Papers › Tangent Images for Mitigating Spherical Distortion

Tangent Images for Mitigating Spherical Distortion

19 Dec 2019CVPR 2020 6arXiv:1912.09390archive 2025-07-28

Marc Eder, Mykhailo Shvets, John Lim, Jan-Michael Frahm

In this work, we propose "tangent images," a spherical image representation that facilitates transferable and scalable 360° computer vision. Inspired by techniques in cartography and computer graphics, we render a spherical image to a set of distortion-mitigated, locally-planar image grids tangent to a subdivided icosahedron. By varying the resolution of these grids independently of the subdivision level, we can effectively represent high resolution spherical images while still benefiting from the low-distortion icosahedral spherical approximation. We show that training standard convolutional neural networks on tangent images compares favorably to the many specialized spherical convolutional kernels that have been developed, while also scaling efficiently to handle significantly higher spherical resolutions. Furthermore, because our approach does not require specialized kernels, we show that we can transfer networks trained on perspective images to spherical data without fine-tuning and with limited performance drop-off. Finally, we demonstrate that tangent images can be used to improve the quality of sparse feature detection on spherical images, illustrating its usefulness for traditional computer vision tasks like structure-from-motion and SLAM.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

meder411/Tangent-Images officialmentioned in papermentioned on GitHubpytorchNOASSERTION 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

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Semantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Semantic Segmentation Stanford2D3D Panoramic Tangent (ResNet-101) mAcc 65.2 #19 of 25 Archive leaderboard report
Semantic Segmentation Stanford2D3D Panoramic Tangent (ResNet-101) mIoU 45.6% #19 of 25 Archive leaderboard report
Semantic Segmentation Stanford2D3D Panoramic - RGBD Tangent (ResNet-101) mAcc 69.1 #2 of 3 Archive leaderboard report
Semantic Segmentation Stanford2D3D Panoramic - RGBD Tangent (ResNet-101) mIoU 51.9 #2 of 3 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.

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