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

In the perception task of autonomous driving, multi-modal methods have becomea trend due to the complementary characteristics of LiDAR point clouds andimage data. However, the performance of multi-modal methods is usually limitedby the sparsity of the point cloud or the noise problem caused by themisalignment between LiDAR and the camera. To solve these two problems, wepresent a new concept, Voxel Region (VR), which is obtained by projecting thesparse local point clouds in each voxel dynamically. And we propose a novelfusion method named Sparse-to-Dense Voxel Region Fusion (SDVRF). Specifically,more pixels of the image feature map inside the VR are gathered to supplementthe voxel feature extracted from sparse points and achieve denser fusion.Meanwhile, different from prior methods, which project the size-fixed grids,our strategy of generating dynamic regions achieves better alignment and avoidsintroducing too much background noise. Furthermore, we propose a multi-scalefusion framework to extract more contextual information and capture thefeatures of objects of different sizes. Experiments on the KITTI dataset showthat our method improves the performance of different baselines, especially onclasses of small size, including Pedestrian and Cyclist.

SDVRF: Sparse-to-Dense Voxel Region Fusion for Multi-modal 3D Object Detection