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

This paper addresses the challenging unsupervised scene flow estimationproblem by jointly learning four low-level vision sub-tasks: optical flow$\textbf{F}$, stereo-depth $\textbf{D}$, camera pose $\textbf{P}$ and motionsegmentation $\textbf{S}$. Our key insight is that the rigidity of the sceneshares the same inherent geometrical structure with object movements and scenedepth. Hence, rigidity from $\textbf{S}$ can be inferred by jointly coupling$\textbf{F}$, $\textbf{D}$ and $\textbf{P}$ to achieve more robust estimation.To this end, we propose a novel scene flow framework named EffiScene withefficient joint rigidity learning, going beyond the existing pipeline withindependent auxiliary structures. In EffiScene, we first estimate optical flowand depth at the coarse level and then compute camera pose byPerspective-$n$-Points method. To jointly learn local rigidity, we design anovel Rigidity From Motion (RfM) layer with three principal components:\emph{}{(i)} correlation extraction; \emph{}{(ii)} boundary learning; and\emph{}{(iii)} outlier exclusion. Final outputs are fused based on the rigidmap $M_R$ from RfM at finer levels. To efficiently train EffiScene, two newlosses $\mathcal{L}_{bnd}$ and $\mathcal{L}_{unc}$ are designed to preventtrivial solutions and to regularize the flow boundary discontinuity. Extensiveexperiments on scene flow benchmark KITTI show that our method is effective andsignificantly improves the state-of-the-art approaches for all sub-tasks, i.e.optical flow ($5.19 \rightarrow 4.20$), depth estimation ($3.78 \rightarrow3.46$), visual odometry ($0.012 \rightarrow 0.011$) and motion segmentation($0.57 \rightarrow 0.62$).

EffiScene: Efficient Per-Pixel Rigidity Inference for Unsupervised Joint Learning of Optical Flow, Depth, Camera Pose and Motion Segmentation