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

3D scene flow characterizes how the points at the current time flow to thenext time in the 3D Euclidean space, which possesses the capacity to inferautonomously the non-rigid motion of all objects in the scene. The previousmethods for estimating scene flow from images have limitations, which split theholistic nature of 3D scene flow by estimating optical flow and disparityseparately. Learning 3D scene flow from point clouds also faces thedifficulties of the gap between synthesized and real data and the sparsity ofLiDAR point clouds. In this paper, the generated dense depth map is utilized toobtain explicit 3D coordinates, which achieves direct learning of 3D scene flowfrom 2D images. The stability of the predicted scene flow is improved byintroducing the dense nature of 2D pixels into the 3D space. Outliers in thegenerated 3D point cloud are removed by statistical methods to weaken theimpact of noisy points on the 3D scene flow estimation task. Disparityconsistency loss is proposed to achieve more effective unsupervised learning of3D scene flow. The proposed method of self-supervised learning of 3D scene flowon real-world images is compared with a variety of methods for learning on thesynthesized dataset and learning on LiDAR point clouds. The comparisons ofmultiple scene flow metrics are shown to demonstrate the effectiveness andsuperiority of introducing pseudo-LiDAR point cloud to scene flow estimation.

3D Scene Flow Estimation on Pseudo-LiDAR: Bridging the Gap on Estimating Point Motion