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 presents an investigation into the estimation of optical and sceneflow using RGBD information in scenarios where the RGB modality is affected bynoise or captured in dark environments. Existing methods typically rely solelyon RGB images or fuse the modalities at later stages, which can result in loweraccuracy when the RGB information is unreliable. To address this issue, wepropose a novel deep neural network approach named FusionRAFT, which enablesearly-stage information fusion between sensor modalities (RGB and depth). Ourapproach incorporates self- and cross-attention layers at different networklevels to construct informative features that leverage the strengths of bothmodalities. Through comparative experiments, we demonstrate that our approachoutperforms recent methods in terms of performance on the synthetic datasetFlyingthings3D, as well as the generalization on the real-world dataset KITTI.We illustrate that our approach exhibits improved robustness in the presence ofnoise and low-lighting conditions that affect the RGB images. We release thecode, models and dataset at https://github.com/jiesico/FusionRAFT.

Attentive Multimodal Fusion for Optical and Scene Flow