision Transformer On The Sphere

14 Jul 2023CVPR 2024 1arXiv:2307.07313archive 2025-07-28

Oscar Carlsson, Jan E. Gerken, Hampus Linander, Heiner Spieß, Fredrik Ohlsson, Christoffer Petersson, Daniel Persson

High-resolution wide-angle fisheye images are becoming more and more important for robotics applications such as autonomous driving. However, using ordinary convolutional neural networks or vision transformers on this data is problematic due to projection and distortion losses introduced when projecting to a rectangular grid on the plane. We introduce the HEAL-SWIN transformer, which combines the highly uniform Hierarchical Equal Area iso-Latitude Pixelation (HEALPix) grid used in astrophysics and cosmology with the Hierarchical Shifted-Window (SWIN) transformer to yield an efficient and flexible model capable of training on high-resolution, distortion-free spherical data. In HEAL-SWIN, the nested structure of the HEALPix grid is used to perform the patching and windowing operations of the SWIN transformer, enabling the network to process spherical representations with minimal computational overhead. We demonstrate the superior performance of our model on both synthetic and real automotive datasets, as well as a selection of other image datasets, for semantic segmentation, depth regression and classification tasks. Our code is publicly available at https://github.com/JanEGerken/HEAL-SWIN.

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="2307.07313")

Code

Syntology Ran 11 of 11 code samples harvested from 1 repository linked to this paper; 0 have no recorded run. Of those that ran: 1 ran · our draft was wrong; 1 ran · fixture could not drive it; 9 ran with no contract checked.

By repository: official repository: 11 samples from 1 repository, 11 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

janegerken/heal-swin 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

11 samples harvested; 11 ran; 0 honoured the contract we drafted; 0 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
1ran · fixture could not drive it
9ran

Licence: 0 of the 11 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 janegerken/heal-swin. “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.

window_partition janegerken/heal-swin/heal_swin/models_torch/swin_mlp.py official repository ran · fixture could not drive it fingerprinted MIT (permissive) · 144d10b49baeb8a6 · report
get_nest_win_idcs janegerken/heal-swin/heal_swin/models_torch/hp_windowing.py official repository ran MIT (permissive) · 7f47b177b3d0bea8 · report
get_non_inf_non_nan_idxs janegerken/heal-swin/heal_swin/evaluation/custom_metrics.py official repository ran MIT (permissive) · 56d5a522dd1aeb67 · report
l1_loss janegerken/heal-swin/heal_swin/training/loss_depth_regression.py official repository ran MIT (permissive) · 53ceff2b6014c033 · report
mean_log_var_loss janegerken/heal-swin/heal_swin/training/loss_depth_regression.py official repository ran MIT (permissive) · 161a139760517c8c · report
mse janegerken/heal-swin/heal_swin/training/loss_depth_regression.py official repository ran MIT (permissive) · 920963401bbcecee · report
window_partition janegerken/heal-swin/heal_swin/models_torch/hp_windowing.py official repository ran fingerprinted MIT (permissive) · 53e2f7029b4d01c9 · report
window_partition janegerken/heal-swin/heal_swin/models_torch/swin_transformer.py official repository ran MIT (permissive) · 015c320e93487a73 · report
window_reverse janegerken/heal-swin/heal_swin/models_torch/swin_mlp.py official repository ran · our draft was wrong MIT (permissive) · 61bf152e6a42a184 · report
window_reverse janegerken/heal-swin/heal_swin/models_torch/hp_windowing.py official repository ran MIT (permissive) · a1df30ea1ff44d0a · report
window_reverse janegerken/heal-swin/heal_swin/models_torch/swin_transformer.py official repository ran MIT (permissive) · 44f1f7e6cbeb0224 · report

Tasks

Autonomous DrivingSemantic Segmentation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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