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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Lidars and cameras are critical sensors that provide complementaryinformation for 3D detection in autonomous driving. While most prevalentmethods progressively downscale the 3D point clouds and camera images and thenfuse the high-level features, the downscaled features inevitably lose low-leveldetailed information. In this paper, we propose Fine-Grained Lidar-CameraFusion (FGFusion) that make full use of multi-scale features of image and pointcloud and fuse them in a fine-grained way. First, we design a dual pathwayhierarchy structure to extract both high-level semantic and low-level detailedfeatures of the image. Second, an auxiliary network is introduced to guidepoint cloud features to better learn the fine-grained spatial information.Finally, we propose multi-scale fusion (MSF) to fuse the last N feature maps ofimage and point cloud. Extensive experiments on two popular autonomous drivingbenchmarks, i.e. KITTI and Waymo, demonstrate the effectiveness of our method.

FGFusion: Fine-Grained Lidar-Camera Fusion for 3D Object Detection