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

Reconstructing 3D vehicles from noisy and sparse partial point clouds is ofgreat significance to autonomous driving. Most existing 3D reconstructionmethods cannot be directly applied to this problem because they are elaboratelydesigned to deal with dense inputs with trivial noise. In this work, we proposea novel framework, dubbed MV-DeepSDF, which estimates the optimal SignedDistance Function (SDF) shape representation from multi-sweep point clouds toreconstruct vehicles in the wild. Although there have been some SDF-basedimplicit modeling methods, they only focus on single-view-based reconstruction,resulting in low fidelity. In contrast, we first analyze multi-sweepconsistency and complementarity in the latent feature space and propose totransform the implicit space shape estimation problem into an element-to-setfeature extraction problem. Then, we devise a new architecture to extractindividual element-level representations and aggregate them to generate aset-level predicted latent code. This set-level latent code is an expression ofthe optimal 3D shape in the implicit space, and can be subsequently decoded toa continuous SDF of the vehicle. In this way, our approach learns consistentand complementary information among multi-sweeps for 3D vehicle reconstruction.We conduct thorough experiments on two real-world autonomous driving datasets(Waymo and KITTI) to demonstrate the superiority of our approach overstate-of-the-art alternative methods both qualitatively and quantitatively.

MV-DeepSDF: Implicit Modeling with Multi-Sweep Point Clouds for 3D Vehicle Reconstruction in Autonomous Driving