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

One of the key problems in 3D object detection is to reduce the accuracy gapbetween methods based on LiDAR sensors and those based on monocular cameras. Arecently proposed framework for monocular 3D detection based on Pseudo-Stereohas received considerable attention in the community. However, so far these twoproblems are discovered in existing practices, including (1) monocular depthestimation and Pseudo-Stereo detector must be trained separately, (2) Difficultto be compatible with different stereo detectors and (3) the overallcalculation is large, which affects the reasoning speed. In this work, wepropose an end-to-end, efficient pseudo-stereo 3D detection framework byintroducing a Single-View Diffusion Model (SVDM) that uses a few iterations togradually deliver right informative pixels to the left image. SVDM allows theentire pseudo-stereo 3D detection pipeline to be trained end-to-end and canbenefit from the training of stereo detectors. Afterwards, we further explorethe application of SVDM in depth-free stereo 3D detection, and the finalframework is compatible with most stereo detectors. Among multiple benchmarkson the KITTI dataset, we achieve new state-of-the-art performance.

SVDM: Single-View Diffusion Model for Pseudo-Stereo 3D Object Detection