AI Paper Atlas

Research map / Detection and segmentation / CNN features

SphereNet: Learning Spherical Representations for Detection and Classification in Omnidirectional Images

Benjamin Coors, Alexandru Paul Condurache, Andreas Geiger

ECCV 2018 · Detection and segmentation › CNN features · approach: Region-based and query-based detectors · 381 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace regular convolution with SphereNet kernels (bilinear interpolation)EquirectCNN · Omni-MNISTtest error (%): 9.61 -> 5.59Improved
use nearest neighbor instead of bilinear interpolation in SphereNet (ablation)SphereNet · Omni-MNISTtest error (%): 5.59 -> 7.03Hurt
use uniform sphere sampling instead of equirectangular grid (NN) (ablation)SphereNet · Omni-MNISTtest error (%): 7.03 -> 7.16No clear effect
use uniform sphere sampling instead of equirectangular grid (NN) (ablation)SphereNet · Omni-MNISTnumber of parameters: 196K -> 144KImproved
add Spherical Transformer Network to EquirectCNNEquirectCNN · Omni-MNISTtest error (%): 9.61 -> 8.22Improved
add Spherical Transformer Network to EquirectCNNEquirectCNN · FlyingCars testmAP (%): 41.57 -> 38.91Hurt
use cube map representation instead of equirectangular inputCNN · Omni-MNISTtest error (%): 9.61 -> 10.03Hurt
use cube map representation instead of equirectangular inputCNN · FlyingCars testmAP (%): 41.57 -> 48.42Improved
enlarge kernel size towards the poles (EquirectCNN++)EquirectCNN · FlyingCars testmAP (%): 41.57 -> 45.65Improved
use SphereNet (NN) instead of cube map CNNSphere-SSD · FlyingCars testmAP (%): 48.42 -> 50.18Improved
use SphereNet (NN) instead of cube map CNN when transferring a KITTI-trained detectorSphere-SSD · OmPaCa test (transfer from KITTI)mAP (%): 34.19 -> 49.73Improved
use SphereNet (NN) instead of equirectangular CNN when transferring a KITTI-trained detectorSphere-SSD · OmPaCa test (transfer from KITTI)mAP (%): 43.43 -> 49.73Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy