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

Bounded by the inherent ambiguity of depth perception, contemporarycamera-based 3D object detection methods fall into the performance bottleneck.Intuitively, leveraging temporal multi-view stereo (MVS) technology is thenatural knowledge for tackling this ambiguity. However, traditional attempts ofMVS are flawed in two aspects when applying to 3D object detection scenes: 1)The affinity measurement among all views suffers expensive computation cost; 2)It is difficult to deal with outdoor scenarios where objects are often mobile.To this end, we introduce an effective temporal stereo method to dynamicallyselect the scale of matching candidates, enable to significantly reducecomputation overhead. Going one step further, we design an iterative algorithmto update more valuable candidates, making it adaptive to moving candidates. Weinstantiate our proposed method to multi-view 3D detector, namely BEVStereo.BEVStereo achieves the new state-of-the-art performance (i.e., 52.5% mAP and61.0% NDS) on the camera-only track of nuScenes dataset. Meanwhile, extensiveexperiments reflect our method can deal with complex outdoor scenarios betterthan contemporary MVS approaches. Codes have been released athttps://github.com/Megvii-BaseDetection/BEVStereo.

BEVStereo: Enhancing Depth Estimation in Multi-view 3D Object Detection with Dynamic Temporal Stereo