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

Point cloud sequences are commonly used to accurately detect 3D objects inapplications such as autonomous driving. Current top-performing multi-framedetectors mostly follow a Detect-and-Fuse framework, which extracts featuresfrom each frame of the sequence and fuses them to detect the objects in thecurrent frame. However, this inevitably leads to redundant computation sinceadjacent frames are highly correlated. In this paper, we propose an efficientMotion-guided Sequential Fusion (MSF) method, which exploits the continuity ofobject motion to mine useful sequential contexts for object detection in thecurrent frame. We first generate 3D proposals on the current frame andpropagate them to preceding frames based on the estimated velocities. Thepoints-of-interest are then pooled from the sequence and encoded as proposalfeatures. A novel Bidirectional Feature Aggregation (BiFA) module is furtherproposed to facilitate the interactions of proposal features across frames.Besides, we optimize the point cloud pooling by a voxel-based samplingtechnique so that millions of points can be processed in several milliseconds.The proposed MSF method achieves not only better efficiency than othermulti-frame detectors but also leading accuracy, with 83.12% and 78.30% mAP onthe LEVEL1 and LEVEL2 test sets of Waymo Open Dataset, respectively. Codes canbe found at \url{https://github.com/skyhehe123/MSF}.

MSF: Motion-guided Sequential Fusion for Efficient 3D Object Detection from Point Cloud Sequences