English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

A 360{\deg} perception of scene geometry is essential for automated driving,notably for parking and urban driving scenarios. Typically, it is achievedusing surround-view fisheye cameras, focusing on the near-field area around thevehicle. The majority of current depth estimation approaches focus on employingjust a single camera, which cannot be straightforwardly generalized to multiplecameras. The depth estimation model must be tested on a variety of camerasequipped to millions of cars with varying camera geometries. Even within asingle car, intrinsics vary due to manufacturing tolerances. Deep learningmodels are sensitive to these changes, and it is practically infeasible totrain and test on each camera variant. As a result, we present novelcamera-geometry adaptive multi-scale convolutions which utilize the cameraparameters as a conditional input, enabling the model to generalize topreviously unseen fisheye cameras. Additionally, we improve the distanceestimation by pairwise and patchwise vector-based self-attention encodernetworks. We evaluate our approach on the Fisheye WoodScape surround-viewdataset, significantly improving over previous approaches. We also show ageneralization of our approach across different camera viewing angles andperform extensive experiments to support our contributions. To enablecomparison with other approaches, we evaluate the front camera data on theKITTI dataset (pinhole camera images) and achieve state-of-the-art performanceamong self-supervised monocular methods. An overview video with qualitativeresults is provided at https://youtu.be/bmX0UcU9wtA. Baseline code and datasetwill be made public.

SVDistNet: Self-Supervised Near-Field Distance Estimation on Surround View Fisheye Cameras